JP2001051338A - Camera - Google Patents

Abstract

PROBLEM TO BE SOLVED: To execute the recording action of a subject when the face of the subject is turned in a prescribed direction by recognizing the direction of the face. SOLUTION: This camera is provided with a field image detection means 8 detecting the image information on a field, a face recognition means 21 recognizing the face of a subject based on the image information from the detection means 8, a decision means 22 deciding whether the face is turned in a prescribed direction or not based on information from the recognition means 21, and a control means 23 executing the recording action for the subject according to the decided result of the decision means 22.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a camera capable of recognizing a situation of a subject by image.

[0002]

2. Description of the Related Art 1) Conventionally, as shown in Japanese Patent Application Laid-Open No. Hei 7-128711, a person who is a subject is conscious of the fact that the subject is being photographed so as to avoid an unnatural expression. If the photographing lens of the camera is correctly pointed at the subject without looking through the viewfinder of the camera in order to take a good photograph without realizing it, the photographer can sense by sound or light and take a picture. Alternatively, some cameras automatically take a picture when the camera faces the subject.

2) Conventionally, JP-A-3-252775, JP-A-8-249647, JP-A-8-249453,
There have been some techniques for recognizing facial expressions, such as Japanese Patent Application Laid-Open No. H10-255043, but none have been linked to camera functions.

[0004] 3) In order to perform a photographing operation of the camera when a subject enters a specific position in the viewfinder of the camera in photographing a wild animal or the like, an infrared ray projecting / receiving device is provided so as to sandwich the specific position. In some cases, a shooting command is issued as a remote control signal when a subject crosses between the infrared light projecting / receiving devices.

4) Also, as shown in Japanese Patent Application Laid-Open No. 57-115524, when a moving subject arrives at a preset distance position, the focus is automatically detected and the shutter release mechanism is activated. There was something to activate.

[0006]

However, according to the conventional technique 1), even if the subject can be captured in the photographing screen, whether the subject is facing the camera firmly, If you are looking directly into the camera's viewfinder, you must determine if the camera is closed or if the line of sight is facing the camera by the photographer's eyes a considerable distance from the camera's position. There is a disadvantage that the probability of failure is higher than that of

The technique of (2) for recognizing the facial expression of the related art is not applied to the function of the camera, so that the photographer can still determine whether or not to photograph by looking at the facial expression of the subject. For those who want to take pictures automatically with as little effort as possible, there is an inconvenience of being troublesome. In addition, there was also a disadvantage that it was not possible to respond to a request for unattended shooting of a good expression. Furthermore, there was no idea of a production aiming at the effect of raising the atmosphere according to the facial expression.

In the conventional technique (3), infrared rays
Automatic photographing is possible only at the place where the light receiving device is installed, and there is a disadvantage that the degree of freedom of photographing is small and the device becomes large.

In the prior art (4), when another object is present near or suddenly in the vicinity of the target object, another object arrives at a previously set distance position. Thus, there is an inconvenience that the target object is not focused and another subject is focused.

(Object of the Invention) A first object of the present invention is to provide a camera capable of recognizing the direction of a face of a subject and performing a subject recording operation when the face is oriented in a predetermined direction. Is what you do.

A second object of the present invention is to provide a camera capable of recognizing the state of the eyes of a subject and performing a subject recording operation when the eyes are in a predetermined state.

A third object of the present invention is to provide a camera capable of recognizing the facial expression of a subject and performing a subject recording operation when the face has a predetermined facial expression.

A fourth object of the present invention is to provide a camera capable of recognizing the posture of a subject and performing a subject recording operation when the subject has a predetermined posture.

A fifth object of the present invention is to provide a camera capable of recognizing a motion of a subject and performing a subject recording operation when the subject performs a predetermined operation.

A sixth object of the present invention is to provide a camera capable of recognizing a facial expression of a subject and changing the brightness of a subject recording screen when the face has a predetermined facial expression. Things.

A seventh object of the present invention is to provide a camera capable of recognizing a facial expression of a subject and, when the face has a predetermined facial expression, photographing a text or a character matching the facial expression. Is what you do.

An eighth object of the present invention is to provide a camera capable of recognizing the facial expression of a subject and, when the face has a predetermined facial expression, changing the screen to a color suitable for the facial expression. Is what you do.

[0018]

According to a first aspect of the present invention, there is provided an object image detecting means for detecting image information of an object scene, and an object image detecting means for detecting image information of the object scene. Face recognition means for recognizing a face of a subject based on image information from the image detection means; determination means for determining whether the face is oriented in a predetermined direction based on information from the face recognition means; A camera having control means for performing a subject recording operation according to the result.

In order to achieve the second object,
According to a second aspect of the present invention, there is provided an object scene image detecting means for detecting image information of an object scene, and an eye recognizing means for recognizing an eye of a subject based on image information from the object scene image detecting means. A camera having a determination unit for determining whether the eyes are in a predetermined state based on information from the eye recognition unit, and a control unit for performing a subject recording operation in accordance with a determination result of the determination unit It is.

In order to achieve the third object,
According to a third aspect of the present invention, there is provided a scene image detecting means for detecting image information of a scene, and a facial expression recognition for recognizing a facial expression of a subject based on the image information from the scene image detecting means. Means,
The present invention is a camera having a determining means for determining whether a predetermined facial expression is obtained based on information from the facial expression recognizing means, and a control means for performing a subject recording operation according to the determination result of the determining means.

In order to achieve the fourth object,
According to a fourth aspect of the present invention, there is provided an object scene image detecting means for detecting image information of a scene, and a posture recognizing means for recognizing a posture of a subject based on image information from the scene image detecting means. A camera having: a determination unit that determines whether the vehicle is in a predetermined posture based on information from the posture recognition unit; and a control unit that performs a subject recording operation in accordance with a determination result of the determination unit. .

