JP2021022263A - Image processing program, image processing device, image processing system, and image processing method - Google Patents

Abstract

To increase the speed of the processing of improving the visibility of an object in an image.SOLUTION: A computer reduces a first image to generate a reduced image, the contrast of the reduced image is emphasized or the color tone is corrected to generate a second image and identifies a first area in the second image where the object appears. Then, the computer extracts a second area corresponding to the first area from the first image, and emphasizes the contrast or corrects the color tone of the second area to generate the area image.SELECTED DRAWING: Figure 6

Description

The present invention relates to an image processing program, an image processing apparatus, an image processing system, and an image processing method.

With the recent increase in the global population, farmed fish are attracting attention as a sustainable food source. In the aquaculture industry, the use of ICT (Information and Communications Technology) is spreading, and attempts are being made to observe the sea with a camera.

The images taken by the camera are used for observing the inside of the aquaculture cage, real-time comparative observation of fish bodies, fish length measurement by software, fish number measurement by software, parasite observation, etc.

Regarding image processing, an image processing apparatus is known that cuts out a part of an input image to obtain a desired cut-out image (see, for example, Patent Document 1). Retinex treatments that model the role of the retina and cortex in the living body are also known (see, for example, Patent Document 2 and Non-Patent Document 1). Image conversion using a hostile generation network is also known (see, for example, Non-Patent Document 2).

Japanese Unexamined Patent Publication No. 2010-81181 Japanese Unexamined Patent Publication No. 2005-4506

Zia-ur Rahman et al., “A Multiscale Retinex for Color Rendition and Dynamic Range Compression”, PROCEEDINGS VOLUME 2847, Applications of Digital Image Processing XIX, SPIE'S 1996 INTERNATIONAL SYMPOSIUM ON OPTICAL SCIENCE, ENGINEERING, AND INSTRUMENTATION, August 1996 Isola et al., “Image-to-Image Translation with Conditional Adversarial Networks”, Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1125-1134, 2017

The process of improving the visibility of the unclear fish in the image taken underwater takes time due to the large amount of processing.

It should be noted that such a problem occurs not only when observing a fish body using an underwater image but also when observing various objects using an image in a three-dimensional space.

In one aspect, it is an object of the present invention to speed up the process of improving the visibility of an object in an image.

In one proposal, the image processing program causes the computer to perform the following processing.
(1) The computer reduces the first image to generate a reduced image.
(2) The computer generates the second image by enhancing the contrast of the reduced image or correcting the color tone.
(3) The computer identifies the first region in which the object appears in the second image.
(4) The computer extracts a second region corresponding to the first region from the first image.
(5) The computer generates a region image by emphasizing the contrast of the second region or correcting the color tone.

According to one aspect, it is possible to speed up the process of improving the visibility of the object in the image.

It is a figure which shows the Retinex processing. It is a functional block diagram of an image processing apparatus. It is a flowchart of image processing. It is a functional block diagram which shows the specific example of an image processing apparatus. It is a figure which shows the image processing in the comparative example. It is a figure which shows the 1st image processing. It is a figure which shows the 2nd image processing. It is a flowchart which shows the specific example of image processing. It is a functional block diagram of an image processing system. It is a hardware block diagram of an information processing apparatus.

Hereinafter, embodiments will be described in detail with reference to the drawings.
The Retinex process disclosed in Patent Document 2 and Non-Patent Document 1 is an image correction process that reflects human visual characteristics. According to the Retinex process, the visibility can be improved by adjusting the dynamic range of the image to enhance the contrast or correcting the color tone.

Images taken underwater include time-series images, and the images at each time are sometimes called frames. When a high-resolution image is used as a frame included in the video, the number of pixels per frame increases. Therefore, when the Retinex processing is applied to each frame, the processing time becomes long and it becomes difficult to maintain the frame rate.

Also, if the fish to be observed is located far from the camera, or if the fish shadow is small and has low contrast, applying Retinex processing to the entire image improved the fish shadow to the extent that it can be recognized. However, the effect of improving visibility is low.

