JP2010062814A - Image processing apparatus and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a user-friendly image processing apparatus capable of properly conducting an image related processing in view of the state of an object. <P>SOLUTION: An image capturing apparatus 100 includes: a built-in memory 7 for storing a state table related to the current smile degree and sensitivity level of a person's face concerning the decision criteria for the implementation of an automatic photographing process; a specifying processing for specifying the smile degree of the person's face in the newly obtained image; and a CPU (central processing unit) 8 for conducting a change processing for changing the correspondence between the sensitivity level of the state table and the current smile degree. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and a program.

  Conventionally, a digital camera that automatically captures an object is known (see, for example, Patent Document 1). Specifically, in this digital camera, when it is determined that a predetermined condition is satisfied by detecting the facial expression of the object and the orientation of the eyes / face, the shooting / recording operation is automatically performed. Yes.

In addition, when storing multiple images in the memory, it is possible to easily search for images similar to the desired image by classifying images using facial expressions in the images. Digital cameras are also known (see, for example, Patent Document 2).
JP 2001-51338 A JP 2005-234686 A

By the way, when automatically shooting an object, it is possible to switch and set the criteria for determining the facial expression of the object, but the setting of the level is determined uniformly regardless of the shooting object, There are problems such as poor usability.
This problem is the same when image search processing is performed using facial expressions.

  Accordingly, an object of the present invention is to provide an easy-to-use image processing apparatus and program that can appropriately perform image-related processing in consideration of the state of an object.

In order to solve the above problem, an image processing apparatus according to claim 1 is provided.
A level designating unit that designates a sensitivity level related to the execution of the image-related processing, and a state table that associates the reference state of the target object and the sensitivity level related to the determination criterion as to whether to execute the image-related processing are stored. Table storage means, specifying means for specifying the state of the object in the newly acquired image, and the sensitivity level and the object of the state table based on the state of the object specified by the specifying means And changing means for changing the correspondence relationship with the reference state of the object.

The invention according to claim 2 is the image processing apparatus according to claim 1,
And a determination unit for comparing and determining the state of the object specified by the specifying unit, the sensitivity level specified by the level specifying unit, and a reference state of the object associated with the state table. And the changing means corresponds to the sensitivity level of the state table and the reference state of the object based on the state of the object determined by the determining means to exceed the reference state of the object. It is characterized by changing the relationship.

The invention according to claim 3 is the image processing apparatus according to claim 2,
The automatic photographing control further comprising: an imaging unit that images a subject as the object; and an automatic photographing control unit that controls an automatic photographing process in which the subject is automatically imaged by the imaging unit as the image-related processing. The means is characterized by controlling whether or not the imaging means automatically images the subject according to a determination result by the determination means.

The invention according to claim 4 is the image processing apparatus according to claim 2,
Image storage means for storing a plurality of images, and image search for performing a search process for searching for a desired image related to the object among the plurality of images stored in the image storage means as the image-related processing And the image search means controls whether or not to specify any one of the plurality of images as the desired image according to a determination result by the determination means. It is a feature.

The invention according to claim 5 is the image processing apparatus according to any one of claims 2 to 4,
In the state table, each of the plurality of sensitivity levels is associated with each of the reference states of the plurality of objects, and the determination unit is any one of the plurality of sensitivity levels specified by the level specifying unit. One sensitivity level and a reference state of an object associated with the state table are compared with a state of the object specified by the specifying unit.

The invention according to claim 6 is the image processing apparatus according to any one of claims 1 to 5,
The apparatus further comprises past state storage means for storing a plurality of past states of the object identified so far by the specifying means, and the changing means includes past of the plurality of objects stored in the past state storage means. The correspondence relationship between the sensitivity level of the state table and the reference state of the object is changed based on the past states of the predetermined number of objects from the newest among the states.

The invention according to claim 7 is the image processing apparatus according to any one of claims 1 to 6,
The object is a person.

The invention according to claim 8 is the image processing apparatus according to any one of claims 1 to 6,
The object is a human face.