In order to achieve the fifth object,
According to a fifth aspect of the present invention, there is provided an object image detecting means for detecting image information of an object field, and an operation recognizing means for recognizing an operation of a subject based on image information from the object image detecting means. A camera having: a determination unit that determines whether or not a predetermined operation is performed based on information from the operation recognition unit; and a control unit that performs a subject recording operation in accordance with a determination result of the determination unit. .

In order to achieve the sixth object,
According to a sixth aspect of the present invention, there is provided an object scene image detecting means for detecting image information of an object scene, and facial expression recognition for recognizing a facial expression of a subject based on image information from the object scene image detecting means. Means,
A camera having a determining means for determining whether a predetermined facial expression is obtained based on information from the facial expression recognizing means, and a control means for changing brightness of a subject recording screen according to a determination result of the determining means. It is.

Also, in order to achieve the seventh object,
According to a seventh aspect of the present invention, there is provided a scene image detecting means for detecting image information of a scene, and a facial expression recognition for recognizing a facial expression of a subject based on the image information from the scene image detecting means. Means,
Determining means for determining whether a given facial expression is obtained based on the information from the facial expression recognizing means; text / character generating means for generating a text or a character; Together with control means for performing a recording operation for recording.

In order to achieve the eighth object,
According to an eighth aspect of the present invention, there is provided a scene image detecting means for detecting image information of a scene, and a facial expression recognition for recognizing a facial expression of a subject based on the image information from the scene image detecting means. Means,
Determining means for determining whether a predetermined facial expression has been obtained based on information from the facial expression recognizing means; screen color changing means for changing a color of a recording screen; and a screen color changed according to the determination result of the determining means And a control means for performing a recording operation of recording the image together with the subject.

[0026]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described in detail based on embodiments with reference to the drawings.

FIG. 1 is a central longitudinal sectional view showing a camera common to each embodiment of the present invention, and FIG. 2 is a block diagram showing a configuration of a main part according to the first embodiment of the present invention. .

In these figures, 1 is a camera body,
Reference numeral 2 denotes a photographing lens. Reference numeral 3 denotes a main mirror having a half mirror near the photographing optical axis. The main mirror 3 is bonded and fixed to a main mirror receiving plate 4 (having an opening near the photographing optical axis), and has a shaft 4a provided on the main mirror receiving plate 4. The mirror can be pivoted from the observation state in which the mirror is lowered to the center in FIG. In the observation state where the mirror is down, the subject light passing through the taking lens is 45
The light is reflected upward, forms an image on the focus plate 5, becomes an erect image by the penta roof prism 6, and is observed by the photographer through the eyepiece 7. Reference numeral 8 denotes a scene image detection unit including a CCD (solid-state imaging device), which also functions as a photometric sensor. Reference numeral 9 denotes a field image detection lens which forms an image formed on the focus plate 5 on the sensor surface of the field image detection means 8.

Reference numeral 10 denotes a sub-mirror, which is adhered and supported by the sub-mirror receiving plate 11, and is rotatably supported by a shaft 11a of the sub-mirror receiving plate 11. The sub-mirror 10 guides the subject light that has passed through the half mirror section near the photographic optical axis of the main mirror 3 in the mirror-down observation state of FIG. 1 to a focus detection section arranged below the camera, and the sub-mirror receiving plate 4 is a mirror (not shown). In the retracted state outside the imaging optical path, it acts so as to close the opening near the imaging optical axis of the main mirror receiving plate 4. 12 is a field lens of a focus detection optical system, 13 is a reflection mirror, 1
Reference numeral 4 denotes a secondary imaging lens of a focus detection optical system, 15 denotes a focus detection sensor of a known passive autofocus phase difference detection system, 16 denotes a focal plane shutter, 17 denotes a lens aperture, and 18 denotes a film.

Numeral 19 shown in FIG.
Indicates a state in which the person as the subject is facing the front, 19b
Indicates a state in which the person as the subject is facing sideways (not facing the front). Reference numeral 20 denotes a CPU for controlling the entire camera.
A face recognizing means 21 for recognizing a face of a subject based on image information from the camera, a determining means 22 for determining whether a face is oriented in a predetermined direction based on information from the face recognizing means 21, Has a subject recording operation control means 23 for performing a subject recording operation in accordance with the determination result. Reference numeral 24 denotes a camera exposure function unit, which includes a lens aperture 17 and a focal plane shutter 16.

An iR 25 shown in FIG. 1 is provided near the optical axis of the photographing optical system and projects near-infrared light in the same direction as the optical axis of the photographing optical system.
Reference numerals ED and 26 denote near-infrared light transmitting visible light cut filters which enter the front surface of the object scene image detecting means 8 composed of a CCD by an advance / retreat mechanism (not shown) in synchronization with the projection of the iRED 25.
Reference numeral 7 denotes a known date module for imprinting a date and a caption from the back of the film. Numeral 28 denotes an effect filter, which is provided so that the taking lens can enter the light beam and retreat outside the light beam by an actuator (not shown) and an advancing / retracting mechanism (not shown), so that at least two different filters can be selected. I have.

Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.

When a main switch (not shown) is turned on in step 1, power is supplied to the camera, and the camera enters a photographing preparation initial state. Then, in step 2, the CPU 20
Determines whether the release button (not shown) of the camera is pressed to the first stroke and the switch SW-1 is turned on.
If N, go to step 3. Also, the switch SW-1
If is OFF, jump to step 10.

