JPH08202868A - Picture processor - Google Patents

Abstract

PURPOSE: To provide a picture processor capable of quicken picture processor, drawing a color tone faithfull to an original picture and emphasizing the feature of the original picture at the time of photographing a face image as an IC card and a certificate by means of a video camera. CONSTITUTION: The processor consists of an illuminating means 11 illuminating the face image F, a camera 12 photographing the face image F and a picture processing part 20 executing the picture processing of a video signal inputted by the camera 12. Then, a video signal is density-corrected by a gamma correction circuit, color-corrected by a matrix conversion circuit next and transformed to color space so as to optionally adjust individual areas to transform the video signal to a normal video signal by a matrix inverse transformation circuit at last.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing device,
In particular, the present invention relates to an image processing apparatus that is used for a certificate, an IC card, or the like by capturing a face image of a person.

[0002]

2. Description of the Related Art For example, as a certificate or an IC card,
Student ID, ID card, credit card, driver's license,
There is a registration certificate, etc., and the face image of the person concerned is recorded on this certificate, IC card, etc. As a method of creating a face image, in addition to a method of creating an image directly on a color film or color photographic paper by a silver halide photography method, a color image is created from a video signal by shooting with a video camera. There is a video system.

[0003]

When a face image taken by a normal video camera is not image-processed,
The obtained face image tends to have a rounded outline and the features tend to fade. Even when image processing is performed, color tone correction using a LUT (Look Up Table) for image processing has been the mainstream. Such image processing has the following drawbacks.

[0004] Only one color correction can correct only the entire color tone. Therefore, for example, when a magenta system is corrected, not only a certain part is changed but the entire color is changed.

When performing partial correction, only that one point was corrected and the area could not be corrected in a well-balanced manner.

Even if the edge correction is simply applied by the differentiating circuit, the effect is not produced at all, or the effect is too large, and the image is far from the original image.

The present invention solves the above-mentioned drawbacks of the prior art,
An object of the present invention is to provide an image processing device that performs image processing of a face image obtained by shooting a face image of a person.

[0008]

The above-mentioned object is to provide an illuminating means for illuminating a face image, an image inputting means for picking up the face image, and an image for performing image processing of a video signal input by the image inputting means. In the image processing unit, the image signal input by the image input unit is first subjected to density correction by a gamma correction circuit, then color correction is performed by a matrix conversion circuit, and then these image signals are color-corrected. This is achieved by an image processing device characterized in that individual areas are arbitrarily adjusted by converting into space, and finally converted into a normal video signal by a matrix inverse conversion circuit.

[0009]

DESCRIPTION OF THE PREFERRED EMBODIMENTS The present invention will be described below with reference to the drawings. FIG. 1 shows a block diagram for performing image processing of the present invention, and FIG. 2 shows an algorithm for developing a density-color space in an image processing unit of the present invention.

The image processing apparatus of the present invention comprises an illuminating means for illuminating a face image of a person, an image inputting means for photographing a face image,
The image processing unit includes an image processing unit that performs image processing of the video signal input by the image input unit, and the image processing unit can obtain an optimum image by a circuit that performs masking, edge enhancement, gradation correction, and color correction. It is like this.

In FIG. 1, a camera 12, which is an image inputting means, is installed facing the face portion F of a person. Illuminating means 11 provided with a color temperature conversion filter is installed on the front surface of the face portion F to illuminate the face portion F with a predetermined illuminance (for example, 1000 lx) and a predetermined color temperature (for example, 3200 ° K). There is.

The camera 12 has a color CCD as a light receiving element.
12a is provided, and the face image of the front person is formed on the color CCD 12a by the taking lens 12b. The analog RGB 13 is output from the camera 12 as a video signal, and A /
The image signal is converted into RGB digital signals by the D conversion circuit 14, and once stored in the frame memory, the image processing unit 20.
Sent to.

The output from the A / D conversion circuit 14 is also sent to the photographic density judging section 15. In the photo density determination unit 15,
The central part corresponding to the face part is extracted from the image information of the face image, and the density levels are averaged. The averaged average density value is compared with a threshold value by the automatic aperture adjustment unit 16. If there is a deviation, the motor M is used until the difference disappears.
Is controlled to drive the diaphragm 12c in the opening or closing direction so that the average density received by the color CCD 12a on the face becomes constant.

The image processing unit 20 processes the image data in the order of to be described below, and then performs output conversion. However, the edge enhancement may be performed by the camera 12 which is the image input means.

Edge enhancement Each color of R, G, B is extracted, the difference between the density levels of adjacent pixels in the H and V directions is obtained, and the edge is enhanced as in the following equation. This feature is that the degree of edge enhancement can be continuously changed. (The value of K is changed.) The relationship between adjacent pixels is as shown in FIG.

[0016]

[Equation 1]

Density Correction The density of the entire screen is corrected by the following formula.

[0018]

[Equation 2]

Next, the density value of the specific area in the central portion is measured from the face image data to obtain the maximum value (Ymax) and the minimum value (Ymin). Y '= 255 * (Ymax-Y) / (Ymax-Ymin) is calculated from the value, the LUT-Y shape of the look-up table is determined, and the density correction 21 is performed.