FIG. 1 shows an example of retinex processing on an image taken underwater. The image 101 taken by the camera shows various fish bodies. The fish body is an example of an object shown in the image.

By applying the Retinex process to the entire image 101, the image 102 with improved visibility can be obtained. As a result, it can be confirmed that the fish shadow is reflected in the area 111 of the image 102, but the effect of improving the visibility is limited.

FIG. 2 shows an example of a functional configuration of the image processing apparatus of the embodiment. The image processing device 201 of FIG. 2 includes a storage unit 211, a specific unit 212, and a generation unit 213. The storage unit 211 stores the first image. The specific unit 212 and the generation unit 213 perform image processing on the first image.

FIG. 3 is a flowchart showing an example of image processing performed by the image processing device 201 of FIG. First, the specific unit 212 reduces the first image to generate a reduced image (step 301), emphasizes the contrast of the reduced image or corrects the color tone to generate a second image (step 302), and generates the second image. The first region in which the object is captured is specified (step 303). Next, the generation unit 213 extracts the second region corresponding to the first region from the first image (step 304), emphasizes the contrast of the second region or corrects the color tone to generate the region image (step 305). ).

According to the image processing device 201 of FIG. 2, it is possible to speed up the process of improving the visibility of the object in the image.

FIG. 4 shows a specific example of the image processing device 201 of FIG. The image processing device 401 of FIG. 4 includes a storage unit 411, an image acquisition unit 412, a reduction unit 413, an image enhancement unit 414, an area identification unit 415, an area extraction unit 416, an area enhancement unit 417, a correction unit 418, and an enlargement unit 419. It includes a synthesis unit 420 and an output unit 421.

The storage unit 411 corresponds to the storage unit 211 of FIG. 2, the reduction unit 413, the image enhancement unit 414, and the area identification unit 415 correspond to the specific unit 212, and the area extraction unit 416 and the area enhancement unit 417 correspond to the generation unit 213. Corresponds to.

For example, the image processing device 401 is an information processing device (computer), and is used in the work of observing various objects using images in a three-dimensional space. For example, if the image to be processed is an image taken in the sea, the image can be used to observe the inside of the aquaculture cage, real-time comparative observation of fish bodies, fish length measurement by software, and fish number measurement by software. Parasite observations are carried out.

The image to be processed may be an image of the ground surface taken from an aircraft or an artificial satellite, an image of a surveillance camera installed in a factory, an office building, a street, or the like, and may be an image of a moving object such as a vehicle. It may be an image of the mounted camera. The object shown in the image may be a building, a vehicle, a human being, an animal, or the like.

The image pickup device 402 is a camera having an image pickup element such as a CCD (Charged-Coupled Device) or a CMOS (Complementary Metal-Oxide-Semiconductor), and captures an image to be processed. The captured image includes images at each of a plurality of times. When the image to be processed is an image taken in the sea, the image pickup apparatus 402 may be installed in the sea.

The image acquisition unit 412 acquires an image 431 at each time included in the image from the image pickup apparatus 402 and stores it in the storage unit 411. Image 431 is an example of the first image. The image 431 may be a high resolution image.

The reduction unit 413 reduces the image 431 to generate a reduced image 432 and stores it in the storage unit 411. For example, the reduction unit 413 reduces the image 431 by using the pixel interpolation method. As the pixel interpolation method, the nearest neighbor method, the bilinear method, the bicubic method and the like can be used. High-speed image size conversion is realized by using the nearest neighbor method.

The image enhancement unit 414 generates an enhanced image 433 by enhancing the contrast of the reduced image 432 or correcting the color tone, and stores it in the storage unit 411. The emphasized image 433 is an example of the second image.

For example, the image enhancement unit 414 enhances the contrast of the reduced image 432 or corrects the color tone by using a retinex process such as a single scale retinex or a multi-scale retinex. As a result, the reduced image 432 that reflects the characteristics of the image pickup apparatus 402 is converted into an emphasized image 433 that is close to the image visually recognized by humans, and the visibility is improved.