In step 3, the CPU 20 sets the CC
The photometric output from the object scene image detecting means 8 comprising D is taken in, photometric calculation is performed, and an exposure control value is determined. And
In the next step 4, focus detection calculation is performed from the output of the focus detection sensor 15 of the passive autofocusing device of the known phase difference detection type, and the photographing lens drive amount for focusing is determined. In the following step 5, the focus adjusting lens 2a of the photographing lens 2 is driven based on the photographing lens drive amount obtained in step 4 to adjust the focus. Then, in the next step 6, the CPU 20 converts the one-frame image into a 1/30 second video image to the object image detecting means 8 comprising a CCD by focusing the object image on the object which the photographer may have aimed at. Sequentially take in at the rate.

In the next step 7, the face recognizing means 2
1 recognizes a human face from the captured object scene image, and determines whether the recognized human face is facing front by the determining means 22. If the subject person of the scene image is facing the front as in 19a in FIG.
If it is not facing the front as in 9b, the process returns to step 2.

A method of extracting a person image facing the front from the scene image (the face recognition means 21 and the judgment means 22)
The following methods (a) to (c) are known, and in the first embodiment, any one of the methods is used.

(A) Journal of the Institute of Television Engineers of Japan, Vol. 49, No.
6, pp. 787-797 (1995), as shown in “Proposal of a modified HSV color system effective for face area extraction”, a color image is converted into a mosaic image, and a face area is extracted by focusing on a skin color area. Technique.

(B) IEICE Journal Vol. J74-D
-II, No. 11, pp. 1625-1627 (1991), the head of a front human image such as hair, eyes, mouth, etc. A method for extracting the head region of a frontal human image using the geometric shape characteristics of each part to be performed.

(C) Image Lab 1991-11 (199)
As shown in 1) “Videophone face area detection and its effect”, in the case of a moving image, a frontal person image is extracted using a contour edge of a person image generated by a subtle movement of a person between frames. Technique to do.

In step 8, the subject recording operation control means 23 controls the aperture diameter of the aperture 17 and the shutter speed of the focal plane shutter 16 based on the exposure control value determined in step 3 above. , Film 1
Exposure to 8 is performed. Then, in the next step 9,
The film is wound up by one frame, and the film returns to step 2 when the winding of the film is completed in preparation for the next photographing.

In step 2 above, the switch SW-1 is set to O
If the process proceeds to step 10 as FF, here, CP
U20 goes to see the state of the photometry timer (timer that keeps the photometry enabled state for a predetermined time so that the exposure setting can be changed without pressing the release button and holding the switch SW-1 ON), and is operating. Then step 2
Return to If the predetermined time has elapsed and the operation has not been performed, the operation proceeds to step 11, where the state of the main switch (not shown) is checked. If the operation is ON, the operation returns to step 2 and repeats. On the other hand, if it is OFF, the process proceeds to step 12, and the power supply to the camera is cut off.

According to the first embodiment described above, the direction of the face of the subject is recognized, and the subject recording operation is performed when the face faces a predetermined direction, especially when facing the front. This is effective in preventing a failed photograph in which the subject person is not facing the camera properly.

(Second Embodiment) FIG. 4 is a block diagram showing a circuit configuration of a main part of a camera according to a second embodiment of the present invention. FIG. 5 is a block diagram showing a second embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are denoted by the same numbers, and corresponding parts are denoted by numbers obtained by adding 200 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 4, reference numeral 219 denotes a scene image;
Reference numeral 219a denotes a state in which the subject person opens his / her eyes and looks at the camera, 219b denotes a state in which the subject person has his eyes closed, and 219c denotes a state in which the subject person has his eyes opened. Respectively, but not looking at the camera. Reference numeral 220 denotes a CPU for controlling the entire camera, in which an eye recognizing means 22 for recognizing the eyes of the subject based on image information from the scene image detecting means 8
A determination unit 2 that determines whether the eye is in a specific state (for example, whether the eye is open or the line of sight is facing the camera) based on the information from the eye recognition unit 221 and the information from the eye recognition unit 221.
22, and control means 223 for performing a subject recording operation in accordance with the result of the determination by the determination means 222.

Next, the operation of the main part of the camera having the above configuration will be described with reference to the flowchart of FIG.

Steps 201 to 205 are the same as steps 1 to 5 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 206, CPU 200
Causes a scene image focused on a subject which may be aimed at by the photographer to be sequentially captured by a scene image detecting means 8 comprising a CCD at a video rate of 1/30 sec. Also,
The pupil has the property of reflecting incident light in substantially the same direction, and the brightness of the coaxial illumination state is remarkably large compared to other parts of the face, and only the pupil is imaged brightly even with weak near-infrared light Is done. Accordingly, the near infrared light is projected onto the subject by the iRED 25, and the object image transmitted through the near infrared light transmitting visible light cut filter 26 is converted into one frame by the object image detecting means 8 for 1/30 second video. If the images are sequentially taken in at a rate, an eye image can be obtained more effectively.

In the next step 207, the eye recognizing means 221 recognizes human eyes from the captured scene image,
The determination unit 222 determines whether the recognized person's eyes are open and whether the eyes are facing the camera. If the eyes of the person who is the subject of the scene image are open, as in 219a or 219c in FIG. 4, the process proceeds to step 208, and if the eyes are closed as in 219b, the process returns to step 202. Alternatively, if the eyes of the person who is the subject of the scene image are open as shown at 219a in FIG. 4 and the eyes are facing the camera, the process proceeds to step 208, and the eyes are opened as at 219c. However, if the user is not looking at the camera or his eyes are closed as in 219b, the process may return to step 202.

The method of extracting the eyes of the person (and the direction of the line of sight (the line of sight)) from the scene image (performed by the eye recognizing means 221 and the determining means 222) is as follows (d) to (d). The method of h) is known, and in the second embodiment, any one of the methods is used.

(D) As shown in JP-A-3-17696, an eye region is divided by a vertical line and a horizontal line passing through the center of a pupil, and a viewpoint position is calculated using an area ratio of the divided regions as a feature amount. Technique.