The invention according to claim 9 is the image processing apparatus according to claim 8,
In the state table, each of the plurality of sensitivity levels is associated with each of the reference states of the plurality of objects, and the reference state of the object is defined based on the facial expression of the person. It is a feature.

The invention according to claim 10 is the image processing apparatus according to any one of claims 1 to 9,
A plurality of the state tables are provided according to the type of the object.

The program of the invention described in claim 11 is
A level designating unit that designates a sensitivity level related to the execution of the image-related processing, and a state table that associates the reference state of the target object and the sensitivity level related to the determination criterion as to whether to execute the image-related processing are stored. A table storage means, and a computer of an image processing apparatus,
Identification means for specifying the state of the object in the newly acquired image, and correspondence between the sensitivity level of the state table and the reference state of the object based on the state of the object specified by the specifying means It is characterized by functioning as a changing means for changing the relationship.

  According to the present invention, it is possible to appropriately perform image-related processing in consideration of the state of an object, and it is possible to improve the usability of the image processing apparatus.

Hereinafter, specific embodiments of the present invention will be described with reference to the drawings. However, the scope of the invention is not limited to the illustrated examples.
FIG. 1 is a block diagram illustrating a schematic configuration of an imaging apparatus 100 according to an embodiment to which the present invention is applied.

When the state of the subject imaged by the imaging unit 1 satisfies a predetermined condition, the imaging apparatus 100 according to the present embodiment performs the automatic imaging process for recording and saving the image data related to the subject according to the processing result. The current smile degree in the state table T1 related to the execution determination of the automatic photographing process is updated.
Specifically, as illustrated in FIG. 1, the imaging device 100 includes an imaging unit 1, a recording medium control unit 2, a recording medium 3, a display unit 4, an operation input unit 5, a buffer memory 6, A built-in memory 7 and a CPU 8 are provided.

The imaging unit 1 generates an image frame by imaging one scene as an imaging unit. Specifically, although not shown, the imaging unit 1 includes, for example, an imaging lens and a CCD (Charge Coupled Device) or CMOS (Complementary Metal-Metal) that converts a subject image that has passed through the imaging lens into a two-dimensional image signal. An electronic imaging unit composed of oxide semiconductor, etc., and an imaging control unit that controls the electronic imaging unit and controls AE (automatic exposure processing), AF (automatic focusing processing), AWB (automatic white balance), etc. ing.
The imaging control unit causes the electronic imaging unit to image the subject with a predetermined exposure time, and reads an image frame from the imaging area of the electronic imaging unit. Thereafter, the imaging control unit transfers the read image frame to the buffer memory 6 and stores it.

  The recording medium control unit 2 controls storage of the image file on the recording medium 3 and reading of the image file from the recording medium 3.

  The recording medium 3 is configured by, for example, a card-type nonvolatile memory (flash memory), a hard disk, or the like.

  Although not shown, the display unit 4 includes, for example, an image display unit such as a liquid crystal display and a display control unit that controls display of an image frame on the image display unit. The display unit 4 displays the live view image while sequentially updating the image frames captured by the imaging unit 1 at a predetermined frame rate.

  The operation input unit 5 is for performing a predetermined operation of the imaging apparatus 100. Specifically, although not shown, the operation input unit 5 includes a shutter button for instructing recording of a subject by the imaging unit 1, up / down / left / right cursor buttons for selecting various operation modes and various items, and these cursors. A determination button or the like for instructing determination of an operation mode or an item selected by the button is provided.

Examples of the operation mode include a still image shooting mode for shooting a still image, and an automatic shooting mode for automatically recording and saving desired image data similar to the shooting target generated by the imaging unit 1.
When the user selects a predetermined operation mode (for example, an automatic shooting mode), an instruction to set the operation mode is output to the CPU 8 via an input circuit (not shown). When a setting instruction is input, the CPU 8 controls each unit and performs processing according to the operation mode.

