WO2020230445A1 - Image processing device, image processing method, and computer program - Google Patents

Abstract

This image processing device (10) is provided with: an imaging processing unit (111) which captures a first image with the subject illuminated on the basis of a first illumination pattern that indicates a pattern for lighting of multiple lights, and captures a second image with the subject illuminated on the basis of a second illumination pattern; a feature image extraction unit (112) which extracts the region of a recess on the subject from the first image and the second image, and generates a first feature image and a second feature image; and a feature image combining unit (113) which combines the first feature image and the second feature image to generate a combined feature image.

Description

Image processing equipment, image processing methods, and computer programs

The present disclosure relates to an image processing device, an image processing method, and a computer program.

Conventionally, wrinkles on the skin have been detected by analyzing an image of the subject's face (hereinafter referred to as "face image"). In the detection of wrinkles, if the skin is too glossy or the shadow of the skin is too dark, there is a high possibility that false detection of wrinkles and omission of detection will occur. In Patent Document 1, an illuminance measurement value of each predetermined point is acquired from a user's face image, and a plurality of light sources are individually controlled based on the acquired illuminance measurement value of each predetermined point to control the illuminance of the default point. There is disclosed an illuminance control device that suppresses erroneous detection of wrinkles and omission of detection by adjusting the illumination of the face so that the value approaches a predetermined set value.

JP-A-2016-81677

Wrinkle detection omission is not limited to the above cases. For example, wrinkle detection omissions can occur if illumination from multiple different angles just erases the shadows of the wrinkles. Such detection omissions are not limited to wrinkles on the skin, but may occur in the overall image processing for detecting the region of the concave portion from the shadow generated in the concave portion.

The non-limiting embodiment of the present disclosure contributes to the provision of an image processing device, an image processing method, and a computer program that suppresses detection omission of a concave portion of a subject.

The image processing apparatus according to one aspect of the present disclosure illuminates a subject based on a first illumination pattern showing a pattern relating to light emission of a plurality of illuminations, captures a first image, and uses the second illumination pattern as described above. The imaging processing unit that illuminates the subject and captures the second image, and the concave region of the subject is extracted from the first image and the second image, respectively, and the first feature image and the second feature image are obtained. It includes a feature image extracting unit to be generated, and a feature image synthesizing unit that synthesizes the first feature image and the second feature image to generate a composite feature image.

It should be noted that these comprehensive or specific aspects may be realized by a system, a method, an integrated circuit, a computer program, or a recording medium, and any of the systems, devices, methods, integrated circuits, computer programs, and recording media. It may be realized by various combinations.

According to one aspect of the present disclosure, it is possible to suppress the detection omission of the concave portion of the subject.

Further advantages and effects in one aspect of the present disclosure will be apparent from the specification and drawings. Such advantages and / or effects are provided by some embodiments and features described in the specification and drawings, respectively, but not all need to be provided in order to obtain one or more identical features. There is no.

The figure which shows the appearance example of the image processing apparatus which concerns on Embodiment 1. A block diagram showing an example of the configuration of the image processing apparatus according to the first embodiment. The figure for demonstrating an example of the generation and composition of the wrinkle image which concerns on Embodiment 1. The figure for demonstrating an example of the process of generating the synthetic wrinkle image which concerns on Embodiment 1. A flowchart showing a processing example of the image processing apparatus according to the first embodiment. The figure which shows the appearance of the modification of the image processing apparatus which concerns on Embodiment 1. The figure for demonstrating an example of the thickness of the wrinkle in the synthetic wrinkle image which concerns on Embodiment 1. The figure which shows the appearance example of the image processing apparatus which concerns on Embodiment 2. A block diagram showing an example of the configuration of the image processing apparatus according to the second embodiment. A flowchart showing a processing example of the image processing apparatus according to the third embodiment. The figure which shows the example of the hardware configuration which concerns on embodiment of this disclosure.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings as appropriate. However, more detailed explanation than necessary may be omitted. For example, detailed explanations of already well-known matters and duplicate explanations for substantially the same configuration may be omitted. This is to avoid unnecessary redundancy of the following description and to facilitate the understanding of those skilled in the art.