The image enhancement unit 414 may enhance the contrast or correct the color tone of the reduced image 432 by using an image correction process such as a histogram flattening method or an image quality conversion using deep learning. For example, the image enhancement unit 414 can perform image quality conversion using deep learning by using the technique of Non-Patent Document 2.

The area specifying unit 415 identifies the object area in which the object is shown in the emphasized image 433, and the area extracting unit 416 extracts the target area corresponding to the object area from the image 431. The object region is an example of the first region, and the target region is an example of the second region. The area enhancement unit 417 generates an area image 434 by enhancing the contrast of the target area or correcting the color tone, and stores it in the storage unit 411. For example, the area enhancement unit 417 enhances the contrast or corrects the color tone of the image in the target area by using the Retinex process, the histogram flattening method, the image quality conversion using deep learning, and the like.

The correction unit 418 performs color correction that brings the color information of the area image 434 closer to the color information of the object area, generates the correction image 435, and stores it in the storage unit 411. The enlargement unit 419 enlarges the emphasized image 433 to generate an enlarged image 436 and stores it in the storage unit 411. For example, the enlargement unit 419 enlarges the emphasized image 433 by using the pixel interpolation method. The size of the enlarged image 436 may be the same as the size of the image 431.

The compositing unit 420 combines the enlarged image 436 and the corrected image 435 to generate a composite image 437 and stores it in the storage unit 411. The compositing unit 420 specifies a partial region corresponding to the target region in the image 431 in the enlarged image 436, and replaces the image of the specified partial region with the corrected image 435 to generate the composite image 437.

The output unit 421 outputs a composite image 437. For example, when the output unit 421 is a display device, the output unit 421 displays the composite image 437 on the screen. By generating the composite image 437 from the image 431 at each time included in the video, the composite video including the time-series composite image 437 is displayed.

FIG. 5 shows an example of image processing in the comparative example. In this example, the image 502 is generated by applying the Retinex process to the image 501 included in the image taken in the sea. The fish body, which is difficult to see in the image 501, is barely visible in the image 502, as shown by the dotted line.

Therefore, the image 503 is generated by extracting the region including the fish body indicated by the dotted line of the image 502 from the image 501 and applying the Retinex treatment. Then, by synthesizing the image 502 and the image 503, the composite image 504 is generated. As a result, the visibility of the fish body indicated by the dotted line in the image 502 is improved as compared with the image 502.

However, since the color distribution is different between the entire image 501 and the image of a part of the image 501, the colors of the fish in the region do not match in the result of the Retinex processing for each image. Therefore, if the image 502 and the image 503 are combined as they are, the combined image 504 will have a sense of discomfort due to color loss. Further, in the image processing of FIG. 5, since the Retinex processing is applied to the entire image 501, the processing time becomes long, and the high-speed visibility improvement processing that maintains the frame rate cannot be realized.

FIG. 6 shows an example of the first image processing performed by the image processing device 401. The reduction unit 413 reduces the image 601 included in the image captured in the sea to generate the reduced image 602, and the image enhancement unit 414 applies the Retinex process to the reduced image 602 to obtain the enhanced image 603. Generate.

By generating the emphasized image 603 with improved visibility of the reduced image 602, it becomes easy to recognize the fish body shown in the image. Further, since the number of pixels of the reduced image 602 is smaller than the number of pixels of the image 601, the processing amount of the retinex processing is reduced and the processing speed is increased. However, even if the fish body that appears small in the object area 611 can be recognized, the contrast remains low, and the effect of improving the visibility is low.

Therefore, the area identification unit 415 identifies the object area 611 by performing template matching and edge detection processing on the emphasized image 603, and the area extraction unit 416 from the image 601 to the target area 621 corresponding to the object area 611. Image 622 is extracted.

The area enhancement unit 417 generates a region image (not shown) by applying the Retinex process to the image 622 of the target region 621. By applying the Retinex process only to the target region 621, a region image having a higher contrast than the object region 611 can be obtained. Since the number of pixels of the image 622 is smaller than the number of pixels of the image 601, the processing amount of the Retinex processing is reduced and the processing speed is increased. Further, since the image 622 is a part of the original image 601 and has a larger number of pixels than the object area 611, the original resolution is maintained.

