JP2006301675A - Image processor and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor, capable of performing adequate image processing by properly discriminating similar scenes, even when the compositions of the scenes change. <P>SOLUTION: This image processor comprises a similar scene discrimining part 48 for discriminating the similarity among a plurality of input images; and an image processing part 47 for performing predetermined processing to an image discriminated as being a similar scene. The similar scene discrimining part 48 includes a block division part 49 dividing each of two images to be compared to a plurality of blocks of a predetermined size and determining the image characteristic values of each block; an evaluation image generation part 50 mutually relating blocks with high matching degree of the image characteristic values of both the images, and generating an evaluation image, in which the block of one image is moved to and arranged in the position of the block associated therewith of the other image; and an evaluation part 51 for discriminating, whether the two images to be compared are similar scenes, based on the generated evaluation image and the other image. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to an image processing apparatus including a similar scene determination unit that determines similarity between a plurality of input images, and an image processing unit that performs predetermined processing on an image determined to be a similar scene. .

  When creating a photographic print from an image recorded on a developed photographic film using a photographic processing apparatus or an image shot with a digital still camera (hereinafter abbreviated as “DSC”), Various corrections such as backlight scenes, under-exposure scenes, over-exposure scenes, sharpness, and insufficient amount of ambient light are provided by the image processing device built into the photographic processing device in order to improve the deterioration of the quality of the printed image due to shooting conditions. Is performed, and a high-quality and beautiful photo print is output.

  If such image processing is performed in units of frame images, there is a possibility that the finish of the photo prints of similar scenes may vary, so a similar scene determination unit that determines whether the shooting scenes of the respective frame images are similar in advance. In addition, by providing an image processing unit that restricts or corrects the setting of various processing parameters by the image processing apparatus for the frame image determined to be a similar scene, processing is performed so that the photo print finish of the similar scene is uniform. It had been.

As a similar scene discrimination algorithm by the above-mentioned similar scene discrimination unit, approximation is performed between images in which image characteristic values such as an average value, maximum value, and minimum value of color density values obtained from an image are compared. If it is determined as a similar scene, if it is determined as a similar scene based on the histogram of the contrasted image, the shooting time recorded in the magnetic recording area in the case of an APS compatible film, and stored in the DSC ancillary information area of the DSC, for example For example, there has been proposed a method in which a continuous scene whose shooting interval is within a predetermined time is used as a target and an image whose characteristic value such as a histogram is approximated is determined to be a similar scene.
JP 54-26729 A JP-A-56-153334 Japanese Patent Laid-Open No. 2001-24887

  However, in the above-described similar scene discriminating unit, the image characteristic value that is discriminated based on the degree of coincidence of the histogram may be erroneously discriminated as a similar scene when the histogram is approximated even if the scene is completely different. Similar scenes that cannot deal with changes in the composition of the scene due to movement of the subject from the center of the image to the periphery of the image, etc., with those that are determined by the degree of coincidence of the average value, maximum value, minimum value, etc. However, there was a problem that it could not be distinguished from similar scenes.

  In view of the above-described conventional problems, the present invention provides an image processing apparatus and an image processing method capable of appropriately determining similar scenes and performing appropriate image processing even when the composition of the scene changes. The point is to provide.

  In order to achieve the above object, a first characteristic configuration of an image processing apparatus according to the present invention is a similar scene for determining similarity between a plurality of input images as described in claim 1 of the document of the claims. An image processing apparatus configured to include a determination unit and an image processing unit that performs predetermined processing on an image determined to be a similar scene, wherein the similar scene determination unit determines each of the two images to be compared A block dividing unit that obtains an image characteristic value of each block by dividing an area into a plurality of blocks of a size, a block having a high degree of coincidence of the image characteristic values between both images, and a block of one image are associated An evaluation image generation unit that generates an evaluation image moved and arranged at the position of the block of the other image, and whether or not the two images to be compared based on the generated evaluation image and the other image are similar scenes In point configured with a that evaluation unit.