In addition, the operation input unit 5 designates any sensitivity level desired by the user among a plurality of sensitivity levels related to determination as to whether or not to perform automatic shooting processing (image-related processing).
As a method for specifying the sensitivity level, for example, any one of levels 1 to 3 displayed on the sensitivity specification screen (not shown) may be specified, or a desired sensitivity level value may be input. You may make it do. As the sensitivity level is smaller, the sensitivity is lower. Level 1 has the lowest sensitivity, and level 3 has the highest sensitivity.
When a predetermined sensitivity level (for example, level 1) is selected by the user, an instruction to set the sensitivity level is output to the CPU 8 via an input circuit (not shown). When a setting instruction is input, the CPU 8 controls each unit and performs processing according to the sensitivity level.
Here, the operation input unit 5 constitutes a level instruction means for instructing a sensitivity level related to execution of the automatic photographing process.

  The buffer memory 6 is composed of, for example, a flash memory and temporarily stores data processed by the CPU 8.

  The CPU 8 controls each part of the imaging device 100. Specifically, the CPU 8 performs various control operations according to various processing programs for the imaging device 100 stored in a program memory (described later) of the built-in memory 7.

The built-in memory 7 stores, as a table storage unit, a state table T1 in which the current smile level (reference state) of the person's face related to the determination criterion for whether or not to execute the automatic photographing process is associated with the sensitivity level. (See FIG. 2).
As shown in FIG. 2, the state table T1 quantifies a person ID for identifying a person such as Mr. A, Mr. B, and Mr. C, facial feature data of each person's face, and past smile level. The past smile degree history and the current smile degree (reference state of the object) obtained by quantifying the current smile degree for each level are registered in association with each other. The current smile level is a numerical value based on the smile level determination template T2 (see FIG. 3) stored in the built-in memory 7. Here, the smile degree determination template T2 is defined in five stages so that, for example, a big smile is a smile degree 100, and the smile degree gradually decreases as the amount of laughter decreases. For example, in the case of Mr. A, level 1 has a smile level of 50, level 2 has a smile level of 70, and level 3 has a smile level of 100. In the case of Mr. B, level 1 has a smile level of 10, level 2 has a smile level of 30, and level 3 has a smile level of 50. In the case of Mr. C, level 1 has a smile level of 30, level 2 has a smile level of 50, and level 3 has a smile level of 70.
Here, the built-in memory 7 constitutes past state storage means for storing a plurality of past smile degrees (the past state of the object) of the person's face specified by the specifying process (described later).

The built-in memory 7 includes a program memory, and stores various programs and data necessary for the operation of the CPU 8.
This program includes a recognition processing routine, a specific processing routine, a determination processing routine, an automatic photographing control processing routine, and a change processing routine which will be described later.
Here, the routine is a series of instructions that constitute a part of a computer program and have a certain function.

The recognition processing routine is a program part for causing the CPU 8 to function as recognition means. That is, the recognition processing routine includes a command group for causing the CPU 8 to realize a function related to the recognition processing for recognizing the face of a person in a newly acquired image.
Specifically, after this recognition processing routine, the CPU 8 newly acquires each of a plurality of image data sequentially generated by the imaging unit 1, and then a person (for example, Mr. A) in the image related to the image data. A face recognition process for detecting and identifying the face is performed.
Here, the face recognition process refers to, for example, the facial feature data associated with the person ID in the state table T1, the positional relationship of the feature parts corresponding to the eyes, nose, and the like, the area of the skin color region, etc. The person is identified from the face size determined from the above.

The specific process routine is a program part for causing the CPU 8 to function as a specific unit. That is, the specific process routine includes a command group for causing the CPU 8 to realize a function related to the specific process for specifying the face state of the person recognized in the recognition process.
Specifically, according to this specific processing routine, the CPU 8 uses the smile degree determination template T2 to change the smile degree (for example, laughter) from the change state of the coordinates of the face and eyes of the person recognized in the recognition process. Is specified).