In this way, by applying the Retinex process to the reduced image 602 obtained by reducing the original image 601 and the image 622 in a part of the original image 601 to improve the visibility of the image 601. It can be speeded up.

The correction unit 418 acquires the color information of the object region 611 and performs color correction to bring the color information of the region image closer to the color information of the object region 611 to generate the corrected image 623. As a result, the balanced color information obtained by the retinex processing of the entire reduced image 602 is reflected in the corrected image 623, and the visibility improvement processing with color compensation is realized. Therefore, the discomfort as in the composite image 504 shown in FIG. 5 does not occur, and the visibility of the fish body shown in the image 622 is further improved.

The enlargement unit 419 enlarges the emphasized image 603 to generate an enlarged image. The compositing unit 420 identifies the subregion 631 corresponding to the target region 621 in the enlarged image and replaces the image of the subregion 631 with the corrected image 623 to generate the compositing image 604.

As a result, in the weighted image 603, the region 612 and the region 613 including the large fish body are simply enlarged, and the region 611 including the small fish body is replaced with the corrected image 623. By replacing a part of the enlarged image with the corrected image 623, a high-speed visibility improvement process that maintains the frame rate can be realized, and the visibility of the entire image 601 can be improved.

By using the composite image 604 instead of the image 601, it becomes easy to observe the state inside the aquaculture cage in real time, visually compare the fish bodies, and measure the fish body length by software.

FIG. 7 shows an example of the second image processing performed by the image processing device 401. The reduction unit 413 reduces the image 701 included in the video to generate the reduced image 702, and the image enhancement unit 414 generates the enhanced image 703 by applying the Retinex process to the reduced image 702.

The region specifying unit 415 performs template matching using a template image showing an object shown in the image 701 in the emphasized image 703, and identifies a region having a degree of coincidence equal to or higher than a threshold value. In addition, the area specifying unit 415 performs edge detection processing on the emphasized image 703 to detect an edge from the emphasized image 703. Then, the area specifying unit 415 specifies a region having an edge strength smaller than a predetermined value as an object region 711 among the regions specified by template matching.

The threshold for the degree of matching of template matching may be a real number in the range of 0.7 to 0.9. The ratio R of the area of the template image to the area of the emphasized image 703 is a real number in the range of 0 <R <1. In order to realize high-speed processing while maintaining the frame rate, it is preferable that R ≦ 1/4.

The area extraction unit 416 extracts an image of the target area 712 corresponding to the object area 711 from the image 701, and the area enhancement unit 417 and the correction unit 418 perform color-compensated visibility improvement processing 731 for the image of the target area 712. Do. In the color-compensated visibility improvement process 731, the area enhancement unit 417 generates an area image by applying the Retinex process to the image of the target area 712.

The correction unit 418 performs HSV decomposition 732 for the color information C1 of each pixel of the region image to obtain the color information C1 into hue H (Hue), saturation S (Saturation), and lightness V (Value) in the HSV color space. Convert to. Further, the correction unit 418 acquires the color information C0 of the object region 711 and performs HSV decomposition 733 on the color information C0 to convert the color information C0 into hue H, saturation S, and brightness V in the HSV color space. To do. The color information C1 and the color information C0 may be the values of R, G, and B in the RGB color space.

Next, the correction unit 418 performs color correction 734 for the hue H, saturation S, and lightness V of the color information C1, and performs synthesis 735 of the corrected hue H, saturation S, and lightness V. The color information C2 of each pixel of the corrected image is generated. For example, the correction unit 418 obtains the hue H of the color information C2 by performing an operation to bring the hue H of the color information C1 closer to the hue H of the color information C0, and obtains the hue S and the brightness V of the color information C1, respectively. , Used as the saturation S and the lightness V of the color information C2. The correction unit 418 may use the hue H of the color information C0 as the hue H of the color information C2.

The enlargement unit 419 enlarges the emphasized image 703 to generate the magnified image 704. The compositing unit 420 generates the compositing image 705 by replacing the image of the partial region 713 corresponding to the target region 712 in the enlarged image 704 with the corrected image.