(Embodiment 1)
<Configuration example>
FIG. 1 is a diagram showing an example of the appearance of the image processing device 10 according to the first embodiment.

The image processing device 10 is a device that detects a concave region of a subject from a photographed image taken by illuminating the subject. Hereinafter, an example in which the subject is a person's face and the concave portion of the subject is a wrinkle on the face will be described. However, the subject may be skin other than the face of the person (for example, skin of limbs). The recesses may be other than wrinkles (eg, pores, scars, etc.). Further, the subject is not limited to a person, but may be an object (for example, a plate made of metal or plastic). The recess may be a scratch on the surface of the object.

The image processing device 10 includes a photographing unit 101, an illumination unit 102 (102A, 102B, 102C, 102D), and a display unit 103 on the main surface 21 of the housing 20. The main surface 21 of the housing 20 is a rectangular plane having a size one size larger than the human head. For example, the face is arranged at a position where the center of the face faces the center of the main surface 21 at a distance of about several tens of centimeters from the main surface 21.

The photographing unit 101 is, for example, a camera including a lens and an image sensor, and is arranged above the center of the main surface 21. When the face is in a fixed position, the photographing unit 101 photographs the face from a substantially front direction.

The display unit 103 is, for example, a liquid crystal display with a touch panel, and accepts operations on the image processing device 10 and displays an image. The operation may be accepted not via the touch panel but through another input device such as a keyboard and / or a mouse. Alternatively, the display unit 103 may automatically operate when the photographing unit 101 detects the face of the subject within an appropriate range. The display unit 103 displays the face image F, which is a left-right inverted image including the face of the subject photographed by the photographing unit 101.

The lighting unit 102 is arranged so as to emit light toward the outside on the main surface 21 side, using a light emitting element such as an LED (Light-Emitting Diode) as a light source. The illumination units 102A, 102B, 102C, and 102D are arranged near the upper side, the lower side, the left side, and the right side of the main surface 21, respectively. That is, the lighting unit 102A is in a position where the face is illuminated from above, the lighting unit 102B is in a position where the face is illuminated from below, the lighting unit 102C is in a position where the face is illuminated from the left side, and the lighting unit 102D is in a position where the face is illuminated from the right side. Be placed. In other words, each lighting unit 102 has a different irradiation angle of light to the face.

FIG. 2 is a block diagram showing an example of the configuration of the image processing device 10.

The image processing device 10 includes a photographing unit 101, an illumination unit 102 (102A, 102B, 102C, 102D), a display unit 103, a storage unit 104, and a control unit 105. The photographing unit 101, the lighting unit 102, and the display unit 103 are as described above.

The storage unit 104 is, for example, a memory and / or a storage, and holds a program and data processed by the control unit 105.

The control unit 105 is, for example, a CPU (Central Processing Unit), and executes processing for realizing the functions of the image processing device 10. The image processing device 10 has, for example, the functions of a shooting processing unit 111, a feature image extraction unit 112, a feature image composition unit 113, and a display processing unit 114.

The shooting processing unit 111 controls the lighting unit 102 and the shooting unit 101 to shoot images (face images) of a plurality of subjects. For example, the photographing processing unit 111 controls the illumination unit 102 based on the first illumination pattern to illuminate the subject, captures the first face image, and controls the illumination unit 102 based on the second illumination pattern. Illuminates the subject and takes a second facial image.

The first illumination pattern is different from the second illumination pattern in the lighting and / or extinguishing pattern of the illumination unit 102. For example, in the first illumination pattern, the upper and / or lower illumination units 102A and 102B are turned on, and the left and / or right illumination units 102C and 102D are extinguished. In the second illumination pattern, the upper and / or lower illumination units 102A and 102B are turned off, and the left and / or right illumination units 102C and 102D are turned on.

