WO2010058678A1 - 指定色領域画定回路、検出回路及びそれを用いた画像処理装置 - Google Patents
指定色領域画定回路、検出回路及びそれを用いた画像処理装置 Download PDFInfo
- Publication number
- WO2010058678A1 WO2010058678A1 PCT/JP2009/068272 JP2009068272W WO2010058678A1 WO 2010058678 A1 WO2010058678 A1 WO 2010058678A1 JP 2009068272 W JP2009068272 W JP 2009068272W WO 2010058678 A1 WO2010058678 A1 WO 2010058678A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- designated color
- luminance
- image processing
- coefficient
- luminance information
- Prior art date
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N9/00—Details of colour television systems
- H04N9/64—Circuits for processing colour signals
- H04N9/643—Hue control means, e.g. flesh tone control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/62—Retouching, i.e. modification of isolated colours only or in isolated picture areas only
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/46—Colour picture communication systems
- H04N1/56—Processing of colour picture signals
- H04N1/60—Colour correction or control
- H04N1/62—Retouching, i.e. modification of isolated colours only or in isolated picture areas only
- H04N1/628—Memory colours, e.g. skin or sky
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
Definitions
- the present invention relates to an image processing technique, and more particularly, to an image processing technique for favorably processing a specified color.
- Patent Document 1 paragraphs 0113 to 0116 of Patent Document 1
- a method for detecting a skin color area by changing a skin color determination area according to the luminance of each pixel using a table is described. Has been.
- the skin color region is a region limited by hue and color signal saturation and represented by Equation 1 and Equation 2 of Patent Literature 1.
- the skin color regions represented by Formula 1 and Formula 2 of Patent Document 1 are similarly Formula 3 and Formula 4 of Patent Document 1 (from Formula 1 to Formula 4 of Patent Document 1 and from Formula 1 of FIG. 33 of the present application).
- the skin color area changes according to the level of the luminance signal, and as the luminance signal level increases, the skin color area is as shown in FIG. 12, FIG. 13, and FIG. Describes that the color signal saturation increases (FIGS. 11 to 14 of Patent Document 1 are collectively shown in FIG. 35 of the present application).
- FIG. 33 is a diagram showing a skin color detection circuit (FIG.
- a conventional skin color detection circuit 501 shown in FIG. 33 includes a memory 503 and a comparator 505.
- the memory 503 receives the signals RY and BY and compares the output with Y in the comparator 505 to output a skin color detection signal.
- the memory 503 stores a table for skin color detection shown in FIG. 34 (FIG. 15 of Patent Document 1), and numbers are written only in specific areas (“0” is written in other areas). ing).
- fills Formula 1, Formula 2, Formula 3, and Formula 4 shown from the top shown in FIG. 33 with the table for skin color detection shown in FIG. 34 is detectable.
- a region having a predetermined level signal in the two-dimensional plane of-(BY) and RY is regarded as a skin color region.
- the skin color detection process if it is determined that the skin color is in the range from 1/2 to 1/8 of the luminance signal Y, a signal of level 14 from the luminance input terminal Y is obtained.
- 7 to 1 in the table are discriminated as skin color areas and “1” is output. That is, the range indicated by the low luminance Y region (low Y) in FIG. 34 is regarded as a skin color region at low luminance. It can also be seen that the skin color region changes as the luminance changes.
- FIGS. 35A to 35D are diagrams showing changes in the skin color area in the (BY)-(RY) plane in the prior art, and FIG. 35 (a) is a symbol in the equation.
- FIG. 35 (b) to FIG. 35 (d) are diagrams showing changes in the skin color region depending on the luminance.
- ⁇ is the angle of the central axis extending from the origin of the flesh color region
- ⁇ is the flesh color region from the central axis of the flesh color region.
- R is the distance from the origin to the center of the skin color area
- s is the distance from the center of the skin color area to the boundary of the skin color area along the central axis.
- the skin color region can be defined by these parameters.
- the table shown in FIG. 34 is stored in the memory 503 of FIG. 33. Based on the change of the luminance value Y, FIG. 35 (b) in the case of the low luminance Y to FIG.
- the skin color region can be changed by the luminance up to FIG. 35 (d) in the case of high luminance Y.
- Japanese Patent Application Laid-Open No. 11-146405 video signal processing apparatus, and color video camera using the same
- FIGS. 1 to 3 are diagrams showing the distribution of skin color areas on the UV plane, the VY plane, and the UY plane (Y is luminance, U and V are color differences).
- the Y (brightness) size of each pixel is shown in order of c, b, a, and the respective distributions are shown.
- the UV characteristic has a dependency and a size of the skin color region that are once away from the origin (c1-b1) and then close to the origin (b1-a1). It can be seen that this indicates a change depending on the luminance.
- the skin color area has luminance dependence, and the luminance dependence is not linear dependence.
- the conventional image processing technique has a problem that it cannot cope with the luminance dependency of the skin color area.
- An object of the present invention is to provide a technique capable of specifying a specified color area including a skin color area with high accuracy with respect to a change in luminance.
- the image processing technique is characterized in that brightness distribution information of a plurality of pixels of an image is acquired and a designated color region is determined from the information.