By bringing the hue H of the color information C1 closer to the hue H of the color information C0, the hue (red, orange, yellow, green, blue, purple, etc.) of the object region 711 is reflected in the corrected image, and the color in the composite image 705 is reflected. Collapse is reduced.

FIG. 8 is a flowchart showing a specific example of image processing performed by the image processing apparatus 401 of FIG. First, the image acquisition unit 412 determines whether or not to end the image processing (step 801). For example, the image acquisition unit 412 determines that the image processing is finished when the end instruction is received from the user, and determines that the image processing is not finished when the end instruction is not received.

When it is determined that the image processing is not completed (steps 801 and NO), the image acquisition unit 412 acquires the image 431 included in the image from the image pickup apparatus 402 (step 802), and the reduction unit 413 obtains the image 431. It is reduced to generate a reduced image 432 (step 803).

Next, the image enhancement unit 414 enhances the contrast of the reduced image 432 or corrects the color tone to generate the enhanced image 433 (step 804). Then, the area specifying unit 415 performs template matching and edge detection processing on the emphasized image 433 in order to detect an object from the emphasized image 433 (step 805).

Next, the area identification unit 415 checks whether or not an object is detected by template matching (step 806), and if an object is detected (step 806, YES), sets the edge strength of the detected object to a predetermined value. Compare with (step 809). When the edge strength is smaller than the predetermined value (step 809, YES), the area specifying unit 415 specifies the area in which the object is reflected as the object area (step 810).

By identifying the area in the emphasized image 433 where the object is shown and the edge strength is smaller than the predetermined value, the visibility improvement process with color compensation is performed only for the area where the unclear object is shown. It will be possible to do. As a result, the visibility improvement process with color compensation for the area where a clear object is captured is omitted, so that the amount of processing is reduced.

Next, the correction unit 418 acquires the color information of the object region (step 811), and the region extraction unit 416 extracts the target region corresponding to the object region from the image 431 (step 812). Then, the area enhancement unit 417 enhances the contrast of the target area or corrects the color tone to generate the area image 434, and the correction unit 418 performs color correction to bring the color information of the area image 434 closer to the color information of the object area. To generate a corrected image 435 (step 813).

Next, the enlargement unit 419 enlarges the emphasized image 433 to generate an enlarged image 436 (step 807). Next, the compositing unit 420 combines the enlarged image 436 and the corrected image 435 to generate the composite image 437, and the output unit 421 outputs the composite image 437 (step 808). Then, the image processing device 401 repeats the processing after step 801 for the image 431 at the next time.

When the object is not detected (step 806, NO), or when the edge strength is equal to or higher than a predetermined value (step 809, NO), the image processing apparatus 401 performs the processes after step 807. In this case, the corrected image 435 is not generated, and the enlarged image 436 is output as it is as the composite image 437.

When it is determined that the image processing is finished (steps 801 and YES), the image processing apparatus 401 ends the image processing.

When the color information of the area image 434 and the color information of the object area are close to each other, it is not always necessary to perform the color correction of the area image 434. When the color correction is not performed, the image processing device 401 omits the process of step 811 and does not generate the corrected image 435 in step 813. Then, in step 808, the compositing unit 420 synthesizes the enlarged image 436 and the region image 434 to generate the composite image 437.

FIG. 9 shows a functional configuration example of an image processing system that performs image processing similar to that of the image processing device 401 of FIG. The image processing system of FIG. 9 includes an image pickup device 402, a storage unit 411, an image acquisition unit 412, a reduction unit 413, an image enhancement unit 414, an area identification unit 415, an area extraction unit 416, an area enhancement unit 417, a correction unit 418, and an enlargement. A unit 419, a synthesis unit 420, and an output unit 421 are included.

The plurality of components shown in FIG. 9 are distributed and implemented in a plurality of information processing devices. Each of these components may be included in different information processing devices, and any two or more components may be included in one information processing device. The operation performed by each component is the same as in the case of the image processing device 401.

