JP7748334B2 - Image display device and program - Google Patents

Description

Embodiments of the present invention relate to an image display device and a program.

Conventionally, imaging devices such as digital cameras have disclosed techniques for detecting faces from captured images of people using AI (Artificial Intelligence) technology and then color correcting the skin color of the detected faces.

Patent No. 4983643

However, when applying conventional technology to image display devices such as televisions, the environment when the input video was shot and edited is unknown, and the video characteristics differ for each content or scene, making it difficult to perform color correction appropriate for the content or scene.

An image display device according to an embodiment is an image display device that processes input video data and outputs the processed video data to a display unit, and includes: a face detection unit that detects a human face from the video data; a histogram detection unit that detects a hue histogram from the video data; a shift detection unit that uses a face detection result from the face detection unit and a histogram detection result from the histogram detection unit to detect a red shift degree, which is a degree to which the hue of the skin color of the video data is shifted toward red, and a yellow shift degree, which is a degree to which the hue of the skin color of the video data is shifted toward yellow; a color correction parameter generation unit that generates color correction parameters based on the red shift degree and the yellow shift degree detected by the shift detection unit; and a color correction unit that performs color correction of the video data based on the color correction parameters that are generated by the color correction unit, wherein the color correction parameter generation unit has a standard first color correction parameter that is applied when the degree of red shift and the degree of yellow shift are minimum values, a second color correction parameter that is optimal when the degree of red shift is maximum value, and a third color correction parameter that is optimal when the degree of yellow shift is maximum value, and when the first color correction parameter is a value that adds redness to a skin color region, the second color correction parameter is a value that is obtained by subtracting the amount of redness that is added from the first color correction parameter, and the third color correction parameter is a value that is obtained by adding the amount of redness that is added from the first color correction parameter.

FIG. 1 is a schematic diagram illustrating an example of an image display device according to a first embodiment. FIG. 2 is a functional block diagram showing the functional configuration of the skin image correction unit. FIG. 3 is a diagram showing an example of a face detection method in the face detection unit. FIG. 4 is a diagram showing an example of a histogram detection method in the histogram detection unit. FIG. 5 is a diagram showing an example of adding restrictions to histogram detection. FIG. 6 is a diagram showing an example of color correction in the color correction unit. FIG. 7 is a flowchart showing an example of the flow of the skin image correction process executed by the skin image corrector. FIG. 8 is a schematic diagram showing a modified example of the image display device. FIG. 9 is a functional block diagram showing the functional configuration of a skin image correction unit according to the second embodiment. FIG. 10 is a diagram showing an example of a histogram detection method in the histogram detection unit. FIG. 11 is a flowchart showing an example of the flow of the skin image correction process executed by the skin image corrector.

The image display device and program are described in detail below with reference to the attached drawings.

(First embodiment)
FIG. 1 is a schematic diagram showing an example of an image display device 1 according to the first embodiment.

The image display device 1 includes an image processing unit 10 and a display unit 12. Data that has undergone image processing in the image processing unit 10 is transferred to the display unit 12 and displayed on the screen.

Video data 40 is input to the image processing unit 10 from a tuner unit, an HDMI (High-Definition Multimedia Interface) (registered trademark) terminal, or the like (not shown). The image processing unit 10 processes the input video data 40 to generate video data 42, which it then outputs to the display unit 12.

The image processing unit 10 includes an image quality adjustment unit 20 and a skin image correction unit 22.

The image quality adjustment unit 20 has the function of adjusting the gamma, hue, brightness, etc. of the input video data 40. The image quality adjustment unit 20 adjusts the input video data 40 to generate video data 41, which is then output to the skin image correction unit 22.

The skin image correction unit 22 determines scenes to be corrected and performs color correction in real time on the video data 41 input from the image quality adjustment unit 20, in order to display good images even when the environment (conditions) at the time of shooting or editing are unknown.

Here, Figure 2 is a functional block diagram showing the functional configuration of the skin image correction unit 22.