  Similar scenes generally refer to scenes with similar shooting conditions such as the composition and lighting of the main subject, but there is a common subject in the image whether it is a person or an object, and there is also a common part in the background. Even if the composition of the subject changes, it is necessary to discriminate it from a similar scene from the viewpoint of aligning the quality of photographic prints for both images. According to the above configuration, the two images to be compared are divided into blocks by the block dividing unit, and the image characteristic value of each block is obtained. By this, the main subject and the background constituting the image correspond to the block size. An image characteristic value of the unit constituent element is obtained by being divided into constituent elements. The evaluation image generation unit compares the image characteristic values obtained for each block between the two images, determines that the blocks with a high degree of coincidence are common unit components, and associates them with each other. An evaluation image in which the composition of the unit constituent elements of one image is changed is generated by moving and arranging the block at the position of the other associated image. The evaluation unit can appropriately determine whether the scene is a similar scene even when the composition changes by comparing the evaluation image with the other image and evaluating the similarity. As a result, even if the histograms of the contrasted images as a whole are approximated, the unit components cannot be associated with each other, so that erroneous determination that the scenes are similar does not occur.

  In the second feature configuration, as described in claim 2, in addition to the first feature configuration described above, the evaluation unit includes the other image at a position corresponding to each block of the evaluation image. The difference is that it is determined whether or not the two images to be compared are similar scenes based on the similarity evaluation value obtained by adding the difference of the image characteristic values to the block for all the blocks constituting the evaluation image.

  According to the above configuration, when the evaluation unit compares the evaluation image with the other image, the image characteristic value of each block constituting the evaluation image and the block of the other image at the position corresponding to the position of the block. It becomes possible to determine whether or not it is a similar scene based on the similarity evaluation value obtained by taking the difference from the characteristic value and adding them, and the upper limit of the similarity evaluation value that can be determined to be a similar scene Can be appropriately determined by previously determining by simulation or the like.

  In the third feature configuration, as described in claim 3, in addition to the first or second feature configuration described above, the evaluation unit performs a comparison based on a movement vector of each block constituting the evaluation image. The point is to determine whether or not the two images to be processed are similar scenes.

  The evaluation unit obtains a movement vector of each block constituting the evaluation image, that is, a movement direction and a movement amount from the position in one image of each block to the position in the evaluation image, and whether the scene is a similar scene based on the tendency. It is determined whether or not. For example, when one image is shot and then the shooting angle is changed in the up / down / left / right or diagonal directions, and the other image is shot, almost all blocks of the evaluation image generated by the evaluation image generation unit are the same movement vector. When only the main subject moves without changing the shooting angle when shooting the other image, the vector of the block corresponding to the background of the evaluation image indicates zero while the block corresponding to the main subject is the same. The movement vector is shown. In this way, in a similar scene, each block can be grouped into a group of blocks having the same or similar movement vectors, and therefore can be determined based on the tendency. And when it is not a similar scene, it can be clearly discriminated in that the correlation is not seen in each movement vector and it becomes disordered.

  In the fourth feature configuration, in addition to any one of the first to third feature configurations described above, the evaluation unit may further include an evaluation image generated by the evaluation image generation unit. When the number of blocks constituting the image becomes smaller than a predetermined number, it is determined that the scene is not a similar scene.

  As described above, the evaluation image generation unit compares the image characteristic values to determine that the blocks having a high degree of matching are common unit components and associates them with each other. Some blocks that can't be played also appear. Therefore, according to the above-described configuration, the number of blocks constituting the evaluation image is limited, and when the number of blocks constituting the evaluation image is less than a predetermined number, it is determined that the scene is not a similar scene, thereby avoiding erroneous determination. Will be able to.

  In the fifth feature configuration, as described in claim 5, in addition to any of the first to fourth feature configurations described above, an image correction unit that performs a predetermined image correction process on the input image is provided. And the image processing unit includes an image correction limiting unit that limits an image correction processing condition by the image correcting unit for an image determined to be a similar scene by the similar scene determining unit.