The configurations of the image processing devices of FIGS. 2 and 4 are merely examples, and some components may be omitted or changed depending on the use or conditions of the image processing device. For example, in the image processing device 401 of FIG. 4, when the image 431 is stored in the storage unit 411 in advance, the image acquisition unit 412 can be omitted. When the color correction of the area image 434 is not performed, the correction unit 418 can be omitted.

The configuration of the image processing system of FIG. 9 is only an example, and some components may be omitted or changed depending on the use or conditions of the image processing system.

The flowcharts of FIGS. 3 and 8 are merely examples, and some processes may be omitted or changed depending on the configuration or conditions of the image processing device. For example, in the image processing of FIG. 8, when the image 431 is stored in the storage unit 411 in advance, the processing of step 802 can be omitted. In step 805, the area identification unit 415 may omit the edge detection process for the emphasized image 703. In this case, the process of step 809 is also omitted.

The images of FIGS. 1 and 5 to 7 are merely examples, and the image to be processed changes according to the object to be photographed. The visibility improving process 731 with color compensation shown in FIG. 7 is only an example, and another correction process may be used depending on the configuration or conditions of the image processing device 401. For example, the correction unit 418 can change not only the hue H of the color information C1 but also the saturation S and the lightness V. The correction unit 418 may perform color correction of the region image by calculation in a color space other than the HSV color space.

FIG. 10 shows a hardware configuration example of an information processing device used as the image processing device of FIGS. 2 and 4. The information processing device of FIG. 10 includes a CPU (Central Processing Unit) 1001, a memory 1002, an input device 1003, an output device 1004, an auxiliary storage device 1005, a medium drive device 1006, and a network connection device 1007. These components are hardware and are connected to each other by bus 1008.

The memory 1002 is, for example, a semiconductor memory such as a ROM (Read Only Memory), a RAM (Random Access Memory), or a flash memory, and stores a program and data used for processing. The memory 1002 can be used as the storage unit 211 of FIG. 2 or the storage unit 411 of FIG.

The CPU 1001 (processor) operates as the specific unit 212 and the generation unit 213 of FIG. 2 by executing a program using, for example, the memory 1002.

The CPU 1001 can also be used as the image acquisition unit 412, the reduction unit 413, the image enhancement unit 414, the area identification unit 415, the area extraction unit 416, and the area enhancement unit 417 in FIG. 4 by executing the program using the memory 1002. Operate. The CPU 1001 also operates as a correction unit 418, an enlargement unit 419, and a synthesis unit 420 by executing a program using the memory 1002.

The input device 1003 is, for example, a keyboard, a pointing device, or the like, and is used for inputting an instruction or information from an operator or a user. The output device 1004 is, for example, a display device, a printer, a speaker, or the like, and is used for inquiring or instructing an operator or a user and outputting a processing result. The processing result may be a composite image 437. The output device 1004 can be used as the output unit 421 of FIG.

The auxiliary storage device 1005 is, for example, a magnetic disk device, an optical disk device, a magneto-optical disk device, a tape device, or the like. The auxiliary storage device 1005 may be a hard disk drive or a flash memory. The information processing device can store programs and data in the auxiliary storage device 1005 and load them into the memory 1002 for use. The auxiliary storage device 1005 can be used as the storage unit 211 of FIG. 2 or the storage unit 411 of FIG.

The medium driving device 1006 drives the portable recording medium 1009 and accesses the recorded contents. The portable recording medium 1009 is a memory device, a flexible disk, an optical disk, a magneto-optical disk, or the like. The portable recording medium 1009 may be a CD-ROM (Compact Disk Read Only Memory), a DVD (Digital Versatile Disk), a USB (Universal Serial Bus) memory, or the like. The operator or the user can store the programs and data in the portable recording medium 1009 and load them into the memory 1002 for use.

As described above, the computer-readable recording medium that stores the programs and data used for image processing is a physical (non-temporary) recording medium such as a memory 1002, an auxiliary storage device 1005, or a portable recording medium 1009. It is a recording medium.

The network connection device 1007 is a communication interface circuit that is connected to a communication network such as a LAN (Local Area Network) or WAN (Wide Area Network) and performs data conversion associated with the communication. The information processing device can receive programs and data from an external device via the network connection device 1007, load them into the memory 1002, and use them. The network connection device 1007 can be used as the output unit 421 of FIG.

