JP2012129796A - Image processing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To improve operation performance.SOLUTION: A flash memory 44 holds the feature amounts of plural object images respectively corresponding to plural ranges assigned to a specific object image in the state of a nest. A CPU 26 detects the feature amounts of plural partial images respectively corresponding to plural check areas assigned onto a designated image in the state of a nest, and checks the detected feature amounts with the feature amounts held by the flash memory 44. The CPU 26 also executes the image processing in different modes in accordance with the result of the check.

Description

  The present invention relates to an image processing apparatus, and more particularly to an image processing apparatus that searches an image that matches a specific object image from a designated image.

  An example of this type of image processing apparatus is disclosed in Patent Document 1. According to this background art, the image sensor 1 captures a subject image, and the display unit 9 displays a captured image captured by the image sensor. The detection processing unit 10 detects a target shooting target from the captured image. The switching unit 12 enlarges the designated area of the captured image while the captured image sequentially captured by the image sensor is sequentially displayed on the display unit and the display unit operates as an electronic viewfinder, and the detection processing unit Whether to detect the shooting target or to detect the shooting target without enlarging is switched according to the detection result of the shooting target with respect to the previously captured image among the sequentially captured images.

JP 2008-172368 A

  However, in the background art, there is a risk of erroneously detecting an object image different from the search target when a characteristic component is shared by a plurality of object images. In such a case, the operation of the image processing apparatus Performance decreases.

  Therefore, a main object of the present invention is to provide an image processing apparatus capable of improving the operation performance.

  An image processing apparatus according to the present invention (10: reference numeral corresponding to the embodiment; hereinafter the same) holds a feature quantity of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to a specific object image Means (44), detection means (S39, S55) for detecting feature quantities of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on the designated image, and feature quantities detected by the detection means Collating means (S41, S57) for collating with the feature amount held by the holding means, and processing means (S31, S59, S63, S15 to S29) for executing image processing in different modes depending on the collation result of the collating means Prepare.

  Preferably, the detection means detects a first feature quantity detecting means (S39) for detecting a first partial feature quantity corresponding to a part of the plurality of partial images, and a second feature corresponding to the other part of the plurality of partial images. The second feature quantity detection means (S55) for detecting the partial feature quantity includes a collation means, wherein the collation means includes the first partial feature quantity detected by the first feature quantity detection means and a part of the feature quantity held by the holding means. First feature quantity matching means (S41) for matching, and second feature quantity matching for matching the second partial feature quantity detected by the second feature quantity detection means with another part of the feature quantity held by the holding means Means (S57).

  More preferably, the plurality of collation areas include a first collation area having a large size and a second collation area having a small size, and the first partial feature amount corresponds to one of the first collation area and the second collation area. The second partial feature amount includes a feature amount corresponding to the other of the first collation area and the second collation area.

  Preferably, it further includes an activation unit (S43) that activates the second feature amount detection unit when the collation result of the first feature amount collation unit exceeds the first reference.

  More preferably, the processing means repeatedly determines whether the collation result of the second feature amount collating means exceeds the second reference (S59), and the discrimination result of the discrimination means is a negative to positive result Change means (S63, S15) for changing the image processing mode when updated.

  More preferably, an imaging means (16) having an imaging surface for capturing the scene and repeatedly outputting the scene image, and a creation means for creating a designated image based on the scene image output from the imaging means (20, 34), and the change target of the change means includes the adjustment accuracy of the quality of the object scene image output from the imaging means.

  Preferably, it further includes update means (S47, S51, S53) for repeatedly updating the positions and / or sizes of the plurality of collation areas prior to the change processing by the change means.

  Preferably, the specific object image corresponds to an animal face image.

  An image processing program according to the present invention holds a feature amount of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to a specific object image in a processor (26) of the image processing device (10). (44), detection steps (S39, S55) for detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image, and holding the feature amounts detected by the detection step A matching step (S41, S57) for matching with the feature value held by the step and a processing step (S31, S59, S63, S15 to S29) for executing image processing in a different manner depending on the matching result of the matching step are executed. This is an image processing program.

  An image processing method according to the present invention is an image processing method executed by an image processing device (10), and calculates feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to a specific object image. It is detected by the holding step (44) for holding, the detecting step (S39, S55) for detecting feature amounts of a plurality of partial images respectively corresponding to the plurality of collation areas allocated in a nested manner on the designated image, and the detecting step. A collation step (S41, S57) for collating the feature quantity with the feature quantity held by the holding step, and a processing step (S31, S59, S63, S15 ~) for executing image processing in a different manner depending on the collation result of the collation step S29).