Alternatively, the first illumination pattern is different from the second illumination pattern in the magnitude of the illuminance of the illumination unit 102. For example, in the first illumination pattern, the illuminance of the upper and / or lower illumination units 102A and 102B is larger than the illuminance of the left and / or right illumination units 102C and 102D. In the second illumination pattern, the illuminance of the upper and / or lower illumination units 102A and 102B is smaller than the illuminance of the left and / or right illumination units 102C and 102D.

Note that the photographing processing unit 111 may control the upper and lower lighting units 102A and 102B to different illuminances when the upper and lower lighting units 102A and 102B are turned on. Similarly, when the left and right lighting units 102C and 102D are turned on, the photographing processing unit 111 may control the left and right lighting units 102C and 102D to different illuminances.

In this way, the image processing device 10 captures a plurality of face images by changing the illumination patterns of the illumination units 102A, 102B, 102C, and 102D having different irradiation angles for the subject. As a result, even if the shadow of the wrinkle disappears in one lighting pattern or the shadow of the wrinkle is photographed lightly, the shadow of the wrinkle can be photographed deeply in another lighting pattern.

The feature image extraction unit 112 extracts wrinkle regions, which are concave regions of the subject, from the first and second face images, respectively, and generates first and second wrinkle images, which are examples of feature images. For example, the feature image extraction unit 112 extracts a wrinkle region from a face image using a predetermined edge detection filter to generate a wrinkle image.

The feature image synthesizing unit 113 synthesizes the first and second wrinkle images generated by the feature image extracting unit 112 to generate a composite wrinkle image. As a result, wrinkles contained in only one of the first and second wrinkle images are also included in the synthetic wrinkle image, so that omission of detection of wrinkles can be suppressed.

The display processing unit 114 displays, for example, the composite wrinkle image generated by the feature image synthesis unit 113 on the display unit 103.

<Details of wrinkle image generation and composition>
The generation and composition of wrinkle images will be described in detail with reference to FIG.

As shown in FIG. 3, the first face image 200a and the second face image 200b are included in the face included in the first face image 200a and the second face image 200b because the shooting timings are different. The position, size, etc. may be different from the face. Therefore, when the first and second wrinkle images extracted from the first and second face images 200a and 200b are simply combined, the position and size of the wrinkles may be deviated and combined.

Therefore, the feature image extraction unit 112 adjusts at least one of the first and second face images 200a and 200b based on the face feature points so that the position and / or size of the face match, and then the feature image extraction unit 112 Wrinkle images 300a and 300b may be generated from the adjusted face images 201a and 201b, respectively. Facial feature points are data generated by detecting characteristic parts of the face such as facial contours, eyes, nose, mouth, and right using a predetermined image analysis, and are, for example, nodes and edges. It is data composed of. When a device capable of fixing the face is used, the position and / or size of the face in the face image can be fixed, so that the above processing may not be performed.

The feature image synthesizing unit 113 synthesizes the first and second wrinkle images 300a and 300b adjusted and generated by the feature image extracting unit 112 to generate a composite wrinkle image 301. As a result, the composite wrinkle image 301 with less deviation is generated. Further, as shown in FIG. 3, the composite wrinkle image 301 has a wrinkle region 211a and a second face image 200b that are captured by the first face image 200a and not captured by the second face image 200b. The first facial image 200a, which was captured, includes both the wrinkled region 211b, which was not captured.

Next, with reference to FIG. 4, an example of a process of synthesizing a plurality of wrinkle images to generate a composite wrinkle image will be described.

For example, as shown in FIG. 4, the feature image extraction unit 112 generates first and second wrinkle images in which the pixel value of the wrinkle region is a negative value and the pixel value of the non-wrinkle region is 0 (S1). ).

Next, the feature image synthesizing unit 113 calculates "pixel value of the first wrinkle image-pixel value of the second wrinkle image" for each pixel value of the first and second wrinkle images (S2).

