JP2011014051A - Generating device, generating method, and generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a generating device, a generation method and a generation program for more efficiently generating a filter for the conversion processing of a characteristic image into a target image, in genetic processing.SOLUTION: The generating device for generating an adaptive image filter to be adapted to conversion from an input image for learning into a target image is provided with an acceptance section for accepting a designated input image including a partial designated region in the input image for learning and the target image; a generation section for generating a plurality of image filters; a calculation section for calculating the adaptivity of a plurality of output images obtained, by converting the designated input image by each of the plurality of image filters to the target image; and a selection section for selecting the adaptive image filter from among the plurality of image filters, based on the adaptability of each of the plurality of output images.

Description

  The present invention relates to a generation device, a generation method, and a generation program.

  A method for generating a filter or a converter using evolutionary computation such as a genetic algorithm or genetic programming is known (see Non-Patent Document 1). According to the method of generating a filter or a converter using such evolutionary computation, fewer filters or converters having a complicated structure that are optimal for each case and difficult to obtain analytically are obtained. It can be designed with effort and time.

Masayoshi Maebuchi and two others, “Study on Image Filter Design Using Genetic Algorithm” [online], Computer Utilization Education Council, [March 20, 2008 search], Internet <URL: http: //www.ciec. or.jp/event/2003/papers/pdf/E00086.pdf>

  By the way, the method of generating an image filter by such evolutionary calculation requires an enormous number of generations until a target image filter is obtained. Therefore, such a method has a huge calculation cost until obtaining the target image filter. Further, in order to efficiently generate an image filter that can be converted into a target image, a target image for learning must be prepared, and it may take time to create the target image.

  Then, an object of this invention is to provide the production | generation apparatus, production | generation method, and production | generation program which can solve said subject. This object is achieved by a combination of features described in the independent claims. The dependent claims define further advantageous specific examples of the present invention.

  In order to solve the above-described problem, in the first aspect of the present invention, there is provided a generation device that generates an adaptive image filter adapted to conversion from a learning input image to a target image, and includes a part of the learning input image. A receiving unit that receives a designated input image including a designated area, a target image, a generating unit that generates a plurality of image filters, and a plurality of output images obtained by converting the designated input image by each of the plurality of image filters. A generation unit comprising: a calculation unit that calculates the degree of matching with the target image; and a selection unit that selects an adaptive image filter from a plurality of image filters based on the degree of matching of each of the plurality of output images. A generation method and a generation program related to the generation apparatus are also provided.

  The above summary of the invention does not enumerate all necessary features of the present invention. In addition, a sub-combination of these feature groups can also be an invention.

The structure of the production | generation apparatus 10 which concerns on this embodiment is shown. An example of the image filter 20 which combined the filter component 22 which concerns on this embodiment in series is shown. An example of the image filter 20 in which the filter component 22 according to the present embodiment is combined in a tree structure is shown. An example of a genetic operation performed on the image filter 20 in which the filter components 22 according to the present embodiment are combined in series is shown. An example of the crossover operation performed on the image filter 20 in which the filter component 22 according to the present embodiment is combined in a tree structure is shown. An example of a mutation operation performed on the image filter 20 in which the filter component 22 according to the present embodiment is combined in a tree structure is shown. An example of a similarity calculation method, which is an example of a parameter representing the degree of matching of the image filter 20 according to the present embodiment, is shown. An example of the processing flow of the production | generation apparatus 10 which concerns on this embodiment is shown. An example of a processing flow until the image filter 20 is selected in step S14 of FIG. An example of a weight image update processing flow by the weight generation unit 43 in step S21 of FIG. 9 is shown. An example about the designation | designated area | region in case the user concerning this embodiment designates is shown. An example of a designated area in the case of automatic designation by a shape according to the present embodiment will be shown. An example of a designated area in the case of automatic designation by luminance according to the present embodiment will be shown. An example of a designated area in the case of automatic designation by size according to the present embodiment will be shown. An example about the designation | designated area | region in the case of automatic designation | designated by the quantity which concerns on this embodiment is shown. An example of a characteristic selection window is shown for extraction from an image in a designated area according to the present embodiment. 2 shows an exemplary hardware configuration of a computer 1900 according to the present embodiment.

  Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all the combinations of features described in the embodiments are essential for the solving means of the invention.

  FIG. 1 shows a configuration of a generation apparatus 10 according to the present embodiment. The generation apparatus 10 evolves an image filter group including at least one image filter 20 over a plurality of generations based on evolutionary computation. In the present embodiment, each image filter 20 has a structure in which inputs and outputs of a plurality of filter components that process a learning input image and output a processing result as an output image are combined. Then, the generation device 10 generates an image filter 20 suitable for converting the learning input image into the target image. The generation device 10 is realized by a computer as an example.

  The generation device 10 includes a filter storage unit 34, a learning input image storage unit 36, an input image display unit 56, a specifying unit 54, a reception unit 58, a filter processing unit 38, an output image storage unit 40, A target image storage unit 42, a weight generation unit 43, a calculation unit 44, a selection unit 46, an update unit 48, and a generation unit 50 are provided. The filter storage unit 34 stores a plurality of image filters 20 having different configurations.