As shown in FIG. 2, the skin image correction unit 22 has a face detection unit 23, a histogram detection unit 24, a skin color hue shift detection unit 25 which is a shift detection unit, a color correction parameter generation unit 26, and a color correction unit 27. In general, the skin image correction unit 22 uses the face detection result from the face detection unit 23 and the histogram detection result from the histogram detection unit 24 to detect the degree of hue shift in the skin color of the video data 41 (input video) input from the image quality adjustment unit 20 in the skin color hue shift detection unit 25. Based on the degree of hue shift detected in the skin color hue shift detection unit 25, the skin image correction unit 22 generates correction parameters corresponding to the degree of hue shift in the color correction parameter generation unit 26, and performs color correction in the color correction unit 27.

The face detection unit 23, histogram detection unit 24, skin color hue shift detection unit 25, color correction parameter generation unit 26, and color correction unit 27 may be realized by hardware, software, or both hardware and software.

The display unit 12 includes a display driver 14 and a display unit 16. The display unit 16 is a display that displays images. The display unit 16 is, for example, an organic light-emitting diode (EL) display, a liquid crystal display, or the like.

The display driver 14 converts the video data 42 input from the image processor 10 into voltage and current for driving the display unit 16, and drives the display unit 16.

Next, we will describe in detail each component that makes up the skin image correction unit 22.

The face detection unit 23 detects human faces from the video data 41 input from the image quality adjustment unit 20. Here, Figure 3 is a diagram showing an example of a face detection method used by the face detection unit 23. As shown in Figure 3, one face detection method involves using a DNN (Deep Neural Network) that has been trained in advance to detect various faces to divide the video data 41 into multiple areas and calculate the probability (0 to 1) that each area contains a human face. With this method, areas that contain human faces have high numerical values and areas that do not contain human faces have low numerical values. Therefore, the face detection unit 23 detects areas with values greater than a certain threshold as containing a human face and areas with values smaller than the threshold as not containing a human face. If the area containing a human face is equal to or greater than a certain area, the face detection unit 23 detects it as a human face.

The histogram detection unit 24 performs hue histogram detection from the video data 41 input from the image quality adjustment unit 20. Here, Figure 4 shows an example of a histogram detection method used by the histogram detection unit 24. Figure 4(a) shows a hue distribution based on CbCr in a YCbCr signal, and Figure 4(b) shows the YCbCr color space. Histogram detection by the histogram detection unit 24 involves, for example, determining the number of pixels distributed in a specific hue in the entire image related to the video data 41, or in a partial area of the image related to the video data 41 that includes a person's face, and creating a histogram.

Here, Figure 5 shows an example of adding restrictions to histogram detection. As shown in Figure 5, the histogram detection unit 24 may add restrictions to the saturation range in the three-dimensional YCbCr color space (Figure 5(a)) or the luminance range in the three-dimensional YCbCr color space (Figure 5(b)) during histogram detection.

The skin color hue shift detection unit 25 uses the face detection results from the face detection unit 23 and the histogram detection results from the histogram detection unit 24 to detect the degree of hue shift in the skin color of the video data 41 input from the image quality adjustment unit 20. The skin color hue shift detection unit 25 detects, for example, the degree to which the hue of the skin color of the video data 41 input from the image quality adjustment unit 20 has shifted toward red or yellow.

For example, if the skin color hue is shifted toward red, the skin color hue shift detection unit 25 calculates a "shift toward red" indicating the degree of the shift toward red. Furthermore, if the skin color hue is shifted toward yellow, the skin color hue shift detection unit 25 calculates a "shift toward yellow" indicating the degree of the shift toward yellow. On the other hand, if the skin color hue is not shifted toward red, or if the skin color hue is not shifted toward yellow, the skin color hue shift detection unit 25 sets the "shift toward red" and "shift toward yellow," indicating the degree of the shift toward red, to 0.