  An external control program according to the present invention is an external control program supplied to an image processing device (10) including a processor (26) that executes processing according to an internal control program stored in a memory (44), and a specific object image A holding step (44) for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges allocated in a nested manner, and a plurality of matching areas respectively corresponding to a plurality of matching areas nested in a designated image Detection steps for detecting feature amounts of partial images (S39, S55), collation steps for collating the feature amounts detected by the detection step with the feature amounts held by the holding step (S41, S57), and collation results of the collation step Externally to cause the processor to execute processing steps (S31, S59, S63, S15 to S29) for executing image processing in different modes depending on the internal control program. Is your program.

  An image processing apparatus (10) according to the present invention executes a process according to a receiving means (50) for receiving an external control program, and an external control program received by the receiving means and an internal control program stored in a memory (44). An image processing apparatus (10) comprising a processor (26) for holding an external control program for holding feature amounts of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to a specific object image Step (44), detection steps (S39, S55) for detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on the designated image, and feature amounts detected by the detection step A collation step (S41, S57) for collating with the feature value held by the holding step, and a processing step for executing image processing in a different manner depending on the collation result of the collation step. Flop (S31, S59, S63, S15 ~ S29) to correspond to the internal control program in cooperation with a program to be executed.

  The feature amounts held by the holding unit correspond to the feature amounts of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image. The feature amount detected by the detection unit corresponds to the feature amount of a plurality of partial images respectively belonging to a plurality of collation areas allocated in a nested manner on the designated image. The mode of image processing executed by the processing unit differs depending on the result of collating these feature amounts. Thus, the operating performance is improved.

  The above object, other objects, features and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

It is a block diagram which shows the basic composition of one Example of this invention. It is a block diagram which shows the structure of one Example of this invention. (A) is an illustrative view showing an example of a configuration of a pet face dictionary referred to in FIG. 2 embodiment, and (B) is an illustrative view showing an example of a configuration of an external pet face dictionary referred to in FIG. 2 embodiment. It is. It is an illustration figure which shows an example of the dictionary image displayed on the monitor screen. It is an illustration figure which shows an example of the state which allocated the evaluation area to the imaging surface. FIG. 3 is an illustrative view showing one example of a configuration of a register referred to in the embodiment in FIG. 2; It is an illustration figure which shows an example of the face detection frame used in a pet face detection task. It is an illustration figure which shows a part of face detection process in a pet face detection task. It is an illustration figure which shows an example of the image showing the animal caught in the pet face detection task. It is an illustration figure which shows an example of the face frame displayed on the monitor screen. It is a flowchart which shows a part of operation | movement of CPU applied to the FIG. 2 Example. It is a flowchart which shows a part of other operation | movement of CPU applied to the FIG. 2 Example. FIG. 11 is a flowchart showing still another portion of behavior of the CPU applied to the embodiment in FIG. 2; FIG. 10 is a flowchart showing yet another portion of behavior of the CPU applied to the embodiment in FIG. 2; It is a flowchart which shows a part of other operation | movement of CPU applied to the FIG. 2 Example. It is a flowchart which shows a part of operation | movement of CPU applied to another Example. It is an illustration figure which shows an example of the image showing the animal caught in the pet face detection task of FIG. 16 Example. It is a block diagram which shows the structure of the other Example of this invention.

Embodiments of the present invention will be described below with reference to the drawings.
[Basic configuration]

Referring to FIG. 1, the image processing apparatus of this embodiment is basically configured as follows. The holding unit 1 holds feature amounts of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image. The detecting means 2 detects feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on the designated image. The collating unit 3 collates the feature amount detected by the detecting unit 2 with the feature amount held by the holding unit 1. The processing unit 4 performs image processing in a different manner depending on the collation result of the collation unit 3.
[Example]

  Referring to FIG. 2, the digital camera 10 of this embodiment stores a pet face dictionary DC1 and an outer shape pet face dictionary DC2 in a flash memory 44. The pet face dictionary DC1 and the external pet face dictionary DC2 are prepared for searching for face images of animals appearing in the scene. Referring to FIG. 3A, the pet face dictionary DC1 stores one or more dictionary image data representing the characteristics of the animal's face. The dictionary image data of the pet face dictionary DC1 corresponds to the region of the inner part of the animal's face including eyes, nose and mouth. With reference to FIG. 3 (B), the external pet face dictionary DC2 stores dictionary image data corresponding to the pet face dictionary DC1. The dictionary image data of the external pet face dictionary DC2 includes an area of dictionary image data of the pet face dictionary DC1, and further corresponds to an area including an outer portion of an animal face such as an ear.