  The learning input image storage unit 36 stores a plurality of learning input images to be converted by the image filter 20. As an example, the learning input image is an image captured in advance by a user and an image generated in advance.

  The input image display unit 56 sequentially acquires one or more learning input images stored in the learning input image storage unit 36. The input image display unit 56 displays each acquired learning input image to the user.

  The specifying unit 54 specifies the designated area received by the receiving unit 58 from the learning input image. For example, the specifying unit 54 sets a part of the learning input image that satisfies a predetermined characteristic as the designated area. Here, the specifying unit 54 may specify the shape, size, quantity, luminance value, and the like in the learning input image as characteristics for specifying a region. Instead of this, the specifying unit 54 may set a partial area that satisfies at least one characteristic selected by the user in the learning input image as the designated area.

  The accepting unit 58 accepts a designated input image including a part of a designated area in the learning input image and a target image. Here, as an example, the accepting unit 58 accepts a designated input image and a target image in which a designated region is a region including a part of a converted image obtained by converting the learning input image by the image filter 20. The accepting unit 58 may accept a designated input image having at least one region frame of a plurality of region frames set in advance or at least one region identified by the identifying unit 54 as a designated region.

  In addition, the reception unit 58 may cause the learning input image displayed by the input image display unit 56 to be changed by the user to create a target image. In this case, as an example, the receiving unit 58 receives a region freely designated by the user in the learning input image and creates a target image.

  The filter processing unit 38 sequentially acquires one or a plurality of image filters 20 stored in the filter storage unit 34. The filter processing unit 38 converts each learning input image stored in the learning input image storage unit 36 by each acquired image filter 20 to generate each output image.

  The output image storage unit 40 stores the output image generated by the filter processing unit 38. For example, the output image storage unit 40 stores each output image in association with the converted image filter 20.

  The target image storage unit 42 stores a target image that is a target of an output image generated by converting the learning input image. As an example, the target image may be an image received by the receiving unit 58, or generated or prepared in advance by the user in order to extract a target image from the learning input image.

  The weight generation unit 43 generates a weight image representing the weight for each data area in the comparison between the output image and the target image. For example, the weight generation unit 43 generates a weight image in which data is arranged in the same manner as the output image and the target image. The weight generation unit 43 may generate a weight image representing the weight of the pixel position based on the value of each pixel (for example, luminance value) of the output image and the target image. Here, as an example, the weight generation unit 43 sets the weight for an image having a larger difference for each image between at least one set of the output image and the target image to be larger than the weight for an image having a smaller difference. A weight image is generated.

  As an example, the weight generation unit 43 includes a weight storage unit 60 and a weight update unit 62. The weight storage unit 60 stores a weight image. The weight updating unit 62 calculates, for example, a pixel-by-pixel difference between at least one output image extracted for updating the weighted image and the target image, and assigns a weight of an area where the difference for each pixel is larger to an area with a smaller difference. The weight image stored in the weight storage unit 60 is updated so as to be larger than the weight.

  The weight update unit 62 may update the weight image for each generation. Here, as an example, the weight update unit 62 adds a predetermined value to the weight corresponding to data whose difference from the target image in the current generation weight image is larger than the threshold value, and A value smaller than a predetermined value is added to the weight corresponding to the data whose difference is equal to or less than the threshold value.

  In this way, the weight update unit 62 generates the next generation weight image. Instead, the weight updating unit 62 adds a predetermined value to the weight corresponding to data in which the difference from the target image is larger than the threshold in the current generation weight image, and the data in which the difference from the target image is equal to or less than the threshold. A predetermined value may be subtracted from the weight corresponding to. For example, every time the weight image is updated by the weight update unit 62, the weight storage unit 60 may store the weight image before being updated separately from the updated weight image.

  The calculation unit 44 calculates the degree of matching with the target image for each of the plurality of output images obtained by converting the designated input image by each of the plurality of image filters 20 stored in the filter storage unit 34. Here, the fitness is an index value indicating whether or not the learning input image is suitable for conversion to the target image, and the higher the value, the more suitable the conversion of the learning input image to the target image. Represents that As an example, the calculation unit 44 calculates the fitness for conversion from the learning input image to the target image for each current-generation image filter 20 by weighting the weighted image.

  The selection unit 46 selects at least one adaptive image filter 20 from among the plurality of image filters 20 stored in the filter storage unit 34 based on the respective fitness levels of the plurality of output images. Here, as an example, the selection unit 46 preferentially selects the image filter 20 obtained by converting the output image having a higher fitness. More specifically, the selection unit 46 selects at least one image filter 20 to remain by using a technique that models natural selection of living things. Further, as an example, the selection unit 46 selects at least one image filter 20 by genetic calculation such as elite selection and roulette selection based on the fitness of each of the plurality of image filters 20 stored in the filter storage unit 34. . Further, the selection unit 46 may select the adaptive image filter 20 from the plurality of image filters 20 included in the image filter group based on the degree of fitness.