- the designated color area is an approximate color area centered on the designated color in the color space.
- a luminance information acquisition unit that acquires luminance distribution information of a plurality of pixels included in an input image, and a plurality of pixels based on the luminance information of the plurality of pixels acquired by the luminance information acquisition unit.
- a luminance information analysis unit that obtains a characteristic value according to the luminance information of the pixel, and obtains a coefficient for demarcating a designated color region in the color space of the input image according to the luminance based on the characteristic value;
- a designated color region defining circuit is provided.
- the present invention has a designated color characterized by having a designated color detection unit that outputs the degree of approximation obtained by the designated color region, which is defined by the coefficient obtained by the luminance information analysis unit described above. It may be a detection circuit.
- the degree of approximation is 0 on the boundary that defines the designated color area and outside the boundary, and approaches 1 in the area as it approaches the center. The degree of approximation can be uniquely obtained at a certain point on the color space.
- an image in which an image processing coefficient is changed between the designated color and other colors by using the designated color detection circuit described above and the approximation degree that is an output of the designated color detection circuit as inputs.
- An image processing apparatus comprising: a processing coefficient output circuit; and an image processing circuit that outputs an output image signal based on an image processing coefficient that is an output of the image processing coefficient output circuit and an input image signal. May be.
- a luminance information analysis step for obtaining a characteristic value according to luminance information of a plurality of pixels, and for obtaining a coefficient for demarcating a designated color area in the color space of the input image according to the luminance based on the characteristic value; A method for defining a designated color region is provided.
- the present invention has a designated color detecting step for obtaining and outputting an approximation degree by the designated color region defined by the coefficient obtained by the luminance information analyzing step described above. It may be a detection method.
- the present invention may be a program for causing a computer to execute the method described above, or a computer-readable recording medium for recording the program.
- This program may be acquired by a transmission medium such as the Internet.
- the designated color area can be appropriately designated corresponding to the change in the skin color area due to the luminance, there is an advantage that false detection other than the designated color can be reduced.
- FIG. 5 is a diagram illustrating a configuration of an entire image processing circuit including a designated detection color circuit 1 illustrated in FIG. 4. It is a figure which shows a mode that mixing of an image processing coefficient is linearly performed according to the value of the designated color approximation degree N which is an output of a designated color detection circuit.
- FIG. 6 is a diagram illustrating an image in which a specified color coefficient combining unit combines coefficients of a specified color region of N-2 frame and N-1 frame and outputs the result to a specified color detection unit as a specified region coefficient of N frame.
- FIG. 5 is a diagram showing an image in which a specified color coefficient composition unit combines coefficients of a designated color area of N-2 frame and N-1 frame and outputs the result to a designated color detection part as a coefficient of a designated area of N frame.
- FIG. 6 is a diagram illustrating an image in which a specified color coefficient combining unit combines coefficients of a specified color region of N-2 frame and N-1 frame and outputs the result to a specified color detection unit as a specified region coefficient of N frame.
- FIG. 10 is a diagram showing a state in which areas are designated so as to include both designated color areas corresponding to the (N-2) th frame and the (N-1) th frame. It is a figure which shows the example of 1 structure of the display apparatus using the designated color detection part using the image processing technique by this Embodiment. It is a figure which shows the example which applied the image processing technique by this Embodiment to the portable terminal. It is a flowchart figure which shows the whole flow of the image processing by this Embodiment. It is a flowchart figure which shows the flow of the 1st process among the processes shown in FIG. It is a flowchart figure which shows the flow of the 2nd process among the processes shown in FIG.
- SYMBOLS 1 Designated color detection circuit, 3 ... Luminance information acquisition part, 5 ... Luminance information analysis part, 5a ... Luminance information calculation part, 5b ... Designated color coefficient prediction part, 6 ... Designated color area demarcation circuit, 7 ... Designated color detection part , 7a, 7b ... designated color detection unit, 41 ... image processing coefficient output circuit, 43 ... image processing circuit. 51 ... Delay circuit 61 ... Designated color coefficient synthesis unit 63 ... Designated color coefficient adjustment unit 65 ... Designated color approximation N synthesis unit
- FIG. 4 is a diagram showing a configuration example of the designated color detection circuit (hereinafter, the designated color will be described by taking skin color as an example) in the image processing apparatus according to the present embodiment.
- the designated color detection circuit 1 includes a luminance information (histogram) acquisition unit 3 for a plurality of pixels, a luminance information (histogram) analysis unit 5 that analyzes the luminance information for a plurality of pixels, A designated color (skin color) detection unit 7.
- a luminance information analysis unit 5 that analyzes luminance information of a plurality of pixels and a designated color detection unit 7 constitute a designated color region defining circuit 6 that demarcates a designated color region.
- the designated color area defining circuit 6 obtains an input image by the luminance information acquisition unit 3, performs analysis based on the luminance information, obtains a feature value, and outputs a coefficient (parameter) for demarcating the designated color area To do.
- the luminance information (histogram) acquisition unit 3 for a plurality of pixels performs processing for acquiring information related to the luminance of the plurality of pixels in the input image.
- a luminance histogram indicating the frequency is created as shown in FIG.