It is not necessary for the information processing apparatus to include all the components of FIG. 10, and some components may be omitted depending on the application or conditions. For example, the input device 1003 may be omitted when it is not necessary to input instructions or information from the operator or the user. When the portable recording medium 1009 or the communication network is not used, the medium driving device 1006 or the network connecting device 1007 may be omitted.

Having described in detail the embodiments of the disclosure and its advantages, those skilled in the art will be able to make various changes, additions and omissions without departing from the scope of the invention as expressly stated in the claims. Let's do it.

The following additional notes will be further disclosed with respect to the embodiments described with reference to FIGS. 1 to 10.
(Appendix 1)
Reduce the first image to generate a reduced image,
The contrast of the reduced image is emphasized or the color tone is corrected to generate a second image.
In the second image, the first region in which the object appears is specified, and
A second region corresponding to the first region is extracted from the first image, and the second region is extracted.
A region image is generated by emphasizing the contrast of the second region or correcting the color tone.
An image processing program that allows a computer to perform processing.
(Appendix 2)
Color correction is performed to bring the color information of the region image closer to the color information of the first region, and a corrected image is generated.
The second image is enlarged to generate an enlarged image,
The enlarged image and the corrected image are combined to generate a composite image.
Output the composite image,
The image processing program according to Appendix 1, wherein the computer further executes the processing.
(Appendix 3)
The image processing program according to Appendix 2, wherein the color correction is a process of bringing the hue of the region image closer to the hue of the first region.
(Appendix 4)
The image processing program causes the computer to further execute a process of detecting an edge from the second image.
The image processing program according to any one of Supplementary note 1 to 3, wherein the first region is a region in which the edge strength is smaller than a predetermined value in the second image.
(Appendix 5)
The image processing program according to any one of Supplementary note 1 to 4, wherein the computer enhances the contrast of the reduced image and the second region or corrects the color tone by retinex processing.
(Appendix 6)
A storage unit that stores the first image and
The first image is reduced to generate a reduced image, the contrast of the reduced image is emphasized or the color tone is corrected to generate a second image, and a first region in which an object is captured is specified in the second image. With a specific part to do
A generation unit that extracts a second region corresponding to the first region from the first image, emphasizes the contrast of the second region, or corrects the color tone to generate a region image.
An image processing device characterized by comprising.
(Appendix 7)
A correction unit that generates a corrected image by performing color correction that brings the color information of the region image closer to the color information of the first region.
An enlargement unit that enlarges the second image to generate an enlarged image, and
A compositing unit that synthesizes the enlarged image and the corrected image to generate a composite image,
An output unit that outputs the composite image and
The image processing apparatus according to Appendix 6, further comprising.
(Appendix 8)
The image processing apparatus according to Appendix 7, wherein the color correction is a process of bringing the hue of the region image closer to the hue of the first region.
(Appendix 9)
The specific part detects an edge from the second image and
The image processing apparatus according to any one of Supplementary note 6 to 8, wherein the first region is a region in which the edge strength is smaller than a predetermined value in the second image.
(Appendix 10)
The specific unit is characterized in that the contrast of the reduced image is emphasized or the color tone is corrected by the Retinex process, and the generation unit is characterized in that the contrast of the second region is emphasized or the color tone is corrected by the Retinex process. The image processing apparatus according to any one of Supplementary note 6 to 9.
(Appendix 11)
A storage unit that stores the first image and
The first image is reduced to generate a reduced image, the contrast of the reduced image is emphasized or the color tone is corrected to generate a second image, and a first region in which an object is captured is specified in the second image. With a specific part to do
A generation unit that extracts a second region corresponding to the first region from the first image, emphasizes the contrast of the second region, or corrects the color tone to generate a region image.
An image processing system characterized by being equipped with.
(Appendix 12)
A correction unit that generates a corrected image by performing color correction that brings the color information of the region image closer to the color information of the first region.
An enlargement unit that enlarges the second image to generate an enlarged image, and
A compositing unit that synthesizes the enlarged image and the corrected image to generate a composite image,
An output unit that outputs the composite image and
The image processing system according to Appendix 11, further comprising.
(Appendix 13)
An image processing method performed by a computer
The computer
Reduce the first image to generate a reduced image,
The contrast of the reduced image is emphasized or the color tone is corrected to generate a second image.
In the second image, the first region in which the object appears is specified, and
A second region corresponding to the first region is extracted from the first image, and the second region is extracted.
A region image is generated by emphasizing the contrast of the second region or correcting the color tone.
An image processing method characterized by that.
(Appendix 14)
The computer
Color correction is performed to bring the color information of the region image closer to the color information of the first region, and a corrected image is generated.
The second image is enlarged to generate an enlarged image,
The enlarged image and the corrected image are combined to generate a composite image.
Output the composite image,
The image processing method according to Appendix 13, characterized in that.