  The update unit 48 leaves the image filter 20 selected by the selection unit 46 among the plurality of image filters 20 stored in the filter storage unit 34, and tricks the image filter 20 not selected by the selection unit 46. For example, the update unit 48 hesitates by deleting the image filter 20 from the filter storage unit 34.

  The generation unit 50 generates a plurality of image filters 20 that process the learning input image and output the processing results as output images. The generation unit 50 acquires from the filter storage unit 34 at least one image filter 20 remaining in the update process by the update unit 48. Subsequently, as an example, the generation unit 50 performs a genetic operation such as crossover and mutation on the acquired at least one image filter 20 to generate a new image filter 20. Then, as an example, the generation unit 50 writes the generated new image filter 20 in the filter storage unit 34. Thereby, the filter storage unit 34 can store at least one image filter 20 remaining in the update process and a new image filter 20 generated by the generation unit 50.

  Such a generation apparatus 10 includes a conversion process by the filter processing unit 38, a calculation process of the fitness by the calculation unit 44, a selection process of the image filter 20 by the selection unit 46, an update process by the update unit 48, and a new process by the generation unit 50. The generation process of the image filter 20 is repeated a plurality of times (for example, a plurality of generations). Thus, the generation device 10 can generate the image filter 20 suitable for converting the designated range from the learning input image into a clear target image using evolutionary calculation.

  FIG. 2 shows an example of the image filter 20 in which the filter components 22 according to the present embodiment are combined in series. FIG. 3 shows an example of the image filter 20 in which the filter component 22 according to the present embodiment is combined in a tree structure.

  The image filter 20 may have a configuration in which a plurality of filter components 22 are combined in series as shown in FIG. The image filter 20 may have a configuration in which a plurality of filter components 22 are combined in a tree structure as shown in FIG. Further, the image filter 20 may have a plurality of output ends with respect to one input end. The image filter 20 may have a configuration having a plurality of input ends and a plurality of output ends.

  The image filter 20 performs a filter calculation process on the received learning input image and outputs an output image. As an example, the image filter 20 is a program that performs an operation on image data. In addition, the image filter 20 may be an arithmetic expression that represents the content of calculation to be performed on the image data.

  Note that the image filter 20 having the structure in which the filter parts 22 are combined in a tree structure is given the same learning input image to each of the end (lowest) filter parts 22 of the tree structure, and the highest level of the tree structure. The output image is output from the filter component 22. Instead of this, such an image filter 20 may be provided with different learning input images for each of the plurality of terminal filter components 22.

  In the present embodiment, the generation unit 50 generates a new image filter 20 by genetic processing from an image filter group having at least one image filter 20 including a plurality of filter components 22 that respectively convert an input image into an output image. In addition to the image filter group, a plurality of image filters 20 are generated. Here, the image filter 20 may have a configuration in which a filter component 22 that is a program for performing an operation on image data is combined. Further, the image filter 20 may have a configuration in which a filter component 22 that is an arithmetic expression representing the content of calculation to be performed on image data is combined.

  Each of the plurality of filter components 22 receives the image data output from the filter component 22 arranged in the previous stage, performs an operation on the received image data, and gives it to the filter component 22 arranged in the subsequent stage. Each of the plurality of filter components 22 may be a program module, an arithmetic expression, or the like, and performs binarization operation, histogram operation, smoothing operation, edge detection operation, morphology operation, and / or frequency on received image data. Unary operations such as space operations (for example, low-pass filtering operations and high-pass filtering operations) may be performed.

  In addition, each of the plurality of filter components 22 performs an average operation, a difference operation, and / or a fuzzy operation (for example, logical sum operation, logical product operation, algebraic sum, algebraic product, limit sum, limit product, Binomial operations such as intense sum and intense product) may be performed.

  FIG. 4 shows an example of a genetic operation performed on the image filter 20 in which the filter components 22 according to this embodiment are combined in series. FIG. 5 shows an example of a crossover operation performed on the image filter 20 in which the filter component 22 according to this embodiment is combined in a tree structure. FIG. 6 shows an example of a mutation operation performed on the image filter 20 in which the filter component 22 according to this embodiment is combined in a tree structure.

  For example, the generation unit 50 performs a crossover operation, which is an example of a genetic operation, on two or more image filters 20 to generate two or more new image filters 20. As an example, as illustrated in FIG. 4 and FIG. 5, the generation unit 50 converts a part of the filter component group 24A of at least one image filter 20A that has already been generated into another image filter 20B that has already been generated. Are replaced with at least a part of the filter component group 24B to generate new image filters 20E and 20F. The filter component group 24 may be a member in which one or a plurality of filter components 22 are combined.

  Further, for example, the generation unit 50 performs a mutation operation, which is an example of a genetic operation, on one image filter 20 to generate a new one image filter 20. As an example, as illustrated in FIG. 4 and FIG. 6, the generation unit 50 converts a part of the filter component group 24 </ b> C of one image filter 20 </ b> C that has already been generated into another filter component group 24 </ b> G selected at random. A new image filter 20G is generated by replacement.