The color correction parameter generation unit 26 generates color correction parameters to be applied to the color correction unit 27 based on the "amount of shift toward red" or "amount of shift toward yellow" detected by the skin color hue shift detection unit 25.

For example, the color correction parameter generation unit 26 has a standard color management table (CMS[m]) that is applied when there is no hue shift, a color management table (CMR[m]) that is optimal when the degree of red shift (RH; 0 to 1) is 1, and a color management table (CMY[m]) that is optimal when the degree of yellow shift (YH; 0 to 1) is 1.

The color correction parameter generation unit 26 generates the color correction parameters as a color management table (CM[m]) that is ultimately applied to the color correction unit 27. Here, CM[m] consists of the elements hue H[h], saturation S[s], and lightness V[v]. In other words, m = h × s × v.

When the degree of red shift and the degree of yellow shift in the detection result by the skin color hue shift detection unit 25 are both 0, the color correction parameter generation unit 26 sets CM[m] = CMS[m] as a color correction parameter to be applied to the color correction unit 27. Furthermore, when the degree of red shift in the detection result by the skin color hue shift detection unit 25 is not 0, the color correction parameter generation unit 26 sets CM[m] = RH × CMR[m] + (1 - RH) × CMS[m] as a color correction parameter to be applied to the color correction unit 27. Furthermore, when the degree of yellow shift in the detection result by the skin color hue shift detection unit 25 is not 0, the color correction parameter generation unit 26 sets CM[m] = YH × CMY[m] + (1 - YH) × CMS[m] as a color correction parameter to be applied to the color correction unit 27.

Here, when CMS[m] is a value that adds a slight redness to the skin color area, CMR[m] is a value that is a slight negative (minus) amount of redness to be added, and CMY[m] is a value that is a slight positive (plus) amount of redness to be added. If the image data 41 (input image) input from the image quality adjustment unit 20 is shifted toward red, excessive correction can be suppressed. Also, if the image data 41 (input image) input from the image quality adjustment unit 20 is shifted toward yellow, insufficient correction can be compensated for.

The color correction unit 27 performs color correction on the video data 41 input from the image quality adjustment unit 20 based on the color management table (CM[m]) applied by the color correction parameter generation unit 26.

Figure 6 shows an example of color correction in the color correction unit 27. CM[m] consists of the elements hue H[h], saturation S[s], and lightness V[v]. Hue H[h], saturation S[s], and lightness V[v] represent the degree of correction of hue, saturation, and brightness at the point where h, s, and v overlap in three-dimensional YCbCr space (see Figure 6(d)).

For intermediate values between points, the color correction unit 27 interpolates using the correction values of adjacent points.

Next, we will explain an example of the flow of the skin image correction process performed by the skin image correction unit 22.

Figure 7 is a flowchart showing an example of the flow of the skin image correction process executed by the skin image correction unit 22. As shown in Figure 7, the face detection unit 23 divides the video data 41 input from the image quality adjustment unit 20 into multiple areas and detects whether each area contains a human face (step S1).

If the area containing a human face is equal to or larger than a certain area (Yes in step S2), the face detection unit 23 determines that a human face has been detected in the video data 41, and proceeds to step S3. On the other hand, if the area containing a human face is smaller than a certain area (No in step S2), the face detection unit 23 determines that a human face has not been detected in the video data 41, and proceeds to step S6.

In step S3, the histogram detection unit 24 obtains a hue histogram from the video data 41 input from the image quality adjustment unit 20.

Next, the skin color hue shift detection unit 25 uses the face detection results from the face detection unit 23 and the histogram detection results from the histogram detection unit 24 to detect the degree to which the skin color hue of the video data 41 input from the image quality adjustment unit 20 has shifted toward red and the degree to which the skin color hue has shifted toward yellow (step S4).