  When the power is turned on, the CPU 26 reads out and reads out the dictionary image data stored in the outer pet face dictionary DC2 from the flash memory 44 under the imaging task so that the operator can select an animal to be searched. The dictionary image data is developed in the display image area 32 b of the SDRAM 32. The LCD driver 36 reads the developed dictionary image data through the memory control circuit 30 and drives the LCD monitor 38 based on the read dictionary image data.

  Therefore, when the external pet face dictionary DC2 is prepared as shown in FIG. 3B, two dictionary images representing cats and dogs are displayed on the LCD monitor 38 as shown in FIG.

  When a selection operation for selecting any one of the displayed dictionary images is performed, the CPU 26 reads out a feature amount corresponding to the selected dictionary image from the pet face dictionary DC1 and the pet face dictionary DC2. When the dictionary image representing the cat is selected in the example of FIG. 4, the feature amount of the cat's face is read from the pet dictionary DC1 and the external pet face dictionary DC2.

  Referring to FIG. 2, the digital camera 10 of this embodiment includes a focus lens 12 and an aperture unit 14 driven by drivers 18a and 18b, respectively. The optical image of the object scene that has passed through these members is irradiated onto the imaging surface of the image sensor 16 and subjected to photoelectric conversion. As a result, a charge representing the object scene image is generated.

  When the reading of the feature values from the pet dictionary DC1 and the outer pet face dictionary DC2 is completed, the CPU 26 instructs the driver 18c to repeat the exposure operation and the charge reading operation in order to start the moving image capturing process under the imaging task. In response to a vertical synchronization signal Vsync periodically generated from an SG (Signal Generator) (not shown), the driver 18c exposes the imaging surface and reads out the charges generated on the imaging surface in a raster scanning manner. From the image sensor 16, raw image data based on the read charges is periodically output.

  The preprocessing circuit 20 performs processing such as digital clamping, pixel defect correction, and gain control on the raw image data output from the image sensor 16. The raw image data subjected to these processes is written into the raw image area 32 a of the SDRAM 32 through the memory control circuit 30.

  The post-processing circuit 34 reads the raw image data stored in the raw image area 32a through the memory control circuit 30, and performs processing such as color separation processing, white balance adjustment processing, and YUV conversion processing on the read raw image data. , Display image data and search image data according to the YUV format are individually created. The display image data is written into the display image area 32 b of the SDRAM 32 by the memory control circuit 30. The search image data is written into the search image area 32 c of the SDRAM 32 by the memory control circuit 30.

  The LCD driver 36 repeatedly reads the display image data stored in the display image area 32b through the memory control circuit 30, and drives the LCD monitor 38 based on the read image data. As a result, a real-time moving image (through image) of the object scene is displayed on the monitor screen. Further, the search image data is repeatedly written in the search image area 32c.

  Referring to FIG. 5, an evaluation area EVA is allocated at the center of the imaging surface. The evaluation area EVA is divided into 16 in each of the horizontal direction and the vertical direction, and 256 divided areas form the evaluation area EVA. In addition to the processing described above, the preprocessing circuit 20 executes simple RGB conversion processing that simply converts raw image data into RGB data.

  The AE evaluation circuit 22 integrates RGB data belonging to the evaluation area EVA among the RGB data generated by the preprocessing circuit 20 every time the vertical synchronization signal Vsync is generated. As a result, 256 integral values, that is, 256 AE evaluation values, are output from the AE evaluation circuit 22 in response to the vertical synchronization signal Vsync.

  The AF evaluation circuit 24 extracts high-frequency components of RGB data belonging to the same evaluation area EVA from the RGB data output from the preprocessing circuit 20, and the vertical synchronization signal Vsync is generated from the extracted high-frequency components. Integrate every time. As a result, 256 integral values, that is, 256 AF evaluation values, are output from the AF evaluation circuit 24 in response to the vertical synchronization signal Vsync.