  The generation unit 50 may leave the current generation image filter 20 as the next generation image filter 20 as it is. For example, as illustrated in FIG. 4, the generation unit 50 generates a next-generation image filter 20H that includes the configuration of the filter component 22 of the image filter 20D as it is.

  For example, the selection unit 46 preferentially selects at least one image filter 20 having a higher degree of matching of each of the plurality of output images. Subsequently, the update unit 48 stores the image filter 20 in the filter storage unit 34 in order to make the selected image filter 20 survive to the next generation, and the filter storage unit 34 in order to kill the image filter 20 that has not been selected. Delete from within.

  FIG. 7 shows an example of a method for calculating similarity, which is an example of a parameter representing the degree of matching of the image filter 20 according to the present embodiment. In the present embodiment, the calculation unit 44 calculates a similarity indicating how similar the output image generated by converting the learning input image by the image filter 20 and the target image are. This similarity is an example of a parameter representing the degree of matching of the image filter 20, and is used as an evaluation value or index indicating that the larger the value is, the more appropriate the image filter 20 that generated the output image is. .

  The calculation unit 44 calculates a comparison value by comparing the value of each region of the output image with the value of each region corresponding to the target image, and multiplies the comparison value for each region by the weight specified by the weight image. Then, the calculation unit 44 calculates a value obtained by averaging or summing the comparison values for each region multiplied by the weight for all regions, and outputs the calculated value as the similarity of the output image.

  For example, the calculation unit 44 calculates the difference or ratio between the luminance value for each pixel of the output image and the luminance value of the corresponding pixel of the target image. Then, as an example, the calculation unit 44 multiplies each calculated difference or ratio for each pixel by the corresponding weight specified by the weight image, and sums or averages the difference or ratio for each pixel multiplied by the weight. Thus, the similarity is calculated. In this case, the sizes of the output image, the target image, and the weight image are the same.

In the formula (1), f represents the similarity. Y _max represents the maximum luminance value. X is a variable indicating the pixel position in the horizontal direction of the image. y is a variable indicating the pixel position in the vertical direction of the image. xmax is a constant indicating the number of pixels in the horizontal direction of the image. ymax is a constant indicating the number of pixels in the vertical direction of the image.

I _weight (x, y) represents the luminance value of the pixel at the (x, y) position in the weighted image. I _target (x, y) represents the luminance value of the pixel at the (x, y) position in the target image. I _filter (x, y) represents the luminance value of the pixel at the (x, y) position in the output image.

  That is, as indicated by the numerator part in the curly braces of Expression (1), the calculation unit 44 calculates the luminance value of the weighted image with respect to the absolute value of the difference between the luminance value of the target image and the luminance value of the output image. The multiplied weighted difference value is calculated for every pixel in the screen, and a total weighted difference value is calculated by adding the calculated weighted difference values for all pixels. Further, as indicated by the denominator part in the curly braces of Expression (1), the calculation unit 44 calculates a total weight obtained by adding the luminance values of the weighted image for all pixels.

  Further, the calculation unit 44 multiplies the division value (in the curly braces of the equation (1)) obtained by dividing the total weighted difference value by the total weight by the reciprocal (1 / Ymax) of the maximum value of the luminance value (normalized value). The second term of the formula (1) is calculated. Then, the calculation unit 44 calculates a value obtained by subtracting the normalized value from 1 as the similarity f. In this way, the calculation unit 44 can calculate the similarity by weighting the difference between the output image and the target image for each region.

  FIG. 8 shows an example of the processing flow of the generation apparatus 10 according to this embodiment. First, the generating apparatus 10 specifies a specified area by the specifying unit 54 and generates a target image based on the specified area received by the receiving unit 58 (S18). The accepting unit 58 may accept coordinate information or the like designated by the user in the input image display unit 56 as a designated area.

  And the production | generation apparatus 10 performs each process of step S12-step S15 repeatedly (for example, multiple generations) repeatedly (S11, S16). The generation device 10 preliminarily filters the randomly generated or already generated image filter 20 as an initial image filter 20 for generating the image filter 20 that converts the given learning input data into target data. Stored in the storage unit 34.

  In each generation process, the generation unit 50 performs genetic operations such as a crossover operation and a mutation operation on the plurality of image filters 20 remaining from the previous generation, so that at least some of the filter components 22 are replaced. A plurality of new image filters 20 replaced with the filter component 22 are generated (S12). As an example, the generation unit 50 preliminarily filters the randomly generated or already generated image filter 20 as the initial image filter 20 for generating the image filter 20 that converts the learning input image into the output image. Stored in the storage unit 34.

  Subsequently, the filter processing unit 38 generates an output image by filtering the learning input image with each of the plurality of image filters 20 remaining from the previous generation and the plurality of image filters 20 newly generated in step S12. (S13). Thereby, the filter processing unit 38 can generate a plurality of output images corresponding to the plurality of image filters 20.