- an image having 0 to 255 gradations is divided into 32 (0-7, 8-15,... 240-247, 248-255), and pixels existing in the divided gradations (luminance Y) Count the number.
- the luminance information analysis unit 5 from the histogram information obtained from the luminance information acquisition unit 3, the average (luminance) value, the central (luminance) value, the mode (luminance) value, the variance, the standard deviation, the minimum in the histogram. At least one of a value, maximum value, kurtosis, skewness, geometric mean, harmonic mean, weighted mean, etc. is obtained, and a coefficient table (feature value) shown in FIG. Center coordinates U (u0), center coordinates V (v0), slope (a), first weight (w1), second weight (w2) of the skin color area (here mainly assuming an ellipse as follows) Is output to the designated color detection unit 7.
- This coefficient table stores, for example, coefficients for defining an ellipse on the color space with respect to the average (luminance) value.
- the center coordinates U (u0) of the coefficients V (v0) ), Slope (a), first weight (w1), and second weight (w2) may be calculated for the average value of a plurality of pixels of the input image, or the skin color distribution may be extracted and parameters Using the fitting, it is also possible to appropriately determine the center coordinates, inclination, and weighting (area size) on the color space.
- a straight line is obtained from the skin color distribution using the least square method, and the center coordinates, inclination, and weight are determined so as to include all skin color distribution areas from the area having the center coordinates (center) as the intersection of the straight lines that intersect the line at right angles. Also good. These values may be stored in a memory, for example.
- the skin color region is specified based on the coefficient obtained from the luminance information analysis unit 5. An area determination method (calculation method) will be described later.
- the distance from the center of the skin color region is weighted (the ellipse center is approximately 0 at the outer periphery of the ellipse with the designated color approximation degree 1 that seems to be the most designated color).
- the degree of approximation is 0 at the boundary that defines the specified color area and outside the boundary, and approaches 1 in the area as it approaches the center (the center of the specified color area is the most specified color). That's the point.)
- the degree of approximation can be uniquely obtained at a certain point on the color space.
- the YUV space is used as the color space, but other color spaces (L * u * v *, L * a * b *, HSV, HLS, YIQ, YCbCr, YPbPr, etc.) may be used. .
- color spaces L * u * v *, L * a * b *, HSV, HLS, YIQ, YCbCr, YPbPr, etc.
- FIG. 8 is a diagram showing a definition relating to an ellipse.
- a straight line passing through two focal points is drawn inside the ellipse, this is called a long axis.
- the length of the major axis is called the major axis.
- the difference in distance from the two focal points becomes the maximum.
- this line segment is called the short axis.
- the length of the minor axis is called the minor axis.
- FIG. 7 is a diagram illustrating an example of a specified color region discrimination (calculation) method.
- characteristic axes two axes (hereinafter referred to as “characteristic axes”) representing the directionality of the designated color region are expressed by the following equations. Defined by The major axis is the characteristic axis L1, and the minor axis is the characteristic axis L2.
- Equation 3 is obtained.
- the characteristic axis is as shown in the following formula 6. Even in this case, it can be confirmed that the characteristic axis is orthogonal.
- a straight line drawn with a solid line is included in the range, and a broken line range is not included. With this mechanism, it is possible to set a designated color range (ellipse) having an arbitrary inclination. As shown in FIG.
- the characteristic axes L1 and L2 can be set by three parameters, the coordinates u0 and v0 of the skin color designated color P0 and the inclination a.
- the distance from a designated color P0 to a point P (u, v) obtained by plotting an input signal on the UV plane as shown in FIG. 10 is defined by the following procedure.
- the distance d1 from P to each characteristic axis L1 and d2 from the characteristic axis L2 are obtained by the following equations 8 and 9.
- the intercepts to the U axis are b1 and b2.
- a value D obtained by multiplying each of d1 and d2 by weights w1 and w2 is defined as a distance from the center P0.
- the designated color approximation N (the output N of the designated color detection circuit 1 in FIG. 4) indicating the closeness to the designated color is defined by the following equation 11.
- the outer area AR2 is a non-designated color area.
- the weighting factors w1 and w2 have a function of deforming the designated color range, and the designated color range becomes smaller as these values are increased (see arrow AR11).
- the ratio of w1 and w2 is the ratio of the major axis to the minor axis of the ellipse. Therefore, if the same value is set for w1 and w2, the designated color range is a circle.
- the designated color area is designated by an ellipse, but the designated color area AR3 and the outside area AR4 are designated by simplifying Equation 10 and using the rhombus defined by Equation 12-1. (See FIG. 12).
- the intersection of the diagonal lines of the rhombus is defined as P0, and the lines including the diagonal lines are defined as characteristic axes L1 ′ and L2 ′. If the same value is set for w1 and w2, the designated color range becomes a square.
- the skin color region can also be specified using a rectangle defined by Expression 12-2 (see FIG. 13).
- straight lines L1 and L2 are used as the characteristic axis, but an arbitrary polygon can be used as the designated color region by using a plurality of characteristic axes.
- the weights w1 and w2 indicate the lengths of the major axis and the minor axis, and each half is an ellipse that is symmetric with respect to the minor axis and the major axis.
- a short axis and a long axis asymmetrical ellipse in which 1 ⁇ 2 of the length of the minor axis or major axis is not the center point may be used.