  As described above, in order to improve the deterioration of the quality of a print image generally caused by inappropriate shooting conditions at the time of shooting, the image processing apparatus includes a backlight scene, an underexposure scene, an overexposure scene, a sharpness, and a peripheral light amount. Various image correction units such as a shortage are provided. However, if correction is performed independently for each image, the quality of the finished photo print may be greatly different, but the user may feel uncomfortable. Therefore, by limiting the image correction processing conditions for the similar scene by the image correcting unit by the image correction limiting unit, the quality of the photo print for the similar scene can be adjusted to be constant.

  According to the first characteristic configuration of the image processing method of the present invention, as described in claim 6, a similar scene determination step for determining similarity between a plurality of input images, and an image determined as a similar scene An image processing method comprising an image processing step for performing predetermined processing, wherein the similar scene determination step divides each of the two images to be compared into a plurality of blocks of a predetermined size, and images of each block A block division step for obtaining a characteristic value, an evaluation image in which blocks having a high degree of coincidence between the image characteristic values are associated between both images, and the block of one image is moved to the position of the associated block of the other image An evaluation image generation step to generate, and an evaluation step to determine whether or not two images to be compared based on the generated evaluation image and the other image are similar scenes Provided there to point configured.

  As described above, according to the present invention, there are provided an image processing apparatus and an image processing method capable of appropriately discriminating similar scenes and performing appropriate image processing even when the composition of the scene changes. I was able to do it.

  Embodiments of a photographic processing apparatus incorporating an image processing apparatus according to the present invention will be described below. As shown in FIG. 1, a photographic image processing apparatus 1 includes a photographic printer 2 that performs exposure processing on photographic paper P based on output image data and develops the exposed photographic paper, and a developed photographic film F. A media driver 32 that reads image data from an image data storage medium M such as a memory card that stores image data taken by a film scanner 31 or a digital still camera that reads an image from the camera, a general-purpose computer as a controller 33, and the like The print data is set and inputted with the print order information for the inputted photographic image as the original image, and includes an operation station 3 for performing various image correction processes, and the print data edited from the original image by the operation station 3 Is output to the photographic printer 2 to produce a desired photographic print. That.

  As shown in FIGS. 1 and 2, the photographic printer 2 has two systems of photographic paper magazines 21 containing roll-shaped photographic paper P, and photographic paper P drawn from the photographic paper magazine 21 with a predetermined print. A sheet cutter 22 that cuts into a size; a back print unit 23 that prints print information such as a frame number on the back of the cut photographic paper P; an exposure unit 24 that exposes the photographic paper P based on the print data; A development processing unit 25 including a plurality of processing tanks 25a, 25b, and 25c filled with processing solutions for developing, bleaching, and fixing the exposed photographic paper P is disposed along the conveyance path of the photographic paper P. The laterally-feeding conveyor 26 that discharges the photographic paper P that has been dried after the development process, and the sheet-paper (photo print) P that is stacked on the laterally-feeding conveyor 26 is sorted in order units. Configured to include the data 27.

  The exposure unit 24 includes a laser beam bundle of RGB three colors modulated based on the print data in the main scanning direction orthogonal to the conveyance direction with respect to the photographic paper P conveyed in the sub-scanning direction by the conveyance mechanism 28. The exposure head 24a that outputs and exposes.

  A transport mechanism 28 including a plurality of roller pairs that transport the photographic printing paper P at a process speed corresponding to the exposure unit 24 and the development processing unit 25 disposed along the transport path is disposed before and after the exposure unit 24. Is provided with a chucker-type transport mechanism 28a capable of transporting photographic paper P in multiple rows.

  The controller 33 provided in the operation station 3 is installed with an application program that operates under the control of a general-purpose operating system and executes various controls of the photographic processing apparatus 1, and a monitor 34 as an operation interface with the operator. A keyboard 35, a mouse 36, and the like are connected.