  Subsequently, the calculation unit 44 weights and compares the output image obtained by converting the learning input image by the image filter 20 and the target image with the weight image generated by the weight generation unit 43. Here, the calculation unit 44 calculates the degree of similarity or the degree of similarity between each of the plurality of output images and the target image. Note that the calculation unit 44 calculates the degree of fitness with higher evaluation in accordance with the number of filter components 22, the low processing load, the degree of parallelism, and the like in addition to the similarity or approximation. Also good.

  Then, as an example, the selection unit 46 selects one or a plurality of image filters 20 having a higher matching degree from the plurality of image filters 20 included in the current generation image filter group (S14). For example, the selection unit 46 may randomly select the image filter 20 under a condition that the image filter 20 having a higher degree of matching is selected with a higher probability. Note that the selection unit 46 may select one image filter 20 having the highest fitness in the last generation.

  In addition, the selection unit 46 may select two or more image filters 20 having a matching degree equal to or higher than a reference value from among the plurality of image filters 20. In this case, as an example, the selection unit 46 preferentially selects two or more image filters 20 from the top of the image filters 20 having a fitness level equal to or higher than a reference value. Instead of this, the selection unit 46 may randomly select two or more image filters 20 out of the image filters 20 having a reference value or more. Further, the generation device 10 displays each of the two or more output images obtained by converting the learning input image by each of the two or more image filters 20 via the input image display unit 56 or the like. The adaptive image filter 20 may be selected from the two or more image filters 20 selected by the selection unit 46.

  Further, the update unit 48 causes the one or more image filters 20 selected in step S14 to remain in the next generation, and the image filter 20 that has generated the output image not selected in step S14 is stored in the filter storage unit 34. It is hesitant by deleting from the image filter group (S15). In addition, the generation unit 50 may return the newly generated image filters 20 to the filter storage unit 34 and store them in addition to the already generated image filters 20.

  The generation apparatus 10 repeatedly executes the above processing for a plurality of generations (for example, tens of generations or hundreds of generations or more), and executes the processing up to the last generation (for example, the Nth generation, where N is a natural number of 2 or more). Later, the flow is exited (S16). In this way, the generation apparatus 10 can generate the image filter 20 suitable for converting the learning input image into the target image using evolutionary calculation.

  FIG. 9 shows an example of a processing flow until the image filter 20 is selected in step S14 of FIG. The generation device 10 executes the following processing in step S14 shown in FIG.

  First, the weight generation unit 43 automatically updates the weight image so as to generate an appropriate weight image for each generation (step S21). Details of the weight image update processing by the weight generation unit 43 will be described later with reference to FIG.

  Subsequently, the calculation unit 44 performs the following step S23 for each of the plurality of output images generated by each of the plurality of image filters 20 stored in the filter storage unit 34 (S22, S24). . In step S <b> 23, the calculation unit 44 compares the output image with the target image by weighting according to the weighted image, and calculates the degree of similarity or approximation between the output image and the target image as the fitness. When the calculation unit 44 finishes the process for all of the plurality of output images, the process proceeds to step S25 (S24).

  Subsequently, the selection unit 46 selects an output image that is closer to the target image from the plurality of output images based on the degree of matching of each of the plurality of output images (S25). As an example, the selection unit 46 preferentially selects an output image having a higher degree of matching among a plurality of output images converted by the plurality of image filters 20. For example, the selection unit 46 selects an output image having a fitness level higher than the standard fitness level. Further, the selection unit 46 may select a selection target image in a range in which the fitness is predetermined from the top. Further, the selection unit 46 may select the output image at random under the condition that the output image having a higher fitness is selected with a higher probability.

  Then, the selecting unit 46 selects the image filter 20 that generates the selected output image as the image filter 20 that converts the learning input image into an image that is more similar to the target image (S26). When the process of step S26 is completed, the generation device 10 ends the flow. As described above, in the present embodiment, the image filter 20 selected by the selection unit 46 among the plurality of image filters 20 generated based on the designated input image including a part of the designated area in the learning input image is selected. It can be applied to an input image for learning. Therefore, by applying to the learning input image the image filter 20 that has been applied to the designated input image and converted to an output image having a high degree of fitness with respect to the target image, the computation cost (eg, efficiency improvement, time reduction, etc.) Can be reduced.

  FIG. 10 shows an example of a weight image update processing flow by the weight generation unit 43 in step S21 of FIG. The weight generation unit 43 performs the following steps S31 to S33 in the weight image update processing in step S21 shown in FIG.

  First, the weight update unit 62 includes at least one of a plurality of output images generated by each of the plurality of image filters 20 remaining from the previous generation and the plurality of image filters 20 newly generated in step S12 of FIG. Two output images are extracted as output images for updating the weight image (S31). For example, the weight updating unit 62 extracts an output image generated by the image filter 20 having the highest degree of matching calculated in the previous generation among the plurality of image filters 20. Further, the weight update unit 62 may extract one or a plurality of output images generated by the image filter 20 having a fitness calculated in the previous generation equal to or greater than a predetermined value. For example, the weight update unit 62 extracts an output image generated by any one of the plurality of image filters 20.