If the skin color hue has shifted toward red or toward yellow (Yes in step S4), the skin color hue shift detection unit 25 calculates the "amount of red shift" indicating the degree of red shift or the "amount of yellow shift" indicating the degree of yellow shift (step S5). On the other hand, if the skin color hue has not shifted toward red or the skin color hue has not shifted toward yellow (No in step S4), or if the area containing a human face is less than a certain area (No in step S2), the skin color hue shift detection unit 25 sets the "amount of red shift" indicating the degree of red shift and the "amount of yellow shift" indicating the degree of yellow shift to 0 (step S6).

Next, the color correction parameter generation unit 26 generates color correction parameters to be applied to the color correction unit 27 based on the "amount of shift toward red" or "amount of shift toward yellow" detected by the skin color hue shift detection unit 25 (step S7).

Finally, the color correction unit 27 performs color correction on the video data 41 input from the image quality adjustment unit 20 based on the color correction parameters applied by the color correction parameter generation unit 26 (step S8).

In this way, the image display device of the first embodiment detects faces and the degree of hue shift in real time, and corrects skin color to match the characteristics of the input video. This makes it possible to display beautiful skin colors even in content where the environment (conditions) at the time of shooting or editing are unknown, thereby enabling good video display.

In this embodiment, the histogram detection unit 24 acquires a hue histogram from the video data 41 input from the image quality adjustment unit 20, but this is not limited to this. Here, FIG. 8 is a schematic diagram showing a modified example of the image display device 1. As shown in FIG. 8, the image display device 1 may further include a face region extraction unit 28 in the skin image correction unit 22. The face region extraction unit 28 extracts only those areas of the input video that are highly likely to contain a human face based on the face detection results from the face detection unit 23. The histogram detection unit 24 then acquires a hue histogram from only those areas of the input video that are highly likely to contain a human face.

By doing this, it is possible to minimize the inclusion of components other than human faces in the histogram detection results.

Second Embodiment
Next, a second embodiment will be described.

The second embodiment differs from the first embodiment in that a saturation histogram is detected from the video data 41. In the following explanation of the second embodiment, we will omit explanations of the same parts as the first embodiment and focus on the differences from the first embodiment.

Figure 9 is a functional block diagram showing the functional configuration of the skin image correction unit 22 according to the second embodiment.

As shown in FIG. 9, the skin image correction unit 22 of the image display device 1 according to this embodiment has a histogram detection unit 34, a skin color saturation shift detection unit 35 (which is a shift detection unit), and a color correction parameter generation unit 36, instead of the histogram detection unit 24, skin color hue shift detection unit 25, and color correction parameter generation unit 26 described in the second embodiment.

The histogram detection unit 34 performs saturation histogram detection from the video data 41 input from the image quality adjustment unit 20. Here, Figure 10 shows an example of a histogram detection method used by the histogram detection unit 34. Figure 10(a) shows a saturation distribution based on CbCr in a YCbCr signal, and Figure 10(b) shows the YCbCr color space. Histogram detection by the histogram detection unit 34 involves, for example, determining the number of pixels distributed at a specific saturation in the entire image related to the video data 41, or in a partial area of the image related to the video data 41 that includes a person's face, and creating a histogram. As shown in Figure 10(a), the histogram detection unit 34 may also apply saturation restrictions in the three-dimensional YCbCr color space during histogram detection.

The skin color saturation shift detection unit 35 uses the face detection results from the face detection unit 23 and the histogram detection results from the histogram detection unit 34 to detect the degree of saturation shift in skin color in the video data 41 input from the image quality adjustment unit 20. The skin color saturation shift detection unit 35 detects, for example, the "amount of high saturation shift," which is the degree to which the saturation of skin color has shifted to a higher saturation than expected, and the "amount of low saturation shift," which is the degree to which the saturation of skin color has shifted to a lower saturation than expected.

The color correction parameter generation unit 36 generates color correction parameters to be applied to the color correction unit 27 based on the "high saturation shift amount" and "low saturation shift amount" detected by the skin color saturation shift detection unit 35.