Next, the feature image synthesizing unit 113 converts the negative value of "pixel value of the first wrinkled image-pixel value of the second wrinkled image" calculated in S2 to 0, and the pixel value after the third conversion. Is calculated (S3).

Next, the feature image synthesizing unit 113 calculates "first pixel value-third converted pixel value" and generates a pixel value of the composite wrinkled image (S4).

The synthesis method is not limited to the above method. For example, the maximum value may be selected by comparing each pixel of the first wrinkle image and the second wrinkle image. Alternatively, the wrinkle image may be binarized and the first wrinkle image and the second wrinkle image may be OR-combined.

By this process, a composite wrinkle image can be generated from a plurality of wrinkle images. The method of synthesizing two wrinkle images obtained by extracting a wrinkle region from a face image, which is described in the present embodiment, is only an example. For example, first, the first face image and the second face image may be combined to generate a composite face image having the shades of both wrinkles, and the wrinkle region may be extracted from the composite face image.

<Operation example>
A processing example of the image processing apparatus 10 according to the first embodiment will be described with reference to the flowchart shown in FIG.

The shooting processing unit 111 controls the lighting unit 102 based on the first lighting pattern (S11). The shooting processing unit 111 controls the shooting unit 101 to shoot the first face image 200a (S12). The shooting of the first face image 200a may be instructed by the operator.

The shooting processing unit 111 controls the lighting unit 102 based on the second lighting pattern (S13). The shooting processing unit 111 controls the shooting unit 101 to shoot the second face image 200b (S14). The shooting of the second face image 200b may be instructed by the operator.

The feature image extraction unit 112 extracts facial feature points from the first and second face images 200a and 200b, respectively (S15). The feature image extraction unit 112 adjusts at least one of the first and second face images 200a and 200b based on the extracted face feature points so that the position and size of the face match (S16).

The feature image extraction unit 112 generates first and second wrinkle images 300a and 300b from the first and second face images 201a and 201b adjusted in S16, respectively (S17).

The feature image synthesizing unit 113 synthesizes the first and second wrinkle images 300a and 300b generated in S17 to generate a composite wrinkle image 301 (S18).

The display processing unit 114 displays the synthetic wrinkle image 301 generated in S18 on the display unit 103 (S19).

By the above processing, the image processing apparatus 10 can generate and display a synthetic wrinkle image 301 in which wrinkle detection omission is suppressed.

<Modification example>
At least one of the illumination units 102A, 102B, 102C, and 102D may have a mechanism capable of adjusting the irradiation angle. In this case, the irradiation angle of at least one of the illumination units 102A, 102B, 102C, and 102D may be different between the first illumination pattern and the second illumination pattern described above. In this case, the photographing processing unit 111 may control to change the irradiation angle of the illumination unit 102 in the processing of S11 and S13 of FIG. The irradiation angles in the first and second illumination patterns may be predetermined or may be manually adjusted by the operator.

Further, as shown in FIG. 6, in the image processing device 10, the illumination units 102E and 102F are arranged at the upper half and the lower half positions near the left side of the main surface 21 of the housing 20, respectively, and the main of the housing 20. In the vicinity of the right side of the surface 21, the illumination units 102G and 102H may be arranged at the positions of the upper half and the lower half, respectively. In this case, in the first illumination pattern, the upper half illumination units 102E and 102G may be turned on, and the lower half illumination units 102F and 102H may be turned off. In the second illumination pattern, the upper half illumination units 102E and 102G may be turned off, and the lower half illumination units 102F and 102H may be turned on. The above-mentioned "turning off" may be read as irradiation with an illuminance lower than the illuminance of the lighting unit 102 that "turns on".