- it is a rhombus, but it may be a rectangle.
- FIG. 14 is a diagram showing the properties of a flesh-color image used for comparing the present invention with the prior art.
- this image is a 3 ⁇ 3 skin color image composed of pixels (1) to (9).
- the pixel (1) is a noise pixel
- the Y value is significantly different from the other pixels (2) to the pixel (9)
- the UV value is almost the same as the other pixels.
- the average value of Y (luminance) is 103.
- FIG. 15 is a diagram showing differences in the skin color area depending on Y (luminance) in the UV space.
- the elliptical area representing the skin color area is arranged in the order of small luminance, medium luminance, and large luminance from the position close to the origin in the direction in which V increases and U decreases.
- the flesh color region at the luminance (144) of the pixel (1) is the high luminance region in FIG. 15, and the flesh color region at the luminance (91 to 105) from the pixel (2) to the pixel (9) is medium. It is a luminance area.
- the skin color region at the luminance (103) that is an average value of the luminances of the pixels (1) to (9) is a medium luminance region.
- the U and V (both color differences) of the pixel (1) to the pixel (9) are present in the flesh color region at the medium luminance in FIG. 15 and outside the flesh color region at the high luminance.
- the skin color region is determined by the Y (luminance) value of the pixel for discriminating the skin color.
- the flesh-colored region is the large luminance region in FIG. 15, and the U and V of the pixel (1) are not included in this region. Therefore, it is determined that the pixel (1) is not a skin color.
- the flesh color region is the middle luminance region in FIG. 15, and U and V of these pixels are included in this region. Therefore, these pixels are discriminated as skin color.
- the pixels (2) to (9) are also determined to be skin color.
- the image processing is different from the skin color and other than the skin color in the conventional technology (individual processing is performed).
- individual processing is performed.
- multiple pixels need only be processed in the same way with the same skin color, so the average brightness of the multiple pixels is taken according to the brightness of the scene, and as a result, noise is conspicuous compared to the prior art. There is an advantage that it is difficult.
- FIG. 16 is a diagram showing a configuration of the entire image processing circuit including the designated color detection circuit 1 shown in FIG.
- the designated color detection circuit 1 discriminates the skin color
- the image processing coefficient output circuit 41 at the subsequent stage changes the image processing coefficient between the skin color and the other portions.
- the image processing coefficients are mixed linearly according to the value of the designated color approximation degree N that is the output of the designated color detection circuit 1 (see FIG. 17).
- the normal image processing coefficient is S1
- the image processing coefficient of the skin color that is the designated color is S2
- the final image processing coefficient S is expressed by Equation 13.
- the coefficient S in the function L11 determined by the numbers S1 and S2 can be obtained according to the input value (arrow) of the designated color approximation degree N.
- This coefficient is an image processing coefficient that is an output of the image processing coefficient output circuit 41.
- the image processing circuit 43 can perform image processing such as saturation correction to generate an output image.
- the color that people imagine in memory is called the memory color, and it is generally said that the memory color has higher saturation than the actual color, especially in the sky blue, plant green, etc. The tendency is strong.
- the color of human skin is an exception, and fairness (high brightness and low saturation) is a preferred color than actual.
- Perform image processing Image processing for correcting hue and brightness may be performed as another image processing circuit. As the degree of approximation N is larger, the process suitable for the specified color is more strongly performed.
- the skin color region can be appropriately determined even in a scene where the luminance changes (daytime, night, etc.).
- FIG. 29 to FIG. 32 are flowcharts showing the flow of designated color detection according to the present embodiment.
- the designated color detection process is started (START), and a histogram is acquired in step S1.
- a histogram analysis process is performed. For example, the average luminance is obtained, and a coefficient for defining the designated color (skin color) region is obtained from the designated color coefficient table (feature value).
- step S3 a designated color detection process is performed, and the process ends (END). Note that the designated color area demarcating step is executed in steps S1 and S2.
- FIG. 30 is a flowchart showing the flow of the histogram acquisition process (step S1 in FIG. 29).
- step S15 the acquisition size of the histogram is set to “0”.
- FIG. 31 is a flowchart showing the flow of histogram analysis processing.
- the average luminance is calculated from step S31 to step S36, and the coefficient of the designated color region is acquired in step S37.
- step S31 32 steps of histogram information from 0 to 31 are input.
- the histogram of 3.5 it is 3.5 (the median value of gradations 0 to 7), and in the one-stage histogram, it is 11.5 (the median value of gradations 8 to 15).
- the definition of the designated color coefficient table (feature value) is a definition of coefficients, which is as follows (301 in FIG. 31).
- step S43 d1 and d2 are obtained based on the following equation (14).
- step S44 D is obtained based on the following equation 15.
- step S45 the designated color approximation degree N is obtained based on the following equation 16.
- step S46 the designated color approximation N is output.
- step S47 it is determined whether or not img_size ⁇ HV_SIZE.
- img_size img_size + 1 is set, and the process returns to step ZS42. If yes, the process is terminated (EXIT). Thereby, the designated color approximation degree N can be output.
- the image processing technique according to the present embodiment is an example adapted to a moving image.