  Subsequently, the weight updating unit 62 calculates a difference for each region between at least one output image selected in step S31 and the target image (S32). As an example, the weight update unit 62 calculates a difference for each pixel between the target image and at least one output image selected in step S31. When a plurality of output images are selected in step S31, the weight updating unit 62, for example, is the largest of a plurality of differences between each of the selected plurality of output images and one target image. One difference or an average value of the plurality of differences is selected for each region (for example, for each pixel).

  Subsequently, the weight update unit 62 changes the weight image stored in the weight storage unit 60, that is, the weight image used in the previous generation process, based on the difference for each region calculated in step S32 (S33). ). More specifically, the weight update unit 62 updates the weight image stored in the weight storage unit 60 so that the weight of the region with the larger difference is larger than the weight of the region with the smaller difference. For example, the weight storage unit 60 stores in advance, as an initial generation weight image, a weight image generated with the same weight for each region or already generated.

  In the above, the weight generation unit 43 can generate and update a weight image for converting the learning input image into an image more similar to the learning target image.

  FIG. 11A shows an example of the designated area when designated by the user according to the present embodiment. FIG. 11B shows an example of the designated area in the case of automatic designation by the shape according to the present embodiment. FIG. 11C shows an example of a designated area in the case of automatic designation by luminance according to the present embodiment. FIG. 11D shows an example of a designated area in the case of automatic designation by size according to the present embodiment. FIG. 11E shows an example of a designated area in the case of automatic designation by quantity according to the present embodiment.

  The accepting unit 58 causes the user to designate at least one designated region in the learning input image displayed by the input image display unit 56 as in the manual region designation screen 1100. In this case, the accepting unit 58 designates a range by a frame of a preset range or a range input with a mouse.

  The automatic area designation (shape) screen 1110 is an example of a case where a shape preset in the generation apparatus 10 is searched and a range is automatically designated. The accepting unit 58 may extract two or more shapes at the same time and extract a designated range. The automatic area designation (brightness value) screen 1120 is an example of a case in which a range is automatically designated from the brightness value preset in the generation device 10 for the output image. In this case, the reception unit 58 sets all the objects corresponding to the luminance values in the set range as targets for automatic specification in the output image. The accepting unit 58 may specify a range of an area that is an average value of luminance values of the entire image area.

  The automatic area designation (size) screen 1130 is an example of automatically designating a range of a figure having a size set in advance in the generation apparatus 10. Here, as an example, the accepting unit 58 automatically designates all figures having a specified size (for example, area or pixel) or more. Instead of this, the receiving unit 58 may designate at least one figure having a size (for example, area or pixel) in a range designated by the user as a designation target. The automatic area designation (quantity) screen 1140 is an example of automatic designation when there is a designated quantity of objects in the output image. Here, the accepting unit 58 designates a plurality of regions because the region is designated when the same figure satisfies a certain number in the output image.

  The accepting unit 58 may specify the range by combining the plurality of features described above. Thereby, the generation device 10 can efficiently generate the image filter 20 suitable for extracting a plurality of features in the designated region.

  FIG. 12 shows an example of a characteristic selection window when extracting from an image in a designated area. As shown in the figure, the reception unit 58 stores parameters that are characteristics set by the user in order to generate the image filter 20 that extracts the specified feature by filter conversion. As an example, the accepting unit 58 displays a setting window on the screen of the input image display unit 56, and the user selects a plurality of prepared setting values.

  Here, the accepting unit 58 causes the user to select at least one of a plurality of types of characteristics such as the shape, quantity, size, and average luminance value range for the designated object. In addition, the reception unit 58 may set each of two or more areas obtained by combining a plurality of two or more different characteristics in the learning input image as designated areas. Instead of this, the receiving unit 58 may be switched to a setting that allows the user to manually specify a range via the input image display unit 56.

  As described above, the generation device 10 can generate the image filter 20 suitable for extracting the range and features specified by the user.

  FIG. 13 shows an example of a hardware configuration of a computer 1900 according to the present embodiment. A computer 1900 according to this embodiment is connected to a CPU peripheral unit including a CPU 2000, a RAM 2020, a graphic controller 2075, and a display device 2080 that are connected to each other by a host controller 2082, and to the host controller 2082 by an input / output controller 2084. An input / output unit having a communication interface 2030, a hard disk drive 2040, and a DVD drive 2060, and a legacy input / output unit having a ROM 2010, a flexible disk drive 2050, and an input / output chip 2070 connected to the input / output controller 2084 Is provided.

  The host controller 2082 connects the RAM 2020 to the CPU 2000 and the graphic controller 2075 that access the RAM 2020 at a high transfer rate. The CPU 2000 operates based on programs stored in the ROM 2010 and the RAM 2020 and controls each unit. The graphic controller 2075 acquires image data generated by the CPU 2000 or the like on a frame buffer provided in the RAM 2020 and displays it on the display device 2080. Instead of this, the graphic controller 2075 may include a frame buffer for storing image data generated by the CPU 2000 or the like.