Further, as shown in FIG. 7A, when light 401a is irradiated from above, a shadow 402a is generated on the upper part of the wrinkle. As shown in FIG. 7B, when the light 401b is irradiated from the lower side, a shadow 402b is generated at the lower part of the wrinkle. Therefore, in the first illumination pattern, the illuminance of the lower illumination unit 102B may be smaller (or extinguished) than the illuminance of the upper illumination unit 102A. Then, in the second illumination pattern, the illuminance of the upper illumination unit 102A may be smaller (or extinguished) than the illuminance of the lower illumination unit 102B. As a result, the first wrinkle image showing the thickness La of the upper part of the wrinkle is generated from the first face image, and the second wrinkle showing the thickness Lb of the lower part of the wrinkle is generated from the second face image. An image is generated. Therefore, by synthesizing the first and second wrinkle images, as shown in FIG. 7C, a synthetic wrinkle image showing the wrinkle thickness L with higher accuracy can be generated. The above "upper side" and "lower side" may be read as "left side" and "right side".

Also, the lighting pattern is not limited to the above two patterns. For example, in the first lighting pattern, the upper lighting unit 102A is lit, in the second lighting pattern, the lower lighting unit 102B is lit, in the third lighting pattern, the left lighting unit 102C is lit, and the fourth In the illumination pattern of, the lower illumination unit 102D may be lit. In this case, the image processing device 10 generates first to fourth wrinkle images from the first to fourth face images taken in each of the first to fourth illumination patterns, and generates a composite wrinkle image. You may. As a result, the image processing apparatus 10 can suppress omission of detection of wrinkles and generate a synthetic wrinkle image showing the thickness of wrinkles with higher accuracy.

(Embodiment 2)
In the second embodiment, an example is shown in which the image processing device 10 changes the lighting at the time of shooting in cooperation with a lighting unit (hereinafter referred to as “external lighting unit”) provided in an external environment. In the second embodiment, the same reference numerals may be given to the configurations described in the first embodiment, and the description may be omitted.

<Configuration example>
FIG. 8 shows an example of the appearance of the image processing apparatus 10 according to the second embodiment. FIG. 9 shows a configuration example of the image processing device 10 according to the second embodiment.

As shown in FIG. 8, the image processing device 10 connects the external lighting unit 401 through a wired or wireless communication network 400. The wired communication network 400 is, for example, Ethernet or PLC (Power Line Communication). The wireless communication network 400 is, for example, Wi-Fi, Bluetooth®.

The external lighting unit 401 is a lighting device provided for an external environment such as a ceiling and a wall of a room, and is composed of LEDs and the like. The external lighting unit 401 may be turned on and off only, or the illuminance may be adjustable.

The image processing device 10 includes a communication unit 402 for communicating with the external lighting unit 401. The photographing processing unit 111 may control the lighting and / or extinguishing of the external lighting unit 401 or the adjustment of the illuminance via the communication unit 402.

In the second embodiment, the first lighting pattern differs from the second lighting pattern in the lighting and extinguishing patterns of the external lighting unit 401. For example, in the first illumination pattern, the external illumination unit 401 is turned on, and in the second illumination pattern, the external illumination unit 401 is extinguished. In this case, the left and / right illumination units 102C and 102D may be lit in both the first illumination pattern and the second illumination pattern.

Alternatively, when the illuminance of the external lighting unit 401 can be adjusted, the magnitude of the illuminance of the external lighting unit 401 is different from that of the second lighting pattern in the first lighting pattern. For example, in the first illumination pattern, the illuminance of the external illumination unit 401 may be larger than that in the second illumination pattern.

In this way, the image processing device 10 changes the illumination pattern of the external illumination unit 401 to capture a plurality of face images. As a result, as in the case of the first embodiment, even if the shadow of the wrinkle disappears in one lighting pattern, the shadow of the wrinkle is shot in another lighting pattern. That is, it is possible to suppress the omission of detection of wrinkles.

The external lighting unit 401 may be provided in the image processing device 10 shown in FIG. Further, the external lighting unit 401 may be incorporated into the lighting pattern as one of the plurality of lighting units 102. In addition to changing the lighting pattern, the size of the lighting may be changed, or the position of the lighting may be changed. In this case as well, since the way the light hits the face changes, different wrinkle shadows are photographed, so that detection omission can be suppressed. It should be noted that the lighting method may be controlled according to the part of the face to be detected (under the eyes, the outer corners of the eyes, the forehead, the space between the eyebrows, etc.). It is possible to further improve the detection accuracy by using an illumination pattern that matches the direction and depth of wrinkles that are likely to occur according to each part.