(E) As shown in Japanese Patent Application Laid-Open No. 4-255015, a method of extracting the relative movement amount of the line of sight by extracting contour data of the pupil and changing the center coordinates of the pupil.

(F) As shown in JP-A-5-300601, a method of projecting infrared light onto a face and extracting an eyeball having a particularly high reflectance.

(G) As shown in Japanese Patent Application Laid-Open No. 9-21611, a method of irradiating near-infrared light substantially coaxially with a photographic lens to a subject, detecting high-brightness reflection of a pupil, and extracting eyes. .

(H) As shown in JP-A-9-251342, the obtained image is divided into regions, and a face region is found from the hue and saturation information of each region. Next, by binarizing the hue image, candidates for an eye portion and a mouth portion having color attributes different from those of the skin color portion are obtained, and collation with the light and shade pattern of the eyes and the mouth is performed to determine an eye region and a mouth region. And the detected eyes,
An edge image is generated for the mouth, and the edge image is vertically mapped in a one-dimensional axial direction to detect the inner corner of the eye and the left and right mouths.
Further, the cutout image of the eye is binarized, the center of gravity of the black pixel is set as the center of gravity of the pupil, and the pupil vector is obtained from the inner corner of the eye. Finally, the point of gaze is determined from the position of the eyes in the face direction. That technique.

Steps 208 to 212 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the second embodiment, the state of the subject's eyes is recognized, and when the eyes are in a predetermined state, especially when the eyes are opened firmly and the eyes are facing the camera, the subject is recognized. Since the recording operation is performed, there is an effect that the photographer does not place a burden on the photographer and prevents a failed photograph in which the person who is the subject has closed his eyes or is not looking at the camera properly.

(Third Embodiment) FIG. 6 is a block diagram showing a circuit configuration of a main part of a camera according to a third embodiment of the present invention, and FIG. 7 is a block diagram showing a third embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and corresponding parts are indicated by numbers obtained by adding 300 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 6, reference numeral 319 denotes a scene image.
Reference numeral 319a denotes a state in which the person who is the subject has no expression;
b indicates the state of joy that the subject person is smiling, 31
9c shows the state of sadness in which the subject person is crying,
319d shows the state of anger of the subject, 319e.
Indicates the state of surprise of the person who is the subject. Reference numeral 320 denotes a CPU that controls the entire camera, and includes a facial expression recognition unit 321 that recognizes a facial expression of a subject based on image information from the scene image detection unit 8, and information from the facial expression recognition unit 321. Facial expressions are in certain states (for example,
A determination unit 322 for determining whether the user is in a state of joy, sadness, anger, or surprise), and a control unit 323 for performing a subject recording operation according to the determination result of the determination unit 322.

Next, the operation of the main part of the camera having the above configuration will be described with reference to the flowchart of FIG.

Steps 301 to 306 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 307, the facial expression recognizing means 321 recognizes the facial expression of the person from the captured scene image,
The determination unit 322 determines whether the recognized expression of the person is in a specific state (for example, a state of joy, sadness, anger, or surprise). As shown in 319b to 319e in FIG. 6, if the expression of the person who is the subject of the scene image is in a state of joy, sadness, anger, or surprise, the process proceeds to step 308; Step 30
Return to 2.

As a method of recognizing a facial expression of a person from the scene image (performed by the facial expression recognizing means 321 and the determining means 322), the following methods (i) to (k) are known. In the third embodiment, any one of the methods is used.

(I) As shown in Japanese Patent Application Laid-Open No. 3-252775, a module for measuring muscle movement is provided. With this module, learning based on the temporal change pattern of facial muscle movement is performed. In the mode, the standard expression pattern is learned and stored. In the recognition mode, the facial expression pattern based on the captured image is compared with the learned standard expression pattern to recognize the facial expression.

(J) As shown in Japanese Patent Application Laid-Open No. Hei 8-249449, the face image signal is subjected to wavelet transform, and the average power of the spatial frequency obtained thereby is compared with the average power in the absence of expression to recognize facial expressions. The technique of doing.

(K) As shown in JP-A-8-249453 and JP-A-10-255043, six types of basic facial expressions including anger, disgust, fear, sadness, happiness, and surprise are considered as facial expression categories. The processing of the time-series image from the non-expression to each basic expression is performed. For example, for two regions each including the right eye and the mouth, which are the regions that the person is most interested in reading the expression of the other party, using an optical flow algorithm from two consecutive images in the moving image of the human face To get the velocity vector. A discrete Fourier transform is applied to each component of the velocity vector, and a low-frequency component of a Fourier transform coefficient is extracted as a feature vector. Next, a method of calculating a feature vector generation probability using an HMM (Hidden Markov Model) and performing recognition processing.

Steps 308 to 312 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the third embodiment, the facial expression of a subject is recognized, and when the face has a predetermined facial expression, the facial expression is particularly interesting as a photograph such as joy, sadness, anger, or surprise. The subject recording operation is performed when
This eliminates the burden on the photographer and eliminates the need for taking ordinary photographs close to expressionlessness, which has the effect of increasing the probability of taking masterpieces.

(Fourth Embodiment) FIG. 8 is a block diagram showing a circuit configuration of a main part of a camera according to a fourth embodiment of the present invention, and FIG. 9 is a diagram showing a second embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and corresponding parts are indicated by numbers obtained by adding 400 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 8, reference numeral 419 denotes a scene image;
Reference numeral 419a denotes a state in which the subject is standing on a stick.
b shows a state in which the subject person is sitting with his cheek stick, and 419c shows a state in which the subject person raises one arm. Reference numeral 420 denotes a CPU for controlling the entire camera, in which a pose recognition unit 421 for recognizing a pose of a subject based on image information from the scene image detection unit 8 and information from the pose recognition unit 421 are used.
Judging means 422 for judging whether the pose is in a specific state (for example, sitting with a cheek stick, raising one arm, etc.), and further, control for performing a subject recording operation according to the judgment result of the judging means 422 It has means 423.