  The input / output controller 2084 connects the host controller 2082 to the communication interface 2030, the hard disk drive 2040, and the DVD drive 2060, which are relatively high-speed input / output devices. The communication interface 2030 communicates with other devices via a network. The hard disk drive 2040 stores programs and data used by the CPU 2000 in the computer 1900. The DVD drive 2060 reads a program or data from the DVD 2095 and provides it to the hard disk drive 2040 via the RAM 2020.

  The input / output controller 2084 is connected to the ROM 2010, the flexible disk drive 2050, and the relatively low-speed input / output device of the input / output chip 2070. The ROM 2010 stores a boot program that the computer 1900 executes at startup and / or a program that depends on the hardware of the computer 1900. The flexible disk drive 2050 reads a program or data from the flexible disk 2090 and provides it to the hard disk drive 2040 via the RAM 2020. The input / output chip 2070 connects the flexible disk drive 2050 to the input / output controller 2084 and inputs / outputs various input / output devices via, for example, a parallel port, a serial port, a keyboard port, a mouse port, and the like. Connect to controller 2084.

  A program provided to the hard disk drive 2040 via the RAM 2020 is stored in a recording medium such as the flexible disk 2090, the DVD 2095, or an IC card and provided by the user. The program is read from the recording medium, installed in the hard disk drive 2040 in the computer 1900 via the RAM 2020, and executed by the CPU 2000.

  A program that is installed in the computer 1900 and causes the computer 1900 to function as the generation device 10 includes a filter processing module, a weight generation module, a calculation module, a selection module, an update module, a generation module, a specific module, and a reception module. And an input image display module. These programs or modules work with the CPU 2000 or the like to identify the computer 1900, the filter processing unit 38, the weight generation unit 43, the calculation unit 44, the selection unit 46, the update unit 48, the generation unit 50, The unit 54, the input image display unit 56, and the reception unit 58 are caused to function.

  The information processing described in these programs is read into the computer 1900, whereby the filter processing unit 38, which is a specific means in which the software and the various hardware resources described above cooperate, the weight generation unit 43, The calculation unit 44, the selection unit 46, the update unit 48, the generation unit 50, the specification unit 54, the input image display unit 56, and the reception unit 58 function. And the specific production | generation apparatus 10 according to the intended purpose is constructed | assembled by implement | achieving the calculation or processing of the information according to the intended purpose of the computer 1900 in this embodiment by these specific means.

  As an example, when communication is performed between the computer 1900 and an external device or the like, the CPU 2000 executes a communication program loaded on the RAM 2020 and executes a communication interface based on the processing content described in the communication program. A communication process is instructed to 2030. Under the control of the CPU 2000, the communication interface 2030 reads transmission data stored in a transmission buffer area or the like provided on a storage device such as the RAM 2020, the hard disk drive 2040, the flexible disk 2090, or the DVD 2095, and transmits it to the network. Alternatively, the reception data received from the network is written into a reception buffer area or the like provided on the storage device. As described above, the communication interface 2030 may transfer transmission / reception data to / from the storage device by a DMA (direct memory access) method. Instead, the CPU 2000 transfers the storage device or the communication interface 2030 as a transfer source. The transmission / reception data may be transferred by reading the data from the data and writing the data to the transfer destination 2030 or the storage device.

  In addition, the CPU 2000 reads all or necessary portions from files or databases stored in an external storage device such as the hard disk drive 2040, the DVD drive 2060 (DVD 2095), and the flexible disk drive 2050 (flexible disk 2090). The data is read into the RAM 2020 by DMA transfer or the like, and various processes are performed on the data on the RAM 2020. Then, CPU 2000 writes the processed data back to the external storage device by DMA transfer or the like. In such processing, since the RAM 2020 can be regarded as temporarily holding the contents of the external storage device, in the present embodiment, the RAM 2020 and the external storage device are collectively referred to as a memory, a storage unit, or a storage device. Various types of information such as various programs, data, tables, and databases in the present embodiment are stored on such a storage device and are subjected to information processing. Note that the CPU 2000 can also hold a part of the RAM 2020 in the cache memory and perform reading and writing on the cache memory. Even in such a form, the cache memory bears a part of the function of the RAM 2020. Therefore, in the present embodiment, the cache memory is also included in the RAM 2020, the memory, and / or the storage device unless otherwise indicated. To do.

  In addition, the CPU 2000 performs various operations, such as various operations, information processing, condition determination, information search / replacement, etc., described in the present embodiment, specified for the data read from the RAM 2020 by the instruction sequence of the program. Is written back to the RAM 2020. For example, when performing the condition determination, the CPU 2000 determines whether or not the various variables shown in the present embodiment satisfy the conditions such as large, small, above, below, equal, etc., compared to other variables or constants. If the condition is satisfied (or not satisfied), the program branches to a different instruction sequence or calls a subroutine.

  Further, the CPU 2000 can search for information stored in a file or database in the storage device. For example, in the case where a plurality of entries in which the attribute value of the second attribute is associated with the attribute value of the first attribute are stored in the storage device, the CPU 2000 displays the plurality of entries stored in the storage device. The entry that matches the condition in which the attribute value of the first attribute is specified is retrieved, and the attribute value of the second attribute that is stored in the entry is read, thereby associating with the first attribute that satisfies the predetermined condition The attribute value of the specified second attribute can be obtained.