- a histogram is acquired for the input image of at least one frame before the input image of the current frame, and the analyzed designated color approximation N is calculated.
- the image processing circuit shown in FIG. 18 is the designated color detection circuit 1 shown in FIG.
- a luminance information analysis unit 5 that analyzes luminance information of a plurality of pixels and a designated color detection unit 7 constitute a designated color region defining circuit 6 that demarcates a designated color region.
- the input image of the current frame can be synchronized with the input image of the current frame by adding the delay circuit 51 to delay the input image, and therefore, the flesh color is also applied to the moving image. Can be processed with good reproducibility.
- FIG. 20 is a diagram showing an outline of the operation in the designated color (skin color) coefficient prediction unit 5b. As shown in FIG.
- the designated color (skin color) coefficient prediction unit 5b stores average luminance information from an input image four frames before (N-4 frames) before the current frame N in a memory or the like in the example of FIG. Then, the average luminance (140 in the figure) of the input image of the current frame N is predicted, and the coefficient of the designated color area corresponding to the luminance is output to the designated color detection unit.
- FIG. 21 is a diagram showing an image of prediction of the average luminance Ym from the N-4 frame to the N frame. In general, prediction is performed by smoothly connecting trends that change as the frame progresses.
- the specified color approximation degree N based on the average luminance of the input image at least one frame before is used for the input image of the current frame, so that a slight deviation occurs.
- the designated color approximation degree N is obtained, there is an advantage that the designated color area can be more appropriately determined.
- the delay circuit is unnecessary compared with the configuration according to the second embodiment, there is an advantage that the circuit scale can be reduced.
- 22 and 23 are diagrams showing a configuration example of the designated color detection circuit 1 in the image processing circuit according to the present embodiment.
- the designated color detection circuit 1 shown in FIGS. 22 and 23 has a configuration in which a designated color coefficient synthesis unit 61 is added between the luminance information analysis unit 5 and the designated color detection unit 7 in the circuit shown in FIG.
- a luminance information analysis unit 5 that analyzes luminance information of a plurality of pixels and a designated color detection unit 7 constitute a designated color region defining circuit 6 that demarcates a designated color region.
- the designated color coefficient synthesis unit 61 synthesizes the coefficients of the designated color area for the input images of the N-2 frame and the N-1 frame, and the coefficients of the designated color area of the N frame. Is output to the designated color detection unit 7.
- the designated color detection unit 7. By adopting such a configuration, as shown in FIG. 26, it is possible to designate an area so as to include both skin color areas corresponding to the N-2 frame and the N-1 frame. If it is within the change of ⁇ 1 frame, the skin color region can be made to correspond to the change.
- the coefficients of the designated color (skin color) region are synthesized by the designated color coefficient synthesis unit 61, whereas in the configuration shown in FIG. 23, two designated color detection units 7a and 7b are used.
- the coefficient adjusting unit 63 outputs the coefficients of the designated color regions of the N-2 frame and the N-1 frame to the designated color detection units 7a and 7b, respectively, and designates the designated color approximation degree of the N-2 frame and the N-1 frame.
- N is synthesized by the designated color approximation degree N synthesis unit 65.
- the designated color coefficient adjustment unit 63 is a timing adjustment circuit for outputting the coefficients of the designated color areas of the (N ⁇ 2) th frame and the (N ⁇ 1) th frame at a timing suitable for the Nth frame.
- FIG. 27 is a diagram illustrating a configuration example of a display device using the designated color detection unit 1 using the image processing technique according to the present embodiment.
- the display device illustrated in FIG. 27 includes a control unit 105, a video signal processing unit 111, and a display unit 121, and further includes an external connection terminal 103 and an external memory I / F unit 107.
- the video signal processing unit 111 includes the designated color detection unit 1, the image processing unit 115, and the gamma correction unit 117 according to the present embodiment, and can reproduce the designated color (skin color) satisfactorily. .
- FIG. 28 is a diagram illustrating an example in which the image processing technique according to the present embodiment is applied to a mobile terminal.
- a portable device including a designated color designation unit 1 according to the present embodiment, an image processing unit 215, a video signal processing unit 211 including a gamma correction unit 217, a display unit 221, and a control unit 205.
- Terminal 201 Terminal 201.
- the control unit 205 includes an operation unit 223, a wireless communication unit 225, a camera 227, a dedicated storage unit 231, a RAM / ROM 233, a shape detection unit 235 that detects the shape of the mobile terminal, a register 237, a TV reception unit 239, It controls the external connection terminal 241, the external memory I / F 243, the power source 245, and the video signal processing unit 211. That is, the specified color when displaying the still image / moving image acquired by the camera 227, the broadcast content acquired by the TV receiving unit 239, the content data acquired from the wireless communication unit 225, the external memory I / F 243, or the like on the display unit 221.
- the luminance dependency of (skin color) can be adjusted well.
- the present invention can be applied to various electronic devices such as a digital broadcast receiving device and a personal computer.
- the configuration and the like illustrated in the accompanying drawings are not limited to these, and can be changed as appropriate within the scope of the effects of the present invention.
- various modifications can be made without departing from the scope of the object of the present invention.