For example, the color correction parameter generation unit 36 may have a standard color management table (CMS[m]) that is applied when there is no saturation shift, a color management table (CMR[m]) that is optimal when the degree of high saturation shift (RH; 0 to 1) is 1, and a color management table (CMY[m]) that is optimal when the degree of low saturation shift (YH; 0 to 1) is 1.

The color correction parameter generation unit 36 generates the color correction parameters as a color management table (CM[m]) that is ultimately applied to the color correction unit 27. Here, CM[m] consists of the elements hue H[h], saturation S[s], and lightness V[v]. In other words, m = h × s × v.

When both the degree of high saturation shift and the degree of low saturation shift detected by the skin color saturation shift detection unit 35 are zero, the color correction parameter generation unit 36 sets CM[m] = CMS[m] as a color correction parameter to be applied to the color correction unit 27. Furthermore, when the degree of high saturation shift detected by the skin color saturation shift detection unit 35 is not zero, the color correction parameter generation unit 36 sets CM[m] = RH × CMR[m] + (1 - RH) × CMS[m] as a color correction parameter to be applied to the color correction unit 27. Furthermore, when the degree of low saturation shift detected by the skin color saturation shift detection unit 35 is not zero, the color correction parameter generation unit 36 sets CM[m] = YH × CMY[m] + (1 - YH) × CMS[m] as a color correction parameter to be applied to the color correction unit 27.

Here, when CMS[m] is a value that slightly increases the saturation for the skin color area, CMR[m] is a value that increases the saturation by some amount (-), and CMY[m] is a value that increases the saturation by some amount (+). If the image data 41 (input image) input from the image quality adjustment unit 20 is shifted toward high saturation, excessive correction can be suppressed. If the image data 41 (input image) input from the image quality adjustment unit 20 is shifted toward low saturation, insufficient correction can be compensated for.

Next, we will explain an example of the flow of the skin image correction process performed by the skin image correction unit 22.

Figure 11 is a flowchart showing an example of the flow of the skin image correction process executed by the skin image correction unit 22. As shown in Figure 11, the face detection unit 23 divides the video data 41 input from the image quality adjustment unit 20 into multiple areas and detects whether each area contains a human face (step S11).

If the area containing a human face is equal to or larger than a certain area (Yes in step S12), the face detection unit 23 determines that a human face has been detected in the video data 41, and proceeds to step S13. On the other hand, if the area containing a human face is smaller than a certain area (No in step S12), the face detection unit 23 determines that a human face has not been detected in the video data 41, and proceeds to step S16.

In step S13, the histogram detection unit 34 obtains a saturation histogram from the video data 41 input from the image quality adjustment unit 20.

Next, the skin color saturation shift detection unit 35 uses the face detection results from the face detection unit 23 and the histogram detection results from the histogram detection unit 34 to detect the degree to which the skin color saturation of the video data 41 input from the image quality adjustment unit 20 has shifted to a higher saturation than expected (step S14).

If the skin color saturation has shifted higher than expected or lower than expected (Yes in step S14), the skin color saturation shift detection unit 35 calculates a "high saturation shift amount" indicating the degree of shift to high saturation or a "low saturation shift amount" indicating the degree of shift to low saturation (step S15). On the other hand, if the skin color saturation has not shifted higher than expected or has not shifted lower than expected (No in step S14), or if the area containing a human face is less than a certain area (No in step S12), the skin color saturation shift detection unit 35 sets the "high saturation shift amount" indicating the degree of shift to high saturation and the "low saturation shift amount" indicating the degree of shift to low saturation to 0 (step S16).

Next, the color correction parameter generation unit 36 generates color correction parameters to be applied to the color correction unit 27 based on the "high saturation shift amount" or "low saturation shift amount" detected by the skin color saturation shift detection unit 35 (step S17).

Finally, the color correction unit 27 performs color correction on the video data 41 input from the image quality adjustment unit 20 based on the color correction parameters applied by the color correction parameter generation unit 26 (step S18).