Next, the operation of the main part of the camera having the above configuration will be described with reference to the flowchart of FIG.

Steps 401 to 406 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 407, the pose recognizing means 421 recognizes the pose of the person from the captured scene image, and the determining means 422 determines that the recognized pose of the person is in a specific state (for example, when the cheek stick is held). (E.g., sitting in a protruding position, raising one arm, etc.). 419b in FIG. 8,
If the pose of the person who is the subject in the image of the scene is in a state of sitting with a cheek stick or raising one arm as in 419c, the process proceeds to step 408; otherwise, the process returns to step 402.

As a method of recognizing a pose from a scene image (performed by the pose recognizing unit 421 and the determining unit 422), the following method (m) is known, and In the mode 4, the method is used.

(M) As shown in JP-A-7-57103, the contour of a specific part of the imaged subject is extracted,
A method of performing pose recognition by comparing it with a stored pattern.

Steps 408 to 412 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the above-described fourth embodiment, the posture (pose) of the subject is recognized, and when the subject takes a predetermined posture (pose), particularly when the subject has an interesting characteristic pose as a photograph. Since the subject recording operation is performed in a short time, no burden is imposed on the photographer, and it is not necessary to take a photograph in a boring pose such as standing upright, which has the effect of increasing the probability of taking a masterpiece photograph.

(Fifth Embodiment) FIG. 10 is a block diagram showing a circuit configuration of a main part of a camera according to a fifth embodiment of the present invention, and FIG. 11 is a block diagram showing a fifth embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and the corresponding parts are indicated by numbers obtained by adding 500 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 10, reference numeral 519 denotes an object scene image, 519a shows a state in which a person as a subject stands and stands still, and 519b shows a state in which a person as a subject starts running. Reference numeral 520 denotes a CPU for controlling the entire camera, in which an operation recognizing unit 5 for recognizing a motion of a subject based on image information from the scene image detecting unit 8
21 and a determination unit 522 that determines whether the operation is in a specific state (for example, a running state) based on information from the operation recognition unit 521, and further, the determination unit 522.
Control means 52 for performing a subject recording operation according to the determination result of
3

Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.

Steps 501 to 506 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 507, the motion recognizing means 521 recognizes a human motion from the captured scene image,
The determining unit 522 determines whether the recognized motion of the person is in a specific state (for example, a running state). If the motion of the person who is the subject of the scene image starts running as in 519b, step 5 is executed.
08, otherwise return to step 502.

As a method of recognizing a motion from the scene image (performed by the motion recognizing means 521 and the determining means 522), the following method (n) is publicly known. In the fifth embodiment, the method is used.

(N) As shown in JP-A-7-57103, the outline of a specific part of the imaged subject is extracted,
A method of performing motion recognition by comparing it with a stored pattern.

Steps 508 to 512 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the fifth embodiment, the operation of the object is recognized, and the object recording operation is performed when the object performs a predetermined operation, especially when the object performs an interesting characteristic operation as a photograph. This eliminates the burden on the photographer and eliminates the need for taking a photo of a boring action close to a stick, which has the effect of increasing the probability of taking a masterpiece.

(Sixth Embodiment) FIG. 12 is a block diagram showing a circuit configuration of a main part of a camera according to a sixth embodiment of the present invention, and FIG. 13 shows a camera according to the sixth embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and the corresponding parts are indicated by numbers obtained by adding 600 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 12, reference numeral 619 denotes an object scene image, and 619a denotes a state in which a person who is a subject has no expression.
19b shows the state of joy that the subject person is smiling,
619c shows the state of sadness in which the subject person is crying, 619d shows the state of anger of the subject person, 61
Numeral 9e indicates the state of surprise of the person who is the subject. A CPU 620 controls the entire camera.
The facial expression recognition means 621 for recognizing the facial expression of the subject based on the image information from the object scene image detecting means 8 and the information from the facial expression recognition means 621 cause the facial expression to be in a specific state (for example, joy, sadness, etc.). ), And control means 623 for performing a subject recording operation in accordance with the determination result of the determination means 622.

Next, the operation of the main part of the camera having the above configuration will be described with reference to the flowchart of FIG.

Steps 601 to 606 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 607, the facial expression recognizing means 621 recognizes a human facial expression from the captured scene image,
The determining unit 622 determines whether the recognized expression of the person is in a specific state (for example, a state of joy).
If the expression of the person who is the subject of the scene image is in a joy state as in 619b, the process proceeds to step 608. Otherwise, go to step 609.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognizing means 621 and the determining means 622) is performed in the same manner as in the third embodiment described above. Will be

In step 608, a positive exposure correction is performed on the exposure control value determined in step 603 so that the photographing screen becomes brighter (so as to provide a bright atmosphere). Then, in the next step 609, the facial expression recognition means 621 recognizes the facial expression of the person from the captured scene image, and the determining means 622 determines that the recognized facial expression of the person is in a specific state (for example, sadness). State). If the expression of the person who is the subject of the scene image is in a sad state, as shown at 619c in FIG. 12, the process proceeds to step 610; otherwise, the process returns to step 602.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognizing means 621 and the determining means 622) is the same as that described in the step 607, in the third embodiment. It shall be performed by the same known method as that of the embodiment.

In step 610, a negative exposure correction is performed on the exposure control value determined in step 603 so that the photographing screen becomes dark (so as to give a dark atmosphere).