  The photographic processing process executed by the cooperation of the hardware and software of the controller 33 will be described in functional blocks. As shown in FIG. 3, photographic image data read by the film scanner 31 and the media driver 32 is received, An image input unit 40 that performs predetermined preprocessing and transfers it to a memory 41, which will be described later, and print order information and image editing information are displayed on the screen of the monitor 34, and an operation for inputting necessary data for them. A graphic user interface unit 42 that generates a graphic operation screen for displaying an icon or generates various control commands based on an input operation from the keyboard 35 or mouse 36 to the displayed graphic operation screen, and the image input Photos transferred from the section 40 A memory 41 in which image data and photographic image data after correction processing by an image processing unit 47 (to be described later), correction parameters at that time, and set print order information are stored in a predetermined area, and print order information An order processing unit 43 for generating the image, an image processing unit 47 for performing various corrections such as gradation correction, color correction, enlargement / reduction processing, distortion correction on each photographic image data stored in the memory 41, and the graphic A display control unit 46 including a video RAM for displaying the image data and various input / output graphic data developed in the memory 41 based on a display command from the user interface unit 42 on the monitor 34; Print data for outputting the final corrected image for which the correction processing has been completed to the photographic printer 2 is generated. A print data generating unit 44, and the like formatter 45 which converts the final corrected image according to customer orders to a file format for writing in a storage medium such as a CD-R.

  The film scanner 31 is configured to operate in two modes: a pre-scan mode that reads an image recorded on the film F at a high speed although it is a low resolution, and a main scan mode that reads a high resolution at a low speed. Various correction processes are performed in the pre-judge mode (described in detail in the pre-judge process described later) on the low resolution image read in the can mode, and the correction parameters stored in the memory 41 at that time are changed. Based on this, the final correction processing for the high-resolution image read in the main scan mode is executed and output to the printer 2.

  Similarly, the image file read from the media driver 32 includes a high-resolution captured image and its thumbnail image, and various correction processes described later are performed on the thumbnail image. Based on the stored correction parameters, a final correction process is performed on the high-resolution captured image. When the image file does not include a thumbnail image, the image input unit 40 generates a thumbnail image from the high-resolution captured image and transfers it to the memory 41. In this way, the calculation load of the controller 33 is reduced by executing various editing processes that are frequently trial and error on low-resolution images.

  The image processing unit 47 corrects, for example, a tone correction unit 53 that corrects the gradation of the main subject due to excessive or insufficient exposure settings during shooting, a color correction unit 54 that adjusts color balance, and distortion caused by the shooting lens. A distortion correction unit (55) that enhances an edge of an image to reduce noise, an enlargement / reduction processing unit (not shown) that converts the image size to a photo print size, and the like. The provided image correction unit 52, a similar scene determination unit 48 for determining whether or not a series of photographic image data are similar to each other, and a photographic image determined as a similar scene by the similar scene determination unit 48 In contrast, an image correction limiting unit 56 for limiting the correction processing by the image correction unit 52 is provided.

  The similar scene determination unit 48 divides each of two contrasted photographic images into a plurality of blocks of a predetermined size to obtain an image characteristic value of each block, and the image characteristic value between the two images. The evaluation image generation unit 50 that generates an evaluation image in which blocks having a high degree of coincidence are associated with each other and the block of one image is moved to the position of the associated block of the other image; and the generated evaluation image and the other The evaluation unit 51 is configured to determine whether the two images to be compared based on the images are similar scenes.

  The evaluation unit 51 is based on a similarity evaluation value obtained by adding the differences of the image characteristic values between the blocks of the evaluation image and the blocks of the other image at the corresponding positions to all the blocks constituting the evaluation image. It is determined whether or not the two images to be compared are similar scenes.

  The image correction restricting unit 56 selects a similar scene among the correction parameters which are image correction conditions for the individual photographic images by the image correcting unit 52 so that the finish quality of the photographic prints for the photographic images obtained by photographing the similar scenes is uniform. Limits the correction parameters for the discriminated image. For example, an average value of each correction parameter for each image determined to be a similar scene is set as a new correction parameter, or each correction parameter for each image determined to be a similar scene is set to a specific image in them. For example, a correction parameter indicating a median value is replaced, or a correction parameter for another similar scene image is rounded to a predetermined range based on the correction parameter for a specific image indicating the median value.