In this way, the image display device of the second embodiment detects faces and the degree of saturation shift in real time, and corrects skin color to match the characteristics of the input video. This makes it possible to display beautiful skin colors even in content where the environment (conditions) at the time of shooting or editing are unknown, thereby enabling good video display.

In this embodiment, the histogram detection unit 34 acquires a saturation histogram from the video data 41 input from the image quality adjustment unit 20, but this is not limited to this. For example, the histogram detection unit 34 may acquire a hue histogram as described in the first embodiment, in addition to the saturation histogram acquired from the video data 41 input from the image quality adjustment unit 20. In this way, by detecting faces in real time and detecting the degree of hue shift and the degree of saturation shift, and correcting skin color to match the characteristics of the input video, it is possible to display beautiful skin colors in any content.

The program (software) executed by the image display device 1 of this embodiment is provided pre-installed in a ROM or the like.

The program (software) executed by the image display device 1 of this embodiment may be provided by being recorded in an installable or executable file format on a computer-readable recording medium such as a CD-ROM, flexible disk (FD), CD-R, or DVD (Digital Versatile Disc).

Furthermore, the program (software) executed by the image display device 1 of this embodiment may be stored on a computer connected to a network such as the Internet and provided by being downloaded via the network. Furthermore, the program (software) executed by the image display device 1 of this embodiment may be provided or distributed via a network such as the Internet.

Although the above describes embodiments and variations of the present invention, these embodiments and variations are presented as examples and are not intended to limit the scope of the invention. These novel embodiments and variations may be embodied in a variety of other forms, and various omissions, substitutions, and modifications may be made without departing from the spirit of the invention. The above embodiments and variations are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as set forth in the claims.

REFERENCE SIGNS LIST 1 image display device 12 display unit 23 face detection unit 24, 34 histogram detection unit 25, 35 shift detection unit 26, 36 color correction parameter generation unit 27 color correction unit 28 face region extraction unit

Claims (7)