  The determination processing routine is a program part for causing the CPU 8 to function as determination means. That is, the determination processing routine stores the smile level of the face of the person specified in the specifying process, the sensitivity level (for example, level 2) specified based on a predetermined operation of the operation input unit 5 by the user, and the state table T1. It includes a group of instructions for causing the CPU 8 to realize a function related to a determination process for comparing and determining the current smile level (for example, the smile level 70 in the case of Mr. A) of the face of the associated person.

The automatic photographing control processing routine is a program part for causing the CPU 8 to function as automatic photographing control means. In other words, the automatic photographing control processing routine includes a group of instructions for causing the CPU 8 to realize a function related to automatic photographing processing in which the image pickup unit 1 automatically picks up an object.
Specifically, the CPU 8 controls whether or not the image data generated by the imaging unit 1 is automatically recorded and stored in the recording medium 3 according to the determination result of the determination process by this automatic shooting control processing routine. To do. For example, the CPU 8 determines that the smile level of the face of the person specified in the specifying process is greater than the current smile level of the face of the person associated with the sensitivity level specified by the user and the state table T1. When the image data related to the determination is acquired and recorded and stored in the recording medium 3, the smile level of the face of the person specified in the specific process is determined to be less than or equal to the current smile level. The image data recording and storage related to the determination is not executed and controlled.

The change processing routine is a program part for causing the CPU 8 to function as a changing means. That is, the change processing routine determines the state based on the smile level of the face of the person specified by the specifying process, in particular, the smile level of the face of the person determined to exceed the current smile level by the determination process. It includes a command group for causing the CPU 8 to realize a function related to table update processing for changing the correspondence between the sensitivity level of the table T1 and the current smile level of the person's face.
Specifically, by this change processing routine, the CPU 8 causes the smile degree “A” of the latest image data registered in the smile degree past history of the state table T1 and the smile degree “B” of the previous image data. ”, The smile level“ C ”of the previous image data and the smile level“ D ”of the previous image data are obtained, and the values of“ A ”to“ D ”are weighted and averaged ( For example, 0.4 × A + 0.3 × B + 0.2 × C + 0.1 × D), and the calculation result is overwritten and saved as the current smile level of level 2. As for the current smile level of levels 1 and 3, the smile level determination template T2 is used to specify the smile level sandwiching the smile level of level 2 and overwrite the specified value as the current smile level of levels 1 and 3. save. That is, the CPU 8 is based on a predetermined number of smile levels from the smile levels of the face of the newest person newly specified by the specifying process among the smile levels registered in the smile level past history of the state table T1. Thus, the correspondence relationship between the sensitivity level of the state table T1 and the current smile level is changed.
Note that the above-described method of weighted average smile level is an example, and is not limited to this.

  4 to 8 are flowcharts for explaining the overall operation of the imaging apparatus 100, and are flowcharts showing the algorithm structure of the program stored in the program memory. Description of specific program codes corresponding to the CPU 8 to be actually used is omitted, but may be designed as appropriate based on this flowchart (algorithm structure).

Next, the main operation of the imaging apparatus 100 will be described with reference to FIG.
FIG. 4 is a flowchart illustrating an example of a main operation performed by the imaging apparatus 100.

As shown in FIG. 4, first, the CPU 8 performs an initialization process for initializing each unit of the imaging apparatus 100 (step S1).
Thereafter, when the CPU 8 is instructed to execute the automatic photographing process based on a predetermined operation of the operation input unit 5 by the user, the CPU 8 controls each part to perform the automatic photographing process (step S2; details will be described later).
After completion of the automatic photographing process, when the CPU 8 is instructed to execute the table update process based on a predetermined operation of the operation input unit 5 by the user, the CPU 8 controls each part to perform the table update process (step S3; details) Later).
When the table update process is completed, the CPU 8 performs the other process when an instruction to perform the other process is given based on a predetermined operation of the operation input unit 5 by the user (step S4).