  The CPU 26 also searches for an animal face image from the search image data stored in the search image area 32c under a pet face detection task executed in parallel with the imaging task. The searched face image is an image that matches the dictionary image selected by the selection operation. For such a pet face detection task, a register RGST shown in FIG. 6 and a plurality of face detection frames FD, FD, FD,... Shown in FIG.

  Each time the vertical synchronization signal Vsync is generated, the face detection frame FD moves on the search image area 32c in a raster scanning manner corresponding to the evaluation area EVA (see FIG. 8). The size of the face detection frame FD is reduced in increments of “5” from “200” to “20” every time raster scanning ends.

  The CPU 26 reads the image data belonging to the face detection frame FD from the search image area 32c through the memory control circuit 30, and calculates the feature amount of the read image data. The calculated feature amount is collated with the feature amount of the dictionary image of the pet face dictionary DC1 read out earlier. When the matching degree exceeds the reference value REF1, the CPU 26 reads the image data belonging to the outer shape detection frame FDW from the search image area 32c through the memory control circuit 30, and calculates the feature amount of the read image data.

  Referring to FIG. 9, the outer shape detection frame FDW is arranged so as to include a region belonging to the current face detection frame FD and a further outer region, and the current face detection frame FD is allocated in a nested manner. The The position and size of the outer shape detection frame FDW are determined based on the current position and size of the face detection frame FD and the dictionary image of the outer shape pet face dictionary DC2 corresponding to the dictionary image to be collated.

  The calculated feature amount is collated with the feature amount of the dictionary image of the outer shape pet face dictionary DC2 read out earlier. When the matching degree exceeds the reference value REF2, the current position and size of the outer shape detection frame FDW are determined as the size and position of the face image and registered in the register RGST. When the registration in the register RGST is completed, the flag FLGpet is updated from “0” to “1”.

  In addition, since the detection accuracy of the inner part of the face is ensured by collation with the pet face dictionary DC1, in collation with the external pet face dictionary DC2, there is an error of an animal whose outline of the face such as an ear shape is greatly different. It suffices if detection can be avoided. Therefore, the reference value REF2 used in the matching process with the external pet face dictionary DC2 is a threshold set lower than the reference value REF1 used in the matching process with the pet face dictionary DC1 dictionary image.

  Under the imaging task, when the flag FLGpet indicates “0”, the CPU 26 executes a simple AE process based on the output from the AE evaluation circuit 22 under the imaging task, and calculates an appropriate EV value. The simple AE process is executed in parallel with the moving image capturing process, and the aperture amount and the exposure time that define the calculated appropriate EV value are set in the drivers 18b and 18c, respectively. As a result, the brightness of the through image is appropriately adjusted.

  When the flag FLGpet is updated to “1”, the CPU 26 refers to the registered contents of the register RGST and requests the graphic generator 46 to display the face frame KF. The graphic generator 46 outputs graphic information representing the face frame KF to the LCD driver 36. The face frame KF is displayed on the LCD monitor 38 in a manner that matches the position and size of the face image determined under the pet face detection task.

  Therefore, when the cat CT1 is captured in the scene with the cat dictionary image selected, the face frame KF is displayed on the LCD monitor 38 as shown in FIG.

  When the flag FLGpet is updated to “1”, the CPU 26 also uses the register RGST among the 256 AE evaluation values output from the AE evaluation circuit 22 and the 256 AF evaluation values output from the AF evaluation circuit 24. AE evaluation value and AF evaluation value respectively corresponding to the position of the face image registered in (1) are extracted.

  The CPU 26 executes a strict AE process based on a part of the extracted AE evaluation values. The aperture amount and the exposure time that define the optimum EV value calculated by the strict AE process are set in the drivers 18b and 18c, respectively. As a result, the brightness of the through image is adjusted to a brightness focused on a part of the object scene corresponding to the position of the animal face image.

  When the strict AE process is completed, the CPU 26 executes an AF process based on the extracted partial AF evaluation values according to the set adjustment criterion. As a result, the focus lens 12 is arranged at a focal point that focuses on a part of the object scene corresponding to the position of the animal face image, and the sharpness of the through image is improved.

  When the AF process is completed, the CPU 26 executes a still image capturing process and a recording process under the imaging task. One frame of image data immediately after the AF processing is completed is captured into the still image area 32d by the still image capturing processing. The captured one-frame image data is read from the still image area 32d by the I / F 40 activated in association with the recording process, and is recorded on the recording medium 42 in a file format. The face frame KF1 is not displayed after the recording process is completed.