101, 102, 431, 501-503, 601, 622, 701 Image 111, 612, 613 Area 201, 401 Image processing device 211, 411 Storage unit 212 Specific unit 213 Generation unit 402 Imaging device 412 Image acquisition unit 413 Reduction unit 414 Image enhancement part 415 Area identification part 416 Area extraction part 417 Area enhancement part 418 Correction part 419 Enlargement part 420 Synthesis part 421 Output part 432, 602, 702 Reduced image 433, 603, 703 Emphasis image 434 Area image 435, 623 Corrected image 436 , 704 Enlarged image 437, 504, 604, 705 Composite image 611, 711 Object area 621, 712 Target area 631, 713 Partial area 731 Visibility improvement processing with color compensation 732, 733 HSV decomposition 734 Color correction 735 Composite 1001 CPU
1002 Memory 1003 Input device 1004 Output device 1005 Auxiliary storage device 1006 Media drive device 1007 Network connection device 1008 Bus 1009 Portable recording medium

Claims (7)

Reduce the first image to generate a reduced image,
The contrast of the reduced image is emphasized or the color tone is corrected to generate a second image.
In the second image, the first region in which the object appears is specified, and
A second region corresponding to the first region is extracted from the first image, and the second region is extracted.
A region image is generated by emphasizing the contrast of the second region or correcting the color tone.
An image processing program that allows a computer to perform processing. Color correction is performed to bring the color information of the region image closer to the color information of the first region, and a corrected image is generated.
The second image is enlarged to generate an enlarged image,
The enlarged image and the corrected image are combined to generate a composite image.
Output the composite image,
The image processing program according to claim 1, wherein the computer further executes the processing. The image processing program according to claim 2, wherein the color correction is a process of bringing the hue of the region image closer to the hue of the first region. The image processing program causes the computer to further execute a process of detecting an edge from the second image.
The image processing program according to any one of claims 1 to 3, wherein the first region is a region in which the edge strength is smaller than a predetermined value in the second image. A storage unit that stores the first image and
The first image is reduced to generate a reduced image, the contrast of the reduced image is emphasized or the color tone is corrected to generate a second image, and a first region in which an object is captured is specified in the second image. With a specific part to do
A generation unit that extracts a second region corresponding to the first region from the first image, emphasizes the contrast of the second region, or corrects the color tone to generate a region image.
An image processing device characterized by comprising. A storage unit that stores the first image and
The first image is reduced to generate a reduced image, the contrast of the reduced image is emphasized or the color tone is corrected to generate a second image, and a first region in which an object is captured is specified in the second image. With a specific part to do
A generation unit that extracts a second region corresponding to the first region from the first image, emphasizes the contrast of the second region, or corrects the color tone to generate a region image.
An image processing system characterized by being equipped with. An image processing method performed by a computer
The computer
Reduce the first image to generate a reduced image,
The contrast of the reduced image is emphasized or the color tone is corrected to generate a second image.
In the second image, the first region in which the object appears is specified, and
A second region corresponding to the first region is extracted from the first image, and the second region is extracted.
A region image is generated by emphasizing the contrast of the second region or correcting the color tone.
An image processing method characterized by that.

Images