Steps 611 to 615 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the sixth embodiment, the facial expression of the subject is recognized, and when the face has a predetermined facial expression, the ambience of the photograph such as joy and sadness is particularly distinctive between bright and dark. Since the brightness of the subject recording screen is changed in accordance with the atmosphere when the expression becomes unnatural, the effect of raising the atmosphere created by the expression without imposing a burden on the photographer.

(Seventh Embodiment) FIG. 14 is a block diagram showing a circuit configuration of a main part of a camera according to a seventh embodiment of the present invention. FIG. 15 is a block diagram showing a seventh embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and corresponding parts are indicated by numbers obtained by adding 700 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 14, reference numeral 719 denotes a scene image, and reference numeral 719a denotes a state in which a person who is a subject has no expression.
19b shows the state of joy that the subject person is smiling,
Reference numeral 719c denotes a state of sadness in which the subject person is crying, and reference numeral 719d denotes a state of anger of the subject person.
Numeral 9e indicates the state of surprise of the person who is the subject. 720 is a CPU for controlling the entire camera,
The facial expression recognition means 721 for recognizing the facial expression of the subject based on the image information from the scene image detection means 8 and the information from the facial expression recognition means 721 indicate that the facial expression is in a specific state (for example, joy, sadness, An angry state) is provided, and a control unit 723 that performs a subject recording operation and a text character recording operation according to the determination result of the determination unit 722 is provided. 27 is text
This corresponds to a known date module for imprinting a date and a caption from the back of the film by the character generating means. Reference numeral 729 denotes a captured subject recorded image.

Next, the operation of the main part of the camera having the above configuration will be described with reference to the flowchart of FIG.

Steps 701 to 706 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 707, the facial expression recognizing means 721 recognizes the facial expression of a person from the captured scene image,
The determining unit 722 determines whether the recognized facial expression of the person is in a specific state (for example, a state of joy).
If the expression of the person who is the subject of the scene image is in a state of delight as shown at 719b in FIG. 14, the process proceeds to step 708; otherwise, the process proceeds to step 709.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognition means 721 and the determination means 722) is the same as that performed by the same known method as in the third embodiment. I do.

In step 708, a known date module 2 for imprinting a date and a caption, which are text / character generating means, from the back of the film.
7 is driven, and “♪ HAPPY” shown in 729b of FIG.
A text or character having a bright image such as “♪” is transferred to the film 18.

In step 709, the facial expression recognizing means 721 recognizes the human facial expression from the captured scene image,
The determination unit 722 determines whether the recognized facial expression of the person is in a specific state (for example, a sad state). If the expression of the person who is the subject of the scene image is in a sad state as in 719c in FIG. 14, the process proceeds to step 710; otherwise, the process proceeds to step 711.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognizing means 721 and the determining means 722) is the same as that of the third embodiment described in the step 707. It is performed in the same known manner.

In step 710, a known date module 2 for imprinting a date and a caption as text / character generating means from the back of the film.
7 is copied to the film 18 with text of comfort such as “★ Do not cry ★” shown in 729 c of FIG. 14 or text or characters of sad images such as “… lonely…” “sad yo”. Put in.

In step 711, the facial expression recognizing means 721 recognizes the facial expression of a person from the captured scene image,
The determining unit 722 determines whether the recognized facial expression of the person is in a specific state (for example, an angry state).
If the expression of the person who is the subject of the object scene image is in an angry state as in 719d in FIG. 14, the process proceeds to step 712; otherwise, the process returns to step 702.

The method of recognizing a person's facial expression from the scene image (performed by the facial expression recognizing means 721 and the determining means 722) is the same as that of the third embodiment described in the step 707. It shall be performed by the same known technique.

In step 712, a known date module 2 for imprinting a date and a caption as text / character generating means from the back of the film.
Driving 7 and relaxing text such as "Don't get angry" or "▲ Angry! ▲" shown in 729d in FIG.
Is printed on the film 18.

Steps 713 to 717 are the same as steps 8 to 12 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

According to the seventh embodiment, the facial expression of a subject is recognized, and when the face has a predetermined facial expression, the atmosphere of the photograph, such as joy, sadness, and anger, is particularly distinctive. Since the text and the character according to the mood are recorded together with the subject when the expression is obtained, the photographer has no effect on the photographer, and there is an effect of raising the mood created by the expression.

(Eighth Embodiment) FIG. 16 is a block diagram showing a circuit configuration of a main part of a camera according to an eighth embodiment of the present invention, and FIG. 17 is a block diagram showing an eighth embodiment of the present invention. It is a flowchart which shows operation | movement of a main part.

In these figures, the same parts as those in the first embodiment are indicated by the same numbers, and corresponding parts are indicated by numbers obtained by adding 800 to the numbers in the first embodiment. Here, only different points from the first embodiment will be described.

In FIG. 16, reference numeral 819 denotes an object scene image, and 819a denotes a state in which a person who is a subject has no expression.
19b shows the state of joy that the subject person is smiling,
819c indicates the state of sadness in which the subject person is crying, and 819d indicates the state of anger of the subject person.
Numeral 9e indicates the state of surprise of the person who is the subject. A CPU 820 controls the entire camera.
The expression recognition means 821 for recognizing the expression of the subject based on the image information from the scene image detection means 8 and the information from the expression recognition means 821 indicate that the expression is in a specific state (for example, joy, sadness, etc.). Anger state), and control means 823 for performing a subject recording operation and a screen color recording operation according to the determination result of the determination unit 822. 28 is a screen color changing means,
An effect filter is provided by an actuator (not shown) and an advancing / retracting mechanism (not shown) so that the taking lens can enter into the light beam and retreat outside the light beam. A filter that can produce an effect that matches the atmosphere can be selected. Reference numeral 829 denotes a captured subject recorded image.

Next, the operation of the main part of the camera in the above configuration will be described with reference to the flowchart of FIG.