  The CPU 26 executes a plurality of tasks including the imaging task shown in FIGS. 11 to 12 and the pet face detection task shown in FIGS. 13 to 15 in parallel. Control programs corresponding to these tasks are stored in the flash memory 44.

  Referring to FIG. 11, in step S <b> 1, dictionary image data stored in outline pet face dictionary DC <b> 2 is read from flash memory 44, and the read dictionary image data is developed in display image area 32 b of SDRAM 32. As a result, one or more dictionary images are displayed on the LCD monitor 38. In step S3, it is determined whether or not a selection operation for selecting any one of the displayed dictionary images has been performed. When the determination result is updated from NO to YES, the process proceeds to step S5, and the feature amount corresponding to the selected dictionary image is read from the pet face dictionary DC1 and the external pet face dictionary DC2.

  In step S7, a moving image capturing process is executed, and in step S9, the entire evaluation area EVA is set as a search area. In step S11, the maximum size SZmax is set to “200” and the minimum SZmin is set to “20” to define a variable range of the size of the face detection frame FD. When the process of step S11 is completed, the pet face detection task is activated in step S13.

  The flag FLGpet is initially set to “0” under the pet face detection task, and is set to “1” when a face image matching the dictionary image of the pet face dictionary DC1 and the dictionary image of the external pet face dictionary DC2 is found. Updated. In step S15, it is determined whether or not such a flag FLGpet indicates “1”. As long as the determination result is NO, the simple AE process is repeatedly executed in step S17. The brightness of the through image is appropriately adjusted by the simple AE process.

  When the determination result is updated from NO to YES, the process proceeds to step S19, and the graphic generator 46 is requested to display the face frame KF with reference to the registered contents of the register RGST. The graphic generator 46 outputs graphic image data representing the face frame KF to the LCD driver 36. The face frame KF is displayed on the LCD monitor 38 so as to surround the detected face image.

  In step S21, an AE evaluation value corresponding to each position of the face image registered in the register RGST is extracted from the 256 AE evaluation values output from the AE evaluation circuit 22, and a part of the extracted AE evaluations is extracted. A strict AE process based on the value is executed. As a result, the brightness of the through image is adjusted to a brightness focused on a part of the object scene corresponding to the position of the animal face image.

  In step S23, AF evaluation values respectively corresponding to the positions of the face images registered in the register RGST are extracted from the 256 AF evaluation values output from the AF evaluation circuit 24, and a part of the extracted AF evaluations is extracted. The AF process based on the value is executed according to the set adjustment criterion. As a result, the focus lens 12 is arranged at a focal point that focuses on a part of the object scene corresponding to the position of the animal face image, and the sharpness of the through image is improved.

  In step S25, a still image capturing process is executed, and in step S27, a recording process is executed. One frame of image data immediately after the AF processing is completed is captured into the still image area 32d by the still image capturing processing. The captured one-frame image data is recorded on the recording medium 42 by a recording process. When the recording process is completed, the graphic generator 46 is requested to hide the face frame KF in step S29, and then the process returns to step S9.

  Referring to FIG. 13, in step S31, the flag FLGpet is set to “0”, and in step S33, it is determined whether or not the vertical synchronization signal Vsync is generated. When the determination result is updated from NO to YES, the size of the face detection frame FD is set to “SZmax” in step S35, and the face detection frame FD is arranged in the upper left position of the search area in step S37. In step S39, a part of the search image data belonging to the face detection frame FD is read from the search image area 32c, and the feature amount of the read search image data is calculated.

  In step S41, the calculated feature amount is collated with the feature amount of the dictionary image data read from the pet face dictionary DC1, and in step S43, it is determined whether or not the collation degree exceeds the reference value REF1. If the determination result is NO, the process proceeds to step S45, and if the determination result is YES, the process proceeds to step S55.

  In step S45, it is determined whether or not the face detection frame FD has reached the lower right position of the search area. If the determination result is NO, the face detection frame FD is moved in the raster direction by a predetermined amount in step S47, and then the process returns to step S39. If the determination result is YES, it is determined in a step S49 whether or not the size of the face detection frame FD is “SZmin” or less. If the decision result in the step S49 is NO, the size of the face detection frame FD is reduced by “5” in a step S51, the face detection frame FD is arranged in the upper left position of the search area in a step S53, and then the process proceeds to a step S39. Return. If the determination result of step S49 is YES, it will return to step S33 as it is.