(Embodiment 3)
In the third embodiment, an example is shown in which a subject is instructed to move the direction of the face and a plurality of face images having different irradiation angles are taken. The image processing device 10 according to the third embodiment may have the same configuration as that of FIGS. 1 and 2.

<Operation example>
A processing example of the image processing apparatus 10 according to the third embodiment will be described with reference to the flowchart shown in FIG.

The shooting processing unit 111 instructs the subject to orient the first face (S31). For example, the photographing processing unit 111 instructs the face to turn slightly to the left. This instruction may be displayed on the display unit 103 or may be output by voice.

The photographing processing unit 111 photographs the first face image (S32). At this time, the photographing processing unit 111 may light all the lighting units 102, or may light some of the lighting units 102.

The shooting processing unit 111 instructs the subject to have a second face orientation different from that of the first face (S33). For example, the photographing processing unit 111 instructs the face to turn slightly to the right.

The shooting processing unit 111 shoots a second face image (S34). At this time, the photographing processing unit 111 may light all the lighting units 102, or may light some of the lighting units 102. Further, the illumination pattern of S32 and the illumination pattern of S34 may be the same, or may be different as described in the first embodiment.

The subsequent processing is the same as the processing of S15 to S19 shown in FIG. 5, so the description thereof will be omitted. In addition, the above-mentioned "left" and "right" of the face orientation may be read as "upper" and "lower", respectively.

According to the above processing, since the lighting of the first face image and the second face image are different, it is possible to suppress the omission of detection of wrinkles.

(Summary of this disclosure)
The image processing device 10 according to the present disclosure illuminates a subject based on a first illumination pattern showing a pattern relating to light emission of a plurality of illuminations, takes a first image, and shoots the subject based on the second illumination pattern. The photographing processing unit 111 that captures the second image by illuminating and the predetermined characteristic area of the subject are extracted from the first image and the second image, respectively, and the first feature image and the second feature image are taken. It is provided with a feature image extraction unit 112 that generates a composite feature image, and a feature image synthesis unit 113 that synthesizes a first feature image and a second feature image to generate a composite feature image.

According to this configuration, the illumination pattern when the first image is taken is different from the illumination pattern when the second image is taken, so that if one of the illumination patterns, the shadow of the characteristic portion of the subject disappears. Even if the shadow of the characteristic portion is photographed lightly, the shadow of the characteristic portion of the subject can be photographed deeply in the other lighting pattern. Therefore, in the composite feature image generated by synthesizing the first and second feature images extracted from the first and second images, respectively, the omission of detection of the region of the feature portion of the subject is suppressed.

Although the embodiments according to the present disclosure have been described in detail with reference to the drawings, the functions of the image processing apparatus 10 described above can be realized by a computer program.

FIG. 11 is a diagram showing a hardware configuration of a computer that realizes the functions of each device by a program. The computer 2100 includes an input device 2101 such as a keyboard or mouse and a touch pad, an output device 2102 such as a display or a speaker, a CPU (Central Processing Unit) 2103, a ROM (Read Only Memory) 2104, and a RAM (Random Access Memory) 2105. A hard disk device or a storage device 2106 such as SSD (Solid State Drive), a reading device 2107 that reads information from a recording medium such as a DVD-ROM (Digital Versatile Disk Read Only Memory) or a USB (Universal Serial Bus) memory, via a network. A communication device 2108 for communicating is provided, and each part is connected by a bus 2109.

Then, the reading device 2107 reads the program from the recording medium on which the program for realizing the function of each of the above devices is recorded, and stores the program in the storage device 2106. Alternatively, the communication device 2108 communicates with the server device connected to the network, and stores the program downloaded from the server device for realizing the function of each device in the storage device 2106.