Steps 801 to 806 are the same as steps 1 to 6 in FIG. 3 in the first embodiment, and a description thereof will be omitted.

In step 807, the facial expression recognizing means 821 recognizes a human facial expression from the captured scene image,
The determining unit 822 determines whether the recognized facial expression is in a specific state (for example, a state of joy).
As in 819b of FIG. 16, if the expression of the person who is the subject in the scene image is in a state of joy, the process proceeds to step 808; otherwise, the process proceeds to step 809.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognition means 821 and the determination means 822) is the same as that performed by the same known method as in the third embodiment. I do.

In step 808, the yellow-based effect filter of the screen color changing means 28 enters the luminous flux of the photographing lens, and a bright image screen such as the sun shines brightly as shown by 829b in FIG. The colors are transferred to the film 18.

In step 809, the facial expression recognizing means 821 recognizes the facial expression of the person from the captured scene image,
The determination unit 822 determines whether the recognized facial expression of the person is in a specific state (for example, a sad state). As in 819c in FIG. 16, if the expression of the person who is the subject of the scene image is in a sad state, the process proceeds to step 810; otherwise, the process proceeds to step 811.

The method of recognizing the facial expression of a person from the scene image (performed by the facial expression recognizing means 821 and the determining means 822) is the same as that described in the step 807, in the third embodiment. It is performed in the same manner as in the known method.

In step 810, the blue-based effect filter of the screen color changing means 28 is made to enter the light beam of the taking lens, as shown in 829c of FIG.
The sad and blue screen color is transferred to the film 18.

In step 811, the facial expression recognizing means 821 recognizes the facial expression of a person from the captured scene image.
The determining unit 822 determines whether the recognized facial expression of the person is in a specific state (for example, an angry state).
If the expression of the person who is the subject of the object scene image is in an angry state as in 819d in FIG. 16, the process proceeds to step 812, and otherwise returns to step 802.

The method of recognizing the facial expression of the person from the scene image (performed by the facial expression recognizing means 821 and the determining means 822) is the same as that described in the step 807, in the third embodiment. It shall be performed by the same known method as that of the embodiment.

In step 812, the effect filter based on the red color of the screen color changing means 28 is made to enter the luminous flux of the photographing lens, and as shown in 829d of FIG.
The color of the screen, which resembles an anger like a fiery burning flame, is transferred to the film 18.

In step 813, the control means 823 for performing the subject recording operation and the screen color recording operation based on the exposure control value determined in step 803 makes the aperture diameter of the aperture 17 and the shutter of the focal plane shutter 16. The time is controlled to expose the film 18. Then, in the next step 814, after retracting the effect filter out of the luminous flux of the photographing lens, the film is wound up by one frame to prepare for the next photographing. After the winding of the film is completed, the process returns to step 802.

Steps 815 to 817 correspond to step 10 in FIG. 3 in the first embodiment.
To step 12 and the description is omitted.

In the eighth embodiment,
A well-known optical filter, such as a soft focus for softening the screen or a foggy light for fog, in order to record the atmosphere that matches the expression on the screen, although the screen color has been changed. The special effects performed in the above may be provided, or a pattern may be added to the screen.

According to the eighth embodiment described above, the facial expression of the subject is recognized, and when the face has a predetermined facial expression, the feature that the atmosphere of the photograph such as joy, sadness, and anger is particularly clear is obtained. Since the screen color changed according to the atmosphere when the user has the facial expression is recorded together with the subject, there is an effect that the atmosphere created by the facial expression is raised without putting a burden on the photographer.

(Modification) In each of the above embodiments, a CCD (solid-state image sensor) is provided instead of the film 18,
By providing known digital camera components such as an image sensor driving circuit, a digital image processing circuit, and an image storage unit, the present invention can be applied not only to a silver halide camera but also to an electronic still camera. For example, as the means for changing the brightness of the subject recording screen according to the sixth embodiment, a method of changing the gain of a CCD (solid-state image sensor) instead of a film, in addition to the method of changing the exposure with an aperture and a shutter. There is also.

The text character generating means of the seventh embodiment has a text character ROM, and can read text and characters read from the ROM by known image synthesis during digital image processing. It is conceivable that the recording operation is performed while overlapping the subject.

Similarly, as the screen color changing means of the eighth embodiment, it is conceivable to change the screen color by a known color adjustment during digital image processing and record the image together with the subject. Furthermore, it is also possible to give a special effect or to add a pattern by a known image synthesis.

[0139]

As described above, according to the first aspect of the present invention, the orientation of the face of the subject can be recognized, and the subject recording operation can be performed when the face is oriented in a predetermined direction. A camera can be provided.

According to the second aspect of the present invention, it is possible to provide a camera capable of recognizing a state of an eye of a subject and performing a subject recording operation when the eye enters a predetermined state. is there.

According to the third aspect of the present invention, it is possible to provide a camera capable of recognizing a facial expression of a subject and performing a subject recording operation when the face has a predetermined facial expression. is there.

According to the fourth aspect of the present invention, it is possible to provide a camera capable of recognizing a posture of a subject and performing a subject recording operation when the subject takes a predetermined posture.

According to the fifth aspect of the present invention, it is possible to provide a camera capable of recognizing a motion of a subject and performing a subject recording operation when the subject performs a predetermined operation.

According to the sixth aspect of the present invention, there is provided a camera capable of recognizing a facial expression of a subject and changing the brightness of a subject recording screen when the face has a predetermined facial expression. It can be provided.

According to the seventh aspect of the present invention, a camera capable of recognizing a facial expression of a subject and, when the face has a predetermined facial expression, imprinting a text or a character matching the facial expression. Can be provided.

According to the present invention, a camera capable of recognizing a facial expression of a subject and changing the screen to a color matching the facial expression when the facial expression has a predetermined facial expression. Can be provided.