That is,

[0021]

(Equation 3)

Then, the corrected density value (Y ') is obtained.

This means that even if the input data is in the range of 0 to 255 and there is a region that is actually collapsed, the practical range is set to Rmin to Rmax and the output is set to 0 as shown in FIG.
It can be managed by increasing the resolution to ~ 255.

Color Correction The following equation illustrates the conversion 22 with a 3 × 3 matrix.

[0025]

[Equation 4]

For example, in order to match the ink characteristics of the ink ribbon, each coefficient is given and the R, G, B color signals are converted into RY, Y, BY color difference signals.

Of course, if this conversion is not necessary, color correction can be eliminated by setting all the coefficients to "1" (linear).

Color space conversion The following expression is a color space conversion expression, and FIG. 5 is a conceptual diagram thereof.

[0029]

(Equation 5)

The color difference signal obtained in the previous color correction is developed in a color space (for example, L * a * b * or L * u * v *) and a partial color correction 23 is performed. This method is shown in FIG. 6 [0 → 0 ′ conversion].
As shown in, the origin (0) is adjusted according to the characteristics of the printing material.
To the proper position (0 '). Next, an algorithm for correcting a specific color (for example, skin color) will be described. As shown in FIG. 6 [skin color enhancement], when the point A is corrected to a desired color, not only the point A is corrected but the conical range centered on the point A is corrected.

Output conversion Here, in order to pass the image-processed data up to to the next process, the data is inversely converted by a 3 × 3 matrix,
Return to R, G, B signals. The following equation shows the inverse transform 24 by a 3 × 3 matrix.

[0032]

(Equation 6)

After performing the image processings 1 to 3 described above, the analog signal is converted by the D / A conversion circuit 31.
The analog RGB 32 is sent to the next workstation 40.

[0034]

The image processing apparatus according to the present invention can improve the image quality in the following points by processing the input image without destroying the original image.

By performing the color space conversion, it is possible to adjust to a desired color without affecting the gray scale and without changing the brightness level.

In the case of color correction, when one point in the color space was emphasized, neighboring colors were continuously corrected according to the potential, and the color change became smooth.

When edge enhancement is performed, the contour can be clearly displayed by obtaining and correcting the difference between adjacent pixels (in both H and V directions).

After the area at the center of the image is extracted, the density is measured, and the density is corrected from the maximum value and the minimum value, so that it is possible to correct the overbrightness (overexposure) or the overdarkness (underexposure).

[Brief description of drawings]

FIG. 1 shows a configuration diagram for performing image processing of the present invention.

FIG. 2 shows an algorithm in the image processing unit of the present invention.

FIG. 3 is an explanatory diagram showing a relationship between pixels.

FIG. 4 is an explanatory diagram of gamma correction.

FIG. 5 is a conceptual diagram of color space conversion.

FIG. 6 is an explanatory diagram of a color tone correction method.

[Explanation of symbols]

 11 Illuminating means 12 Camera 12a Color CCD 12b Photographing lens 12c Aperture 13 Analog RGB 14 A / D conversion circuit 15 Photo density determination unit 16 Automatic aperture adjustment unit 20 Image processing unit 21 Density correction 22 3 × 3 matrix conversion 23 Color correction 24 Inverse conversion by 3x3 matrix 31 D / A conversion circuit 32 Analog RGB 40 Workstation

─────────────────────────────────────────────────── ─── Continuation of the front page (51) Int.Cl. ⁶ Identification code Internal reference number FI Technical display location G06F 15/66 310 H04N 1/40 D

Claims (7)

[Claims] 1. An illumination means for illuminating a face image, an image input means for capturing the face image, and an image processing section for performing image processing of a video signal input by the image input means, In the image processing section, the video signals input by the image input means are first subjected to density correction by a gamma correction circuit, then color correction is performed by a matrix conversion circuit, and then these video signals are converted into a color space to obtain individual signals. An image processing apparatus characterized in that an area is arbitrarily adjusted, and finally a matrix inverse conversion circuit converts the area into a normal video signal. 2. The image processing apparatus according to claim 1, wherein the lighting unit is a lighting unit that illuminates the face image with a predetermined illuminance and color temperature. 3. The image input means has a photometric means for photometrically measuring a central portion corresponding to a face portion of the facial image, and performs automatic aperture adjustment of the image input means based on the photometric result. The image processing apparatus according to claim 1, wherein: 4. The gamma correction circuit measures a density value in a central portion of an image, obtains a maximum value and a minimum value from the measured values, and performs the density correction based on this.
The image processing device described. 5. The image processing apparatus according to claim 1, wherein the matrix conversion circuit is a conversion using a 3 × 3 matrix for converting a color signal into a color difference signal. 6. The image processing apparatus according to claim 5, wherein in the color space conversion, the color difference signal is expanded into a color space to perform partial color correction. 7. The image according to claim 6, wherein in the partial color correction, when a certain point is corrected to a desired color, a conical range centering on the certain point is corrected. Processing equipment.