  In step S55, image data belonging to the outer shape detection frame FDW is read from the search image area 32c through the memory control circuit 30, and a feature amount of the read image data is calculated. The outer shape detection frame FDW includes an area belonging to the current face detection frame FD and a further outer area, and is arranged so that the current face detection frame FD is allocated in a nested manner. The position and size of the outer shape detection frame FDW are determined based on the current position and size of the face detection frame FD and the dictionary image of the outer shape pet face dictionary DC2 corresponding to the dictionary image to be collated.

  In step S57, the calculated feature amount is collated with the feature amount of the dictionary image data read from the external pet face dictionary DC2, and in step S59, it is determined whether or not the collation degree exceeds the reference value REF2. If a determination result is NO, it will return to Step S45, and if a determination result is YES, it will progress to Step S61.

  In step S61, the current position and size of the outer shape detection frame FDW are determined as the size and position of the face image and registered in the register RGST. When the process of step S61 is completed, the flag FLGpet is set to “1” in step S63, and then the process ends.

  As can be understood from the above description, the flash memory 44 holds the feature amounts of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image. The CPU 26 detects feature quantities of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on the designated image, and collates the detected feature quantities with the feature quantities held by the flash memory 44. . The CPU 26 also executes image processing in a different manner depending on the collation result.

  The feature values held by the flash memory 44 correspond to the feature values of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image. The detected feature amount corresponds to the feature amount of a plurality of partial images respectively belonging to a plurality of collation areas allocated in a nested manner on the designated image. The mode of image processing executed by the CPU 26 differs depending on the result of collating these feature amounts. Thus, the operating performance is improved.

  In this embodiment, the feature of the image data belonging to the contour detection frame FDW when the matching degree between the feature amount of the image data belonging to the face detection frame FD and the feature amount of the pet face dictionary DC1 exceeds the reference value REF1. The amount is read out and collated with the feature amount of the external pet face dictionary DC2. However, the feature amount of the image data belonging to the face detection frame FD and the feature amount of the external pet face dictionary DC2 may be collated first.

  In this case, steps S71 to S73 of FIG. 16 are executed instead of steps S41 to S43 of FIG. 13, and steps S75 to S79 of FIG. 16 are executed instead of steps S55 to S59 of FIG. .

  In step S71, the calculated feature amount is collated with the feature amount of the dictionary image data read from the outer pet face dictionary DC2, and in step S73, it is determined whether or not the collation degree exceeds the reference value REF2. If the determination result is NO, the process proceeds to step S45, and if the determination result is YES, the process proceeds to step S75.

  In step S75, the image data belonging to the inner shape detection frame FDN is read from the search image area 32c through the memory control circuit 30, and the feature amount of the read image data is calculated. Referring to FIG. 17, the inner shape detection frame FDN is arranged so as to be assigned in a nested manner inside the face detection frame FD. The position and size of the inner shape detection frame FDN are determined based on the current position and size of the face detection frame FD and the dictionary image of the pet face dictionary DC1 corresponding to the dictionary image to be collated.

  In step S77, the calculated feature amount is collated with the feature amount of the dictionary image data read from the pet face dictionary DC1, and in step S79, it is determined whether or not the collation degree exceeds the reference value REF1. If a determination result is NO, it will return to Step S45, and if a determination result is YES, it will progress to Step S61.

  Further, in this case, scanning using the face detection frame FD and calculation of the feature amount are executed on the low-resolution image, and the arrangement of the inner shape detection frame FDN and the reading of the image data belonging to the inner shape detection frame FDN are read with high resolution. You may make it perform on an image.

  In this embodiment, the multitask OS and control programs corresponding to a plurality of tasks executed thereby are stored in the flash memory 44 in advance. However, a communication I / F 50 for connecting to an external server is provided in the digital camera 10 in the manner shown in FIG. 18, and some control programs are prepared as internal control programs in the flash memory 44 from the beginning, while other parts are prepared. These control programs may be acquired from an external server as an external control program. In this case, the above-described operation is realized by cooperation of the internal control program and the external control program.