An image display device that processes input video data and outputs the processed video data to a display unit,
a face detection unit that detects a person's face from the video data;
a histogram detection unit that detects a hue histogram from the video data;
a shift detection unit that uses the face detection result from the face detection unit and the histogram detection result from the histogram detection unit to detect a red shift degree, which is the degree to which the hue of the skin color of the video data is shifted toward red, and a yellow shift degree, which is the degree to which the hue of the skin color of the video data is shifted toward yellow;
a color correction parameter generation unit that generates parameters for color correction based on the degree of red shift and the degree of yellow shift detected by the shift detection unit;
a color correction unit that performs color correction on the video data based on the color correction parameters generated by the color correction parameter generation unit;
Equipped with
The color correction parameter generation unit
a standard first color correction parameter to be applied when the degree of red shift and the degree of yellow shift are at their minimum values, a second color correction parameter that is optimal when the degree of red shift is at its maximum value, and a third color correction parameter that is optimal when the degree of yellow shift is at its maximum value,
When the first color correction parameter is a value for adding reddishness to a skin color region, the second color correction parameter is a minus value obtained by comparing the amount of reddishness to the first color correction parameter, and the third color correction parameter is a plus value obtained by comparing the amount of reddishness to the first color correction parameter.
An image display device characterized by: An image display device that processes input video data and outputs the processed video data to a display unit,
a face detection unit that detects a person's face from the video data;
a histogram detection unit that detects a saturation histogram from the video data;
a shift detection unit that uses the face detection result from the face detection unit and the histogram detection result from the histogram detection unit to detect a high saturation shift degree, which is a degree to which the saturation of the skin color of the video data has shifted to a higher saturation than an assumed value, and a low saturation shift degree, which is a degree to which the saturation of the skin color of the video data has shifted to a lower saturation than an assumed value;
a color correction parameter generation unit that generates parameters for color correction based on the degree of the high saturation shift and the degree of the low saturation shift detected by the shift detection unit;
a color correction unit that performs color correction on the video data based on the color correction parameters generated by the color correction parameter generation unit;
Equipped with
The color correction parameter generation unit
a standard first color correction parameter applied when the degree of the high saturation shift and the degree of the low saturation shift are at their minimum values, a second color correction parameter that is optimal when the degree of the high saturation shift is at its maximum value, and a third color correction parameter that is optimal when the degree of the low saturation shift is at its maximum value,
When the first color correction parameter is a value that increases saturation for a skin color region, the second color correction parameter is a value obtained by subtracting the amount of saturation increase from the first color correction parameter, and the third color correction parameter is a value obtained by adding the amount of saturation increase from the first color correction parameter.
An image display device characterized by: the histogram detection unit limits the range of saturation in a three-dimensional YCbCr color space in detecting a histogram from the video data.
3. The image display device according to claim 1, wherein the image display device is a display device having a plurality of display areas. the histogram detection unit limits a luminance range in a three-dimensional YCbCr color space in detecting a histogram from the video data.
2. The image display device according to claim 1, wherein the image display device is a display device having a plurality of display areas. a face region extraction unit that extracts only a region of the video data that is highly likely to contain a human face based on the face detection result of the face detection unit;
the histogram detection unit acquires a hue histogram only from the area extracted by the face area extraction unit that has a high probability of being the person's face.
2. The image display device according to claim 1, wherein the image display device is a display device having a plurality of display areas. A computer that controls an image display device that processes input video data and outputs the processed video data to a display unit,
a face detection unit that detects a person's face from the video data;
a histogram detection unit that detects a hue histogram from the video data;
a shift detection unit that uses the face detection result from the face detection unit and the histogram detection result from the histogram detection unit to detect a red shift degree, which is the degree to which the hue of the skin color of the video data is shifted toward red, and a yellow shift degree, which is the degree to which the hue of the skin color of the video data is shifted toward yellow;
a color correction parameter generation unit that generates parameters for color correction based on the degree of red shift and the degree of yellow shift detected by the shift detection unit;
a color correction unit that performs color correction on the video data based on the color correction parameters generated by the color correction parameter generation unit;
It functions as
The color correction parameter generation unit
a standard first color correction parameter to be applied when the degree of red shift and the degree of yellow shift are at their minimum values, a second color correction parameter that is optimal when the degree of red shift is at its maximum value, and a third color correction parameter that is optimal when the degree of yellow shift is at its maximum value,
When the first color correction parameter is a value for adding reddishness to a skin color region, the second color correction parameter is a minus value obtained by comparing the amount of reddishness to the first color correction parameter, and the third color correction parameter is a plus value obtained by comparing the amount of reddishness to the first color correction parameter.
Program for. A computer that controls an image display device that processes input video data and outputs the processed video data to a display unit,
a face detection unit that detects a person's face from the video data;
a histogram detection unit that detects a saturation histogram from the video data;
a shift detection unit that uses the face detection result from the face detection unit and the histogram detection result from the histogram detection unit to detect a high saturation shift degree, which is a degree to which the saturation of the skin color of the video data has shifted to a higher saturation than an assumed value, and a low saturation shift degree, which is a degree to which the saturation of the skin color of the video data has shifted to a lower saturation than an assumed value;
a color correction parameter generation unit that generates parameters for color correction based on the degree of the high saturation shift and the degree of the low saturation shift detected by the shift detection unit;
a color correction unit that performs color correction on the video data based on the color correction parameters generated by the color correction parameter generation unit;
It functions as
The color correction parameter generation unit
a standard first color correction parameter applied when the degree of the high saturation shift and the degree of the low saturation shift are at their minimum values, a second color correction parameter that is optimal when the degree of the high saturation shift is at its maximum value, and a third color correction parameter that is optimal when the degree of the low saturation shift is at its maximum value,
When the first color correction parameter is a value that increases saturation for a skin color region, the second color correction parameter is a value obtained by subtracting the amount of saturation increase from the first color correction parameter, and the third color correction parameter is a value obtained by adding the amount of saturation increase from the first color correction parameter.
Program for.