- a program for realizing the functions described in the present embodiment is recorded on a computer-readable recording medium, and the program recorded on the recording medium is read into a computer system and executed, thereby executing processing of each unit. May be performed.
- the “computer system” here includes an OS and hardware such as peripheral devices.
- the “computer system” includes a homepage providing environment (or display environment) if a WWW system is used.
- the “computer-readable recording medium” means a storage device such as a flexible disk, a magneto-optical disk, a portable medium such as a ROM and a CD-ROM, and a hard disk incorporated in a computer system. Furthermore, the “computer-readable recording medium” dynamically holds a program for a short time like a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory in a computer system serving as a server or a client in that case is also used to hold a program for a certain period of time.
- the program may be a program for realizing a part of the above-described functions, or may be a program that can realize the above-described functions in combination with a program already recorded in a computer system. .
- the present invention can be used as an image processing apparatus.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Processing Of Color Television Signals (AREA)
Abstract
Description
中心座標V(v0): table_v0[N]
傾き(a): table_a [N]
重み付け1(w1): table_w1[N]
重み付け2(w2): table_w2[N]
N : テーブル段数(0~255)
上記の処理により指定色領域の係数を取得した後、図32に示す指定色検出処理を行う。まず、ステップS41において、入力画像サイズについて、img_size=0を代入(初期化)する。次いで、ステップS42において、入力画像として色差(U,V)=u,vが入力される。ステップS43において、下記式14に基づいて、d1、d2を求める。
Claims (17)
- 入力画像に含まれる複数の画素の輝度分布情報を取得する輝度情報取得部と、
前記輝度情報取得部により取得された前記複数画素の輝度情報に基づいて、複数画素の輝度情報に応じた特徴値を求め、該特徴値に基づいて、輝度に応じた前記入力画像の色空間上での指定色領域を画定するための係数を求める輝度情報解析部と、を有することを特徴とする指定色領域画定回路。 - 前記輝度情報取得部は、ある階調幅をもつ輝度値と該輝度値を有する画素の合計数である度数との関係を示すヒストグラムを取得し、
前記輝度情報解析部は、前記ヒストグラムに基づいて、前記ヒストグラムの前記特徴値を求め、該特徴値に基づいて前記係数を求めることを特徴とする請求項1に記載の指定色領域画定回路。 - 請求項1又は2に記載の輝度情報解析部により求められた前記係数によって画定された、前記指定色領域により近似度を求めて出力する指定色検出部を有することを特徴とする指定色検出回路。
- 前記指定色検出部は、前記係数として、前記指定色領域の中心と、傾きと、前記中心からの大きさと、を備え、
前記色空間上において、前記中心を通り、前記傾きを持つ第1の特性軸と、前記中心を通り、前記第1の特性軸と直交する第2の特性軸と、を定め、前記中心からの大きさにより前記指定色領域を画定し、前記近似度を求めることを特徴とする請求項3に記載の指定色検出回路。 - 前記指定色領域を、前記第1の特性軸と前記第2の特性軸のいずれか一方を長軸に含み、他方を短軸に含む楕円で近似することを特徴とする請求項4に記載の指定色検出回路。
- 前記指定色領域を、前記第1の特性軸と前記第2の特性軸とを対角線に含むひし形で近似することを特徴とする請求項4に記載の指定色検出回路。
- 前記指定色領域の前記中心に近いほど前記近似度を強く、前記指定領域の前記中心から遠いほど前記近似度を弱くすることを特徴とする請求項3から6までのいずれか1項に記載の指定色検出回路。
- 請求項3から7までのいずれか1項に記載の指定色検出回路と、前記指定色検出回路の出力である前記近似度を入力として、前記指定色とそれ以外の色とで画像処理の係数を変更する画像処理係数出力回路と、前記画像処理係数出力回路の出力である画像処理係数と入力画像信号とに基づいて出力画像信号を出力する画像処理回路とを有することを特徴とする画像処理装置。
- 前記画像処理の係数が前記近似度に比例することを特徴とする請求項8に記載の画像処理装置。
- 前記画像処理回路に入力する前記入力画像を遅延させる遅延回路を備えた請求項8又は9に記載の画像処理装置。
- 前記輝度情報解析部に、数フレーム前から1フレーム前までの前記入力画像の複数画素の輝度情報に基づいて現フレームの前記指定色領域を画定するための係数を予測する指定色係数予測部を設けたことを特徴とする請求項8から10までのいずれか1項に記載の画像処理装置。
- 前記輝度情報解析部と前記指定色検出部との間に、現フレームNとしてN-2フレームとN-1フレームの前記指定色領域を画定するための係数を合成しNフレーム目の前記指定色領域を画定するための係数とする指定色係数合成部を設けたことを特徴とする請求項8から10までのいずれか1項に記載の画像処理装置。
- 請求項8から12までのいずれか1項の記載に画像処理装置を備えた表示装置。
- 請求項13に記載の表示装置を備えた電子機器。
- 入力画像に含まれる複数の画素の輝度分布情報を取得する輝度情報取得ステップと、
前記輝度情報取得ステップにより取得された前記複数画素の輝度情報に基づいて、複数画素の輝度情報に応じた特徴値を求め、該特徴値に基づいて、輝度に応じた前記入力画像の色空間上での指定色領域を画定するための係数を求める輝度情報解析ステップと、
を有することを特徴とする指定色領域画定方法。 - 請求項15に記載の前記輝度情報解析ステップにより求められた前記係数によって画定された、前記指定色領域により近似度を求めて出力する指定色検出ステップを有することを特徴とする指定色検出方法。
- 請求項15又は16に記載の方法をコンピュータに実行させるためのプログラム。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2010539191A JP4851624B2 (ja) | 2008-11-19 | 2009-10-23 | 指定色領域画定回路、検出回路及びそれを用いた画像処理装置 |
US13/127,434 US20110216967A1 (en) | 2008-11-19 | 2009-10-23 | Specified color area demarcation circuit, detection circuit, and image processing apparatus using same |