  A procedure for determining a similar scene of a photographic image by the similar scene determining unit 48 will be described below. As shown in FIG. 5, when the image data read by the film scanner 31 in the pre-scan mode or the thumbnail image data read from the media driver 32 is stored in the memory 41, two images are selected in the order of reading. It is then determined whether or not it is a continuous shooting scene (S1, S2, S3). It is determined whether or not it is a continuous shooting scene. For 135 film images, adjacent image frames are determined to be continuous shooting images. For APS film images, shooting time data stored in the magnetic recording area of the film is read from the media driver 32. The thumbnail image data is determined based on whether or not the shooting time is within a predetermined time based on the shooting time data stored in the attribute area of the Exif file. Now, an image in which the two pieces of image data shown in FIGS. 4 (a) and 4 (b) are continuously captured (one image captured first (a), the other image captured later (b)) A case where it is determined whether or not the scene is a similar scene will be described.

The block dividing unit 49 divides each of the two images determined to be continuous shooting scenes by a predetermined number of pixels (S4), and calculates and derives an image characteristic value of each block (S5). For example, as shown in FIGS. 4C and 4D, each of the RGB color components obtained by reading 23.4 mm × 35.3 mm of a 135 film at 320 dpi is an image of about 300 × 440 pixels. The data is divided into 24 regions of about 75 × 73 pixels, and an average luminance value is calculated and derived as an image characteristic value for each region. Here, the number of divided areas is not particularly limited. However, if the subdivision is performed, not only the calculation load increases, but also there is a possibility that a certain tendency does not appear in the later-described movement vector, which may lead to misjudgment. However, in the above-described case, the range of 15 to 30 regions is a preferable value. In addition to the luminance average value, the image characteristic value of each block may be a combination of the maximum luminance and the minimum luminance as the image characteristic value, or the color component average value, that is, the average value of the R, G, and B components of the block. (R _AVR , G _AVR , B _AVR ) may be used.

  Next, the evaluation image generating unit 50 compares the image characteristic values of the blocks of the two images (S6), associates the blocks having the smallest difference as blocks having a high degree of coincidence, and blocks of one image A movement vector that is data defining the direction and distance to the movement destination of the block when moving to the position of the block of the other image associated with the image is calculated and derived (S7), and one image is based on the movement vector. An evaluation image in which the corresponding block is moved is generated (S8). For example, in the case of FIGS. 4C and 4D, the blocks a11, a12, a13, and a14 of one image are compared to the blocks a21, a22, a23, and a24 of the other image. 4 for each block) is associated as a block having a high degree of coincidence, and a movement vector for moving blocks a11, a12, a13, a14 of one image to blocks a21, a22, a23, a24 of the other image V11, V12, V13, and V14 are derived, and the evaluation image shown in FIG. 4E is obtained. Here, there is a block having a high degree of coincidence when the difference between the image characteristic values of each block in step S6 is greater than a predetermined threshold value (a value that is appropriately set by experiment etc.) in any combination. In other words, the block is excluded from the constituent blocks of the evaluation image.

  The evaluation unit 51 calculates a difference between the image characteristic values of each block of the evaluation image and the block of the other image at a position corresponding to each block (S9), and configures the evaluation image with the obtained difference. The similarity evaluation value added for all blocks to be obtained is obtained (S10). Then, it is determined that the two images are similar scenes when the similarity evaluation value is smaller than a predetermined evaluation threshold value (a value that is appropriately set by experiment or the like). (S11, S12, S13). That is, since the blocks constituting the evaluation image shown in FIG. 4E (blocks indicated by hatching in the drawing) are compared with the corresponding blocks of the other images shown in FIG. 4F, the similarity evaluation value is calculated. is there. Here, when the number of blocks constituting the evaluation image generated by the evaluation image generation unit 50 is smaller than a predetermined number, the accuracy of comparison between the evaluation image and the other image is lowered, so both images are image similar scenes. It is determined that it is not. The number of blocks at this time is not particularly limited, but is preferably set to a range of at least 1/2 to 2/3 of the total number of divided blocks. When such a similar scene determination process is completed for all images (S14), the process proceeds to a pre-judge process.