[Brief description of the drawings]

FIG. 1 is a central vertical sectional view showing a camera common to each embodiment of the present invention.

FIG. 2 is a block diagram illustrating a circuit configuration of a main part of the camera according to the first embodiment of the present invention.

FIG. 3 is a flowchart illustrating an operation of a main part of the camera according to the first embodiment of the present invention.

FIG. 4 is a block diagram illustrating a circuit configuration of a main part of a camera according to a second embodiment of the present invention.

FIG. 5 is a flowchart illustrating an operation of a main part of a camera according to a second embodiment of the present invention.

FIG. 6 is a block diagram illustrating a circuit configuration of a main part of a camera according to a third embodiment of the present invention.

FIG. 7 is a flowchart illustrating an operation of a main part of a camera according to a third embodiment of the present invention.

FIG. 8 is a block diagram showing a circuit configuration of a main part of a camera according to a fourth embodiment of the present invention.

FIG. 9 is a flowchart illustrating an operation of a main part of a camera according to a fourth embodiment of the present invention.

FIG. 10 is a block diagram showing a circuit configuration of a main part of a camera according to a fifth embodiment of the present invention.

FIG. 11 is a flowchart illustrating an operation of a main part of a camera according to a fifth embodiment of the present invention.

FIG. 12 is a block diagram showing a circuit configuration of a main part of a camera according to a sixth embodiment of the present invention.

FIG. 13 is a flowchart illustrating an operation of a main part of a camera according to a sixth embodiment of the present invention.

FIG. 14 is a block diagram showing a circuit configuration of a main part of a camera according to a seventh embodiment of the present invention.

FIG. 15 is a flowchart illustrating an operation of a main part of a camera according to a seventh embodiment of the present invention.

FIG. 16 is a block diagram showing a circuit configuration of a main part of a camera according to an eighth embodiment of the present invention.

FIG. 17 is a flowchart showing an operation of a main part of a camera according to an eighth embodiment of the present invention.

[Explanation of symbols]

8 CCD image field detection means 20, 220, 320, 420 CPU 21 Face recognition means 22, 222, 322, 422 Judgment means 23, 223, 323, 423 Subject recording operation control means 24 Camera exposure function unit 27 Text Character generating means (date module) 28 screen color changing means (effect filter) 221 eye recognizing means 321, 621, 721, 821 facial expression recognizing means 421 pose recognizing means 520, 620, 720, 820 CPU 521 action recognizing means, 522 622, 722, 822 determination means 523, 623 subject recording operation control means 723 subject & text / character recording operation control means 823 subject & screen color recording operation control means

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 2H020 MA07 MC62 MC77 MC79 MD00 5C022 AA11 AB03 AB28 AC02 AC42 AC52 AC54 AC55 AC69 AC73 CA00 5L096 BA18 CA02 FA06 FA59 FA62 FA67 FA81 HA02 HA04 HA08 KA04 9A001 HH21 KK42

Claims (8)

[Claims] 1. An object image detecting means for detecting image information of an object scene, a face recognizing means for recognizing a face of a subject based on image information from the object image detecting means, A camera comprising: a determination unit that determines whether a face is facing in a predetermined direction based on information from the unit; and a control unit that performs a subject recording operation according to a determination result of the determination unit. 2. An object image detecting means for detecting image information of an object scene, an eye recognizing means for recognizing an eye of a subject based on image information from the object image detecting means, and an eye recognizing means. A camera comprising: determining means for determining whether an eye is in a predetermined state based on information from the means; and control means for performing a subject recording operation in accordance with a determination result of the determining means. 3. An object scene image detecting means for detecting image information of an object scene; an expression recognizing means for recognizing a facial expression of a subject based on image information from the object scene image detecting means; A camera comprising: a determination unit that determines whether a predetermined facial expression is obtained based on information from a facial expression recognition unit; and a control unit that performs a subject recording operation in accordance with a determination result of the determination unit. 4. An object scene image detecting means for detecting image information of an object scene, a posture recognizing means for recognizing a posture of a subject based on image information from the object scene image detecting means, and the posture recognizing means. A camera comprising: a determination unit that determines whether or not the camera is in a predetermined posture based on information from the unit; and a control unit that performs a subject recording operation according to a determination result of the determination unit. 5. An object scene image detecting means for detecting image information of an object scene, an operation recognizing means for recognizing an operation of a subject based on image information from the object scene image detecting means, and the operation recognizing means. A camera comprising: a determination unit that determines whether a predetermined operation is performed based on information from the unit; and a control unit that performs a subject recording operation in accordance with a determination result of the determination unit. 6. An object scene image detecting means for detecting image information of an object scene, an expression recognizing means for recognizing a facial expression of a subject based on image information from the object scene image detecting means, The information processing apparatus includes: a determination unit configured to determine whether a predetermined facial expression is obtained based on information from the facial expression recognition unit; and a control unit configured to change brightness of a subject recording screen according to a determination result of the determination unit. camera. 7. An object scene image detecting means for detecting image information of an object scene, an expression recognizing means for recognizing a facial expression of a subject based on image information from the object scene image detecting means, Determining means for determining whether a given facial expression is obtained based on information from a facial expression recognizing means; text / character generating means for generating a text or a character; and text and a character together with a subject according to the determination result of the determining means. And a control unit for performing a recording operation for recording. 8. An object scene image detecting means for detecting image information of an object scene, an expression recognizing means for recognizing a facial expression of a subject based on image information from the object scene image detecting means, Based on information from the facial expression recognizing means, a determining means for determining whether or not a predetermined facial expression is obtained, a screen color changing means for changing a color of a recording screen, and a screen color changed according to the determination result of the determining means A camera for performing a recording operation for recording together with the subject.