EP09827459A EP2352123A4 (en) | 2008-11-19 | 2009-10-23 | CIRCUIT FOR THE LIMITATION OF A SPECIFIC COLOR RANGE, DETECTION SWITCHING AND IMAGE PROCESSING DEVICE THEREWITH |
CN2009801458438A CN102216956A (zh) | 2008-11-19 | 2009-10-23 | 指定色区域划定电路、检测电路以及使用其的图像处理装置 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2008-295786 | 2008-11-19 | ||
JP2008295786 | 2008-11-19 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2010058678A1 true WO2010058678A1 (ja) | 2010-05-27 |
Family
ID=42198117
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2009/068272 WO2010058678A1 (ja) | 2008-11-19 | 2009-10-23 | 指定色領域画定回路、検出回路及びそれを用いた画像処理装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US20110216967A1 (ja) |
EP (1) | EP2352123A4 (ja) |
JP (1) | JP4851624B2 (ja) |
CN (1) | CN102216956A (ja) |
WO (1) | WO2010058678A1 (ja) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018037041A (ja) * | 2016-09-02 | 2018-03-08 | 富士通株式会社 | 生体画像処理装置、生体画像処理方法、および生体画像処理プログラム |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5811416B2 (ja) * | 2013-10-09 | 2015-11-11 | カシオ計算機株式会社 | 画像処理装置、画像処理方法及びプログラム |
US9805662B2 (en) * | 2015-03-23 | 2017-10-31 | Intel Corporation | Content adaptive backlight power saving technology |
US10477036B2 (en) * | 2016-04-14 | 2019-11-12 | Canon Kabushiki Kaisha | Image processing apparatus, image processing method, and storage medium |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11146405A (ja) | 1992-01-13 | 1999-05-28 | Mitsubishi Electric Corp | 映像信号処理装置及びこれを用いたカラービデオカメラ |
JP2002157596A (ja) * | 2000-11-17 | 2002-05-31 | Sony Corp | ロボット装置及び顔識別方法 |
JP2002183729A (ja) * | 2000-10-20 | 2002-06-28 | Eastman Kodak Co | 画像肌色検出における金髪画素除去方法 |
JP2004192129A (ja) * | 2002-12-09 | 2004-07-08 | Fuji Photo Film Co Ltd | 顔領域抽出方法及び装置 |
JP2005250596A (ja) * | 2004-03-01 | 2005-09-15 | Fuji Xerox Co Ltd | 画像処理方法および画像処理装置、画像処理プログラム、記憶媒体 |
JP2007264860A (ja) * | 2006-03-28 | 2007-10-11 | Victor Co Of Japan Ltd | 顔領域抽出装置 |
JP2008252475A (ja) * | 2007-03-30 | 2008-10-16 | Mitsubishi Electric Corp | 画像処理装置およびプログラム記録媒体 |
JP2008295786A (ja) | 2007-05-31 | 2008-12-11 | Konami Digital Entertainment:Kk | ゲーム装置、ゲーム装置の制御方法及びプログラム |
JP2009290661A (ja) * | 2008-05-30 | 2009-12-10 | Seiko Epson Corp | 画像処理装置、画像処理方法、画像処理プログラムおよび印刷装置 |
Family Cites Families (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5488429A (en) * | 1992-01-13 | 1996-01-30 | Mitsubishi Denki Kabushiki Kaisha | Video signal processor for detecting flesh tones in am image |
US5638136A (en) * | 1992-01-13 | 1997-06-10 | Mitsubishi Denki Kabushiki Kaisha | Method and apparatus for detecting flesh tones in an image |
DE4309878C2 (de) * | 1992-04-06 | 1994-07-21 | Hell Ag Linotype | Verfahren und Einrichtung zur Analyse und Korrektur der Bildgradation in Bildvorlagen |
EP1085747B1 (en) * | 1999-03-02 | 2009-05-27 | Seiko Epson Corporation | Image data background judging device, image data background judging method, and medium on which image data background judging control program is recorded |
JPWO2006059573A1 (ja) * | 2004-12-02 | 2008-06-05 | 松下電器産業株式会社 | 色彩調整装置及び方法 |
JP4328286B2 (ja) * | 2004-12-14 | 2009-09-09 | 本田技研工業株式会社 | 顔領域推定装置、顔領域推定方法及び顔領域推定プログラム |
JP4982475B2 (ja) * | 2008-12-24 | 2012-07-25 | ローム株式会社 | 画像処理方法及びコンピュータプログラム |
US9946058B2 (en) * | 2010-06-11 | 2018-04-17 | Nikon Corporation | Microscope apparatus and observation method |
-
2009
- 2009-10-23 EP EP09827459A patent/EP2352123A4/en not_active Withdrawn
- 2009-10-23 JP JP2010539191A patent/JP4851624B2/ja not_active Expired - Fee Related
- 2009-10-23 CN CN2009801458438A patent/CN102216956A/zh active Pending
- 2009-10-23 WO PCT/JP2009/068272 patent/WO2010058678A1/ja active Application Filing