  In the pre-judge process, the gradation correction process by the gradation correction unit 54 in the automatic mode or the manual mode is performed on the thumbnail images displayed on a screen in a predetermined number of frames, for example, in units of six frames, and the color correction unit. 53, color correction processing by the distortion correction unit 55, distortion correction processing by the distortion correction unit 55, etc. are performed, and each correction parameter is stored in a partition area of the memory 41, while magnification conversion based on the print size processed by the order processing unit 43 is performed. The parameters for this are stored in the partition area of the memory 41.

  The gradation correction process in the automatic mode is a process in which input pixels are uniformly converted into a predetermined gradation based on a preset lookup table (not shown), and the gradation process in the manual mode is performed. Is a process of changing the tone curve of each image via the tone curve editing tool displayed via the graphic user interface unit 42, and this adjusts the gradation of the highlight part and the shadow part. is there. The color correction processing in the automatic mode refers to color correction processing based on the LATD (Large Area Transmittance Density) method based on the Evans theorem, and the color correction processing in the manual mode is displayed via the graphic user interface unit 42. YMC refers to a process of changing the color component of each image in five levels from standard level 0 to ± 2 via the YMC color component correction tool. A known correction process other than these may be used.

  In this way, correction parameters for each frame image are generated, high-resolution image data is corrected based on the correction parameters, and print data for final print output is generated. As described above, the image correction limiting unit 56 limits the correction parameters for the image data determined as the similar scene by the similar scene determining unit 48. Specifically, the tone correction parameter by the tone curve editing tool and the color correction parameter by the YMC color component correction tool are set as the new correction parameters for the images of similar scenes, or Replace each correction parameter for each identified image with a correction parameter for a specific image among them, for example, a correction parameter indicating a median value, or a predetermined range based on a correction parameter for a specific image indicating a median value In other words, the correction parameters of the images of other similar scenes are rounded. The correction parameters restricted by the image correction restriction unit 56 are not limited to these.

  In this way, it is possible to avoid the output of inconvenient prints with markedly different photographic print quality, i.e. gradation and hue, for photographic images taken of similar scenes.

  Another embodiment will be described below. When the image is divided into blocks, subject detection means for detecting the face area of the person who is the main subject is provided, and the size of the detected face area can be set as the block size. It is also possible to detect a peculiar region of both images to be compared, for example, a region having a color tone different from the surrounding color tone, and set the size of the region as a block size. That is, a specific subject included in common between both images may be detected, and the size of the subject may be set as the block size.

  In the above-described embodiment, the evaluation unit 51 adds the difference of the image characteristic values between each block of the evaluation image and the block of the other image at the position corresponding to each block for all the blocks constituting the evaluation image. Although the description has been given of determining whether or not two images to be compared based on the evaluation value are similar scenes, in addition to or instead of this, the movement vector and the image of each block constituting the evaluation image It is also possible to determine whether or not the two images to be compared are similar scenes based on the correlation between the characteristic values.

  In other words, images of similar scenes are generated when the same subject is continuously shot. After the subject is stationary, the shooting angle is changed to up, down, left, right, or diagonal after shooting one image. When shooting an image, almost all blocks of the evaluation image generated by the evaluation image generation unit show the same movement vector, and only the main subject moves without changing the shooting angle when shooting the other image. In this case, the block vector corresponding to the background of the evaluation image shows zero, while the block corresponding to the main subject shows the same movement vector. In this way, in a similar scene, each block can be grouped into a single block group or a plurality of block groups having the same or similar movement vectors, and therefore, discrimination is made based on the tendency. For example, when there is a group of blocks in which the movement vectors of a plurality of adjacent blocks show almost the same value, it can be determined as a similar scene. If the scene is not similar, it can be clearly discriminated in that there is no correlation between the respective movement vectors and the blocks, resulting in disorder.