  The program or module shown above may be stored in an external recording medium. As the recording medium, in addition to the flexible disk 2090 and the DVD 2095, an optical recording medium such as DVD or CD, a magneto-optical recording medium such as MO, a tape medium, a semiconductor memory such as an IC card, and the like can be used. Further, a storage device such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet may be used as a recording medium, and the program may be provided to the computer 1900 via the network.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

  The order of execution of each process such as operations, procedures, steps, and stages in the apparatus, system, program, and method shown in the claims, the description, and the drawings is particularly “before” or “prior to”. It should be noted that the output can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the description, and the drawings, even if it is described using “first”, “next”, etc. for convenience, it means that it is essential to carry out in this order. It is not a thing.

DESCRIPTION OF SYMBOLS 10 Generation apparatus, 20 Image filter, 22 Filter component, 24 Filter component group, 34 Filter storage part, 36 Learning input image storage part, 38 Filter processing part, 40 Output image storage part, 42 Target image storage part, 43 Weight generation Unit 44 calculation unit 46 selection unit 48 update unit 50 generation unit 54 identification unit 56 input image display unit 58 reception unit 60 weight storage unit 62 weight update unit 1100 manual area designation screen 1110 automatic Area designation (shape) screen, 1120 automatic area designation (luminance value) screen, 1130 automatic area designation (size) screen, 1140 automatic area designation (quantity) screen, 1900 computer, 2000 CPU, 2010 ROM, 2020 RAM, 2030 communication Interface, 2040 hard disk drive, 2050 Lexical Bull disk drive, 2060 DVD drive, 2070 output chip, 2075 graphic controller, 2080 a display device, 2082 host controller 2084 output controller, 2090 a flexible disk, 2095 DVD

Claims (12)

A generating device that generates an adaptive image filter adapted to convert from a learning input image to a target image,
A receiving unit that receives a designated input image including a part of a designated area in the learning input image, and the target image;
A generator for generating a plurality of image filters;
A calculation unit that calculates a degree of matching with the target image for a plurality of output images obtained by converting the designated input image by each of the plurality of image filters;
A selection unit that selects the adaptive image filter from the plurality of image filters based on the fitness of each of the plurality of output images;
A generating device comprising:   The generation device according to claim 1, wherein the designated area includes a part of a converted image obtained by converting the learning input image by the image filter. An input image display unit for displaying the learning input image;
The generation apparatus according to claim 1, wherein the reception unit causes the learning input image displayed by the input image display unit to be changed by a user to create the target image. The generation device according to claim 3, wherein the reception unit causes the user to specify the designated region in the learning input image displayed by the input image display unit. The generation device according to claim 1, further comprising: a specifying unit that specifies the designated region from the learning input image. The generation device according to claim 5, wherein the specifying unit sets a part of the learning input image that satisfies a predetermined characteristic as the designated region. The reception unit causes the user to select at least one characteristic among a plurality of types of characteristics,
The generation device according to claim 6, wherein the specifying unit sets, as the designated region, a partial region that satisfies the at least one characteristic selected by a user in the learning input image. The generation device according to claim 6, wherein the specifying unit sets each of two or more regions satisfying two or more different characteristics in the learning input image as the designated region. The selection unit includes:
Selecting two or more image filters having a fitness equal to or higher than a reference value among the plurality of image filters;
Displaying each of the two or more output images obtained by converting the learning input image by each of the two or more image filters;
The user causes the adaptive image filter to be selected from the two or more image filters selected by the selection unit.
The generation device according to claim 1. The generation unit generates a new image filter by genetic processing from an image filter group having at least one image filter including a plurality of filter components that respectively convert an input image into an output image, and the image filter group Generating the plurality of image filters in addition to
The generation device according to claim 1, wherein the selection unit selects the adaptive image filter based on the fitness level from the plurality of image filters included in the image filter group. A generation method for generating an adaptive image filter adapted for conversion from a learning input image to a target image,
A receiving step for receiving a designated input image including a part of a designated area in the learning input image, and the target image;
A generating step for generating a plurality of image filters;
A calculation step for calculating a degree of matching with the target image for a plurality of output images obtained by converting the designated input image by each of the plurality of image filters;
A selection step of selecting the adaptive image filter from the plurality of image filters based on the fitness of each of the plurality of output images;
A generation method comprising: A generation program that causes a computer to function as a generation device that generates an adaptive image filter adapted to conversion from a learning input image to a target image,
The computer,
A receiving unit that receives a designated input image including a part of a designated area in the learning input image, and the target image;
A generator for generating a plurality of image filters;
A calculation unit that calculates a degree of matching with the target image for a plurality of output images obtained by converting the designated input image by each of the plurality of image filters;
A selection unit that selects the adaptive image filter from the plurality of image filters based on the fitness of each of the plurality of output images;
A generation program that functions as a generation device.

Images