- 2009-10-23 US US13/127,434 patent/US20110216967A1/en not_active Abandoned
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH11146405A (ja) | 1992-01-13 | 1999-05-28 | Mitsubishi Electric Corp | 映像信号処理装置及びこれを用いたカラービデオカメラ |
JP2002183729A (ja) * | 2000-10-20 | 2002-06-28 | Eastman Kodak Co | 画像肌色検出における金髪画素除去方法 |
JP2002157596A (ja) * | 2000-11-17 | 2002-05-31 | Sony Corp | ロボット装置及び顔識別方法 |
JP2004192129A (ja) * | 2002-12-09 | 2004-07-08 | Fuji Photo Film Co Ltd | 顔領域抽出方法及び装置 |
JP2005250596A (ja) * | 2004-03-01 | 2005-09-15 | Fuji Xerox Co Ltd | 画像処理方法および画像処理装置、画像処理プログラム、記憶媒体 |
JP2007264860A (ja) * | 2006-03-28 | 2007-10-11 | Victor Co Of Japan Ltd | 顔領域抽出装置 |
JP2008252475A (ja) * | 2007-03-30 | 2008-10-16 | Mitsubishi Electric Corp | 画像処理装置およびプログラム記録媒体 |
JP2008295786A (ja) | 2007-05-31 | 2008-12-11 | Konami Digital Entertainment:Kk | ゲーム装置、ゲーム装置の制御方法及びプログラム |
JP2009290661A (ja) * | 2008-05-30 | 2009-12-10 | Seiko Epson Corp | 画像処理装置、画像処理方法、画像処理プログラムおよび印刷装置 |
Non-Patent Citations (1)
Title |
---|
See also references of EP2352123A4 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018037041A (ja) * | 2016-09-02 | 2018-03-08 | 富士通株式会社 | 生体画像処理装置、生体画像処理方法、および生体画像処理プログラム |
Also Published As
Publication number | Publication date |
---|---|
US20110216967A1 (en) | 2011-09-08 |
EP2352123A4 (en) | 2012-10-24 |
CN102216956A (zh) | 2011-10-12 |
JPWO2010058678A1 (ja) | 2012-04-19 |
JP4851624B2 (ja) | 2012-01-11 |
EP2352123A1 (en) | 2011-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10469714B2 (en) | Systems and methods for capturing digital images | |
US10013739B2 (en) | Image enhancement methods and systems using the same | |
EP1326425A2 (en) | Apparatus and method for adjusting saturation of color image | |
US10565742B1 (en) | Image processing method and apparatus | |
US8538147B2 (en) | Methods and appartuses for restoring color and enhancing electronic images | |
KR101225058B1 (ko) | 콘트라스트 조절 방법 및 장치 | |
US7933469B2 (en) | Video processing | |
US8526057B2 (en) | Image processing apparatus and image processing method | |
EP2624204A2 (en) | Image processing apparatus and method of controlling the same | |
WO2005072431A2 (en) | A method and apparatus for combining a plurality of images | |
JP5235759B2 (ja) | 画像処理装置、画像処理方法、及びプログラム | |
US20080056566A1 (en) | Video processing | |
CN106575434A (zh) | 图像处理装置、摄像装置、图像处理方法以及程序 | |
JP4851624B2 (ja) | 指定色領域画定回路、検出回路及びそれを用いた画像処理装置 | |
US7340104B2 (en) | Correction parameter determining method, correction parameter determining apparatus, computer program, and recording medium | |
WO2008102296A2 (en) | Method for enhancing the depth sensation of an image | |
US11017510B1 (en) | Digital image dynamic range processing apparatus and method | |
US20080055476A1 (en) | Video processing | |
JP2000099717A (ja) | 画質調整装置及び画質調整方法、並びに画像調整用プログラムを記録した記録媒体 | |
JP3950551B2 (ja) | 画像処理方法、装置および記録媒体 | |
CN108810397A (zh) | 一种图像色偏校正方法及终端设备 | |
EP1976273B1 (en) | Image processing apparatus, imaging apparatus and image processing program | |
CN110035267B (zh) | 影像增强电路与方法 | |
JP2866935B2 (ja) | カラー画像の画質改善方法及びその装置 | |
KR0183830B1 (ko) | 평균 분리 히스토그램 등화를 이용한 화질 개선방법 및 그 회로 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
WWE | Wipo information: entry into national phase |
Ref document number: 200980145843.8 Country of ref document: CN |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 09827459 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2010539191 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 13127434 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2009827459 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 4138/CHENP/2011 Country of ref document: IN |