  In the above-described embodiment, the image correction restriction unit has been described to perform the correction parameter restriction process for an image determined to be a similar scene after the correction parameters for all frame images are derived by the image correction unit. This restriction process may be performed individually after the correction parameters for each frame image are derived by the image correction unit. In this case, the correction parameter for the previously set frame image in the image of the similar scene can be reflected in the next frame image as it is, and the correction parameter corrected in the frame image is reflected in the previous frame image. You may comprise.

  In the above-described embodiment, the image processing unit that performs a predetermined process on the image determined as the similar scene sets the image correction processing condition by the image correction unit for the image determined as the similar scene by the similar scene determination unit. Although the description has been given of the image correction limiting unit that restricts the image processing unit, the image processing unit that performs predetermined processing on the image determined to be a similar scene is not limited to this. For example, a similar scene It is possible to perform arbitrary image processing on images that have been identified as similar scenes, such as providing a grouping processing unit for grouping frame images and an album editing unit for editing an album for each grouped frame image group. is there.

  In the above-described embodiment, the case where the image processing apparatus and the image processing method are realized in the photographic processing apparatus has been described. However, the image processing apparatus and the image processing method according to the present invention can also be realized on a general personal computer. In addition, the detailed configuration of the hardware that implements the image processing apparatus can be appropriately designed using a known technique as long as the effects of the present invention are achieved.

External view of photographic image processing device Block diagram of photo printer Functional block diagram of photographic image processing device Explanatory drawing of block division of image for similar scene discrimination Flow chart explaining similar scene discrimination procedure

Explanation of symbols

48: Similar scene discrimination unit 49: Block division unit 50: Evaluation image generation unit 51: Evaluation unit 52: Image correction unit 56: Image correction restriction unit

Claims (6)

An image processing apparatus configured to include a similar scene determination unit that determines similarity between a plurality of input images, and an image processing unit that performs a predetermined process on an image determined to be a similar scene,
The similar scene discriminating unit divides each of the two images to be compared into a plurality of blocks of a predetermined size to obtain an image characteristic value of each block, and the image characteristic value is highly consistent between the two images An evaluation image generation unit that generates an evaluation image in which blocks are associated with each other and a block of one image is moved to the position of the associated block of the other image, and the generated evaluation image and the other image are compared An image processing apparatus including an evaluation unit that determines whether or not two images are similar scenes.   The evaluation unit is based on a similarity evaluation value obtained by adding the difference of the image characteristic values between each block of the evaluation image and the block of the other image at a position corresponding to each block for all the blocks constituting the evaluation image. The image processing apparatus according to claim 1, wherein it is determined whether or not the two images to be compared are similar scenes.   The image processing apparatus according to claim 1, wherein the evaluation unit determines whether the two images to be compared are similar scenes based on a movement vector of each block constituting the evaluation image.   The image processing apparatus according to claim 1, wherein the evaluation unit determines that the scene is not a similar scene when the number of blocks constituting the evaluation image generated by the evaluation image generation unit is smaller than a predetermined number. .   An image correction unit that performs a predetermined image correction process on the input image, and the image processing unit sets an image correction processing condition by the image correction unit for an image determined as a similar scene by the similar scene determination unit. The image processing apparatus according to claim 1, wherein the image processing apparatus includes an image correction restriction unit that restricts the image correction. An image processing method comprising: a similar scene determination step for determining similarity between a plurality of input images; and an image processing step for performing predetermined processing on an image determined as a similar scene,
The similar scene discrimination step includes a block division step for obtaining an image characteristic value of each block by dividing each of the two images to be compared into a plurality of blocks of a predetermined size, and a high degree of coincidence of the image characteristic values between the two images. An evaluation image generation step for generating an evaluation image in which blocks are associated with each other and a block of one image is moved to the position of the associated block of the other image, and the generated evaluation image is compared with the other image An image processing method comprising an evaluation step for determining whether or not two images are similar scenes.

Images