  In this embodiment, the process executed by the CPU 36 is divided into an imaging task shown in FIGS. 11 to 12 and a pet face detection task shown in FIGS. 13 to 15. However, these tasks may be further divided into a plurality of small tasks, and some of the divided small tasks may be integrated. Further, when the transfer task is divided into a plurality of small tasks, all or part of the transfer task may be acquired from an external server.

  In this embodiment, the digital still camera has been described. However, the present invention can also be applied to a digital video camera, a mobile phone terminal, a smartphone, or the like.

DESCRIPTION OF SYMBOLS 10 ... Digital camera 16 ... Image sensor 22 ... AE evaluation circuit 24 ... AF evaluation circuit 26 ... CPU
32 ... SDRAM
44 ... Flash memory

Claims (12)

Holding means for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image;
Detecting means for detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image;
Image processing comprising: a collating unit that collates a feature amount detected by the detecting unit with a feature amount held by the holding unit; and a processing unit that executes image processing in a different manner depending on a collation result of the collating unit apparatus. The detecting means detects a first feature quantity detecting means for detecting a first partial feature quantity corresponding to a part of the plurality of partial images, and a second partial feature quantity corresponding to another part of the plurality of partial images. A second feature amount detecting means for detecting
The collation means includes a first feature quantity collation means for collating the first partial feature quantity detected by the first feature quantity detection means with a part of the feature quantity held by the holding means, and the second feature quantity. The image processing apparatus according to claim 1, further comprising a second feature amount collating unit that collates the second partial feature amount detected by the detecting unit with another part of the feature amount held by the holding unit. The plurality of collation areas include a first collation area having a large size and a second collation area having a small size;
The first partial feature amount includes a feature amount corresponding to one of the first collation area and the second collation area,
The image processing apparatus according to claim 2, wherein the second partial feature amount includes a feature amount corresponding to the other of the first collation area and the second collation area.   The image processing apparatus according to claim 2, further comprising an activation unit that activates the second feature amount detection unit when a collation result of the first feature amount collation unit exceeds a first reference.   The processing means repeatedly determines whether or not the collation result of the second feature amount collating means exceeds a second reference, and the discrimination result of the discrimination means has been updated from a negative to a positive result 5. The image processing apparatus according to claim 4, further comprising changing means for changing an image processing mode. An imaging unit that has an imaging surface that captures the object scene, and that repeatedly outputs the object scene image; and a creation unit that creates the designated image based on the object scene image output from the imaging unit;
The image processing apparatus according to claim 5, wherein the change target of the change unit includes an adjustment accuracy of the quality of the object scene image output from the imaging unit.   The image processing apparatus according to claim 5, further comprising an updating unit that repeatedly updates positions and / or sizes of the plurality of collation areas prior to the changing process by the changing unit.   The image processing apparatus according to claim 1, wherein the specific object image corresponds to a face image of an animal. In the processor of the image processing device,
Holding step for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image;
A detection step of detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image;
A collation step for collating the feature amount detected by the detection step with the feature amount held by the holding step, and a processing step for executing image processing in a different manner depending on the collation result of the collation step , Image processing program. An image processing method executed by an image processing apparatus,
Holding step for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image;
A detection step of detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image;
Image processing comprising: a collation step for collating the feature quantity detected by the detection step with the feature quantity held by the holding step; and a processing step for executing image processing in a different manner depending on the collation result of the collation step Method. An external control program supplied to an image processing apparatus including a processor that executes processing according to an internal control program stored in a memory,
Holding step for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image;
A detection step of detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image;
The internal control program includes a collation step for collating the feature quantity detected by the detection step with the feature quantity held by the holding step, and a processing step for executing image processing in a different manner depending on the collation result of the collation step An external control program for causing the processor to execute in cooperation with the program. An image processing apparatus comprising: a receiving unit that receives an external control program; and a processor that executes processing according to the external control program received by the receiving unit and an internal control program stored in a memory,
The external control program is
Holding step for holding feature quantities of a plurality of object images respectively corresponding to a plurality of ranges assigned in a nested manner to the specific object image;
A detection step of detecting feature amounts of a plurality of partial images respectively corresponding to a plurality of collation areas allocated in a nested manner on a designated image;
The internal control program includes a collation step for collating the feature quantity detected by the detection step with the feature quantity held by the holding step, and a processing step for executing image processing in a different manner depending on the collation result of the collation step An image processing apparatus corresponding to a program executed in cooperation with the computer.

Images