Then, the CPU 2103 copies the program stored in the storage device 2106 to the RAM 2105, and sequentially reads and executes the instructions included in the program from the RAM 2105, thereby realizing the functions of the above devices.

This disclosure can be realized by software, hardware, or software linked with hardware.

Each functional block used in the description of the above embodiment is partially or wholly realized as an LSI which is an integrated circuit, and each process described in the above embodiment is partially or wholly. It may be controlled by one LSI or a combination of LSIs. The LSI may be composed of individual chips, or may be composed of one chip so as to include a part or all of functional blocks. The LSI may include data input and output. LSIs may be referred to as ICs, system LSIs, super LSIs, and ultra LSIs depending on the degree of integration.

The method of making an integrated circuit is not limited to LSI, and may be realized by a dedicated circuit, a general-purpose processor, or a dedicated processor. Further, an FPGA (Field Programmable Gate Array) that can be programmed after the LSI is manufactured, or a reconfigurable processor that can reconfigure the connection and settings of the circuit cells inside the LSI may be used. The present disclosure may be realized as digital processing or analog processing.

Furthermore, if an integrated circuit technology that replaces an LSI appears due to advances in semiconductor technology or another technology derived from it, it is naturally possible to integrate functional blocks using that technology. There is a possibility of applying biotechnology.

One aspect of the present disclosure is useful for an apparatus for detecting a concave portion of a subject.

10 Image processing device 20 Housing 21 Main surface 101 Imaging unit 102, 102A to 102H Lighting unit 103 Display unit 104 Storage unit 105 Control unit 111 Imaging processing unit 112 Feature image extraction unit 113 Feature image composition unit 114 Display processing unit 400 Communication network 401 External lighting unit 402 Communication unit

Claims (9)

1. Taking a picture of illuminating a subject based on a first lighting pattern showing patterns related to light emission of a plurality of lights to take a first image, and illuminating the subject based on a second lighting pattern to take a second image. Processing unit and
   A feature image extraction unit that extracts a recessed region of the subject from the first image and the second image to generate a first feature image and a second feature image, respectively.
   A feature image compositing unit that synthesizes the first feature image and the second feature image to generate a composite feature image,
   An image processing device.
2. The first lighting pattern differs from the second lighting pattern in that at least one of the plurality of lights is turned off.
   The image processing apparatus according to claim 1.
3. The first illumination pattern differs from the second illumination pattern in the illuminance of at least one of the plurality of illuminations.
   The image processing apparatus according to claim 1.
4. The first illumination pattern differs from the second illumination pattern in the irradiation angle of at least one of the plurality of illuminations.
   The image processing apparatus according to claim 1.
5. The subject is a person's face,
   The recessed area is the wrinkled area of the face.
   The image processing apparatus according to any one of claims 1 to 4.
6. The feature image extraction unit adjusts the position and / or size of the face image included in the first image and the second image based on the characteristic portion of the face, and then determines the region of the recess. Extract,
   The image processing apparatus according to claim 5.
7. At least one of the plurality of lights is an external light provided for an external environment.
   The first lighting pattern is different from the second lighting pattern in the pattern of turning off the external lighting or the illuminance.
   The image processing apparatus according to claim 1.
8. The device is
   A first image is taken by illuminating the subject based on a first illumination pattern showing a pattern relating to light emission of a plurality of lights, and a second image is taken by illuminating the subject based on a second illumination pattern.
   The concave region of the subject is extracted from the first image and the second image, respectively, and the first feature image and the second feature image are generated.
   The first feature image and the second feature image are combined to generate a composite feature image.
   Image processing method.
9. A first image is taken by illuminating the subject based on a first illumination pattern showing a pattern relating to light emission of a plurality of lights, and a second image is taken by illuminating the subject based on a second illumination pattern.
   The concave region of the subject is extracted from the first image and the second image, respectively, and the first feature image and the second feature image are generated.
   The first feature image and the second feature image are combined to generate a composite feature image.
   Let the computer do that,
   Computer program.

Images