Next, the automatic photographing process will be described with reference to FIG.
FIG. 5 is a flowchart illustrating an example of an operation related to automatic photographing processing by the imaging apparatus 100.

As shown in FIG. 5, the CPU 8 determines whether or not the automatic shooting mode is set (step S21).
If it is determined that the automatic shooting mode is set (step S21; YES), the CPU 8 determines whether an instruction to change the sensitivity level of the automatic shooting process is input (step S22). If it is determined in step S22 that an instruction to change the sensitivity level is input, that is, for example, an instruction to change the sensitivity from level 2 to level 1 is input (step S22; YES). The CPU 8 performs a process of setting the sensitivity level in accordance with the input sensitivity level change instruction (step S23).

Next, the CPU 8 newly acquires each of the plurality of image data sequentially generated by the imaging unit 1 by the recognition processing routine, displays the live view image on the display unit 4 based on the image data, A face of a person in the image related to the image data is detected (step S24). If the CPU 8 determines that a person's face has been detected from any of the images (step S24; YES), the CPU 8 performs a personal recognition process that recognizes the face and identifies an individual (for example, Mr. A) (step S24). S25).
Also, when it is determined in step S22 that no sensitivity level change instruction has been input (step S22; NO), the CPU 8 shifts the process to step S24.

Thereafter, the CPU 8 determines whether or not the personally recognized face is registered in the state table T1 (step S26).
Note that when a plurality of persons are recognized in the personal recognition in step S25, it may be determined whether only the person at the approximate center of the image is registered in the state table T1 or not. It may be determined whether or not a person is registered in the state table T1.
If it is determined that it is registered in the state table T1 (step S26; YES), the CPU 8 uses the smile degree determination template T2 from the smile state of the face of the person who has been personally recognized by the specific processing routine. Then, the degree of smile (for example, the degree of smile 100 corresponding to a big laugh) is determined and specified (step S27).

Subsequently, the CPU 8 determines the smile level of the face of the person specified in the specifying process, the designated sensitivity level (for example, level 1), and the person associated with the state table T1 by the determination process routine. A comparison is made with the current smile level of the face (for example, smile level 50 in the case of Mr. A), and it is determined whether or not the smile level exceeds the current smile level (step S28).
When a plurality of persons are recognized in the individual recognition in step S25, it may be determined whether or not the current smile level is exceeded only for the person at the approximate center of the image, or for all persons. It may be determined whether or not the current smile level has been exceeded.
If it is determined that the smile level exceeds the current smile level (step S28; YES), the CPU 8 acquires the image data related to the determination and records and stores it in the recording medium 3 by the automatic shooting control process routine ( Step S29).

On the other hand, if it is determined in step S28 that the smile level does not exceed the current smile level (step S28; NO), the CPU 8 executes recording and saving of the image data related to the determination by an automatic shooting control processing routine. Without the control, it is determined whether the user has operated the shutter button of the operation input unit 5 for a predetermined operation to instruct imaging of the subject (step S2A).
Here, when the shutter button is operated for a predetermined time and imaging of the subject is instructed (step S2A; YES), the CPU 8 shifts the processing to step S29, acquires the image data related to the determination, and acquires the recording medium 3 To record.

If it is determined in step S26 that the personally recognized face is not registered in the state table T1 (step S26; NO), the CPU 8 does not register the person related to the personal recognition in the state table T1. A message (for example, “This person is not registered”) is displayed on the display unit 4 for notification (step S2B).
Thereafter, the CPU 8 shifts the processing to step S2A and determines whether or not the shutter button has been operated in a predetermined manner.
In step S2B, after notifying that the status table T1 is not registered, the ID of the unregistered person may be newly registered.

  Also, when it is determined in step S24 that no human face has been detected (step S24; NO), or when it is determined in step S21 that the automatic shooting mode has not been set (step S21). S21; NO), the CPU 8 shifts the process to step S2A and determines whether or not the shutter button has been operated in a predetermined manner.

Next, the table update process will be described with reference to FIG.
FIG. 6 is a flowchart illustrating an example of an operation related to the table update process.

As shown in FIG. 6, the CPU 8 determines whether or not image data has been newly acquired (step S31).
If it is determined that the image is newly acquired (step S31; YES), the CPU 8 detects the face of the person in the image related to the newly acquired image data by the recognition processing routine. If the CPU 8 determines that a person's face has been detected from any of the images (step S32; YES), the CPU 8 performs a personal recognition process for recognizing the face and identifying an individual (for example, Mr. A) (step S32). S33).

  Next, the CPU 8 determines a smile level (for example, a smile level 100 corresponding to a big smile, etc.) using the smile level determination template T2 from the smile state of the face of the person who is personally recognized by the specific processing routine. Specify (step S34). Thereafter, the CPU 8 registers the specified smile degree in the smile degree past history of the state table T1 (step S35).

After that, the CPU 8 performs the change processing routine so that the smile level “A” of the latest image data from the newest one among the plurality of smile levels registered in the smile level past history of the state table T1. ”, The smile level“ B ”of the previous image data, the smile level“ C ”of the previous image data, and the smile level“ D ”of the previous image data are acquired (step S36). .
Subsequently, the CPU 8 calculates the current smile level at the sensitivity level 2 by averaging the values of the smile levels “A” to “D” (step S37).
Then, the CPU 8 specifies the current smile levels of the sensitivity levels 1 and 3 from the current smile levels of the sensitivity level 2 using the smile level determination template T2, and uses the specified values as the current levels of the sensitivity levels 1 to 3. The state table T1 is updated by overwriting as the smile level (step S38).

  If it is determined in step S31 that image data has not been newly acquired (step S31; NO), a human face is detected from the image associated with the newly acquired image data in step S32. If not (step S32; NO), the table update process is terminated.

As described above, according to the imaging apparatus 100 of the present embodiment, the automatic imaging process is performed, and the smile level of the person's face imaged by the imaging unit 1, the sensitivity level desired by the user, and the state table T1 Is compared with the current smile level of the person's face associated with the image, and based on the smile level of the face of the person determined to exceed the current smile level, the execution determination of the automatic shooting process is performed. The correspondence relationship between the current smile level and the sensitivity level in the state table T1 is updated.
That is, when it is determined that the smile level of the person's face imaged by the imaging unit 1 exceeds the current smile level of the state table T1, the imaging apparatus 100 records and saves image data related to the determination. Execute the process. The correspondence between the current smile level and the sensitivity level in the status table T1 based on the past smile level including the smile level of the image data newly recorded and stored in the automatic shooting process registered in the status table T1. Since the relationship is updated, the automatic photographing process can be appropriately performed in consideration of the state of smile of the person in the subsequent execution determination of the automatic photographing process. In other words, when the sensitivity level for execution determination of automatic shooting processing is set to a user-desired level among a plurality of sensitivity levels, execution determination is not performed uniformly by a plurality of persons according to the sensitivity level. The relationship between the current smile level and the sensitivity level in the state table T1 can be internally set in consideration of the smile status of the person, so that a person with little or no change in facial expression Even in such a case, the automatic photographing process can be appropriately performed by determining the automatic photographing condition based on the judgment criterion more suitable for each person without changing the sensitivity level.
In particular, the current smile level and the sensitivity level of the state table T1 in consideration of a predetermined number of smile levels from the newest ones registered in the past smile history of the state table T1, that is, newer changes in the smiles of each person Is automatically set, so if a person with little change in facial expression recently laughs well, the automatic shooting conditions are determined considering the newer change in the person's smile can do.
In this way, automatic photographing processing can be performed more appropriately, and usability of the imaging apparatus 100 can be improved.

  In the state table T1, each of the plurality of sensitivity levels is associated with each of the current smile levels of the plurality of persons, and one of the plurality of sensitivity levels is designated by the user. Since the current smile level of the person associated with is compared with the smile level of the person in the newly acquired image, the sensitivity level can be changed when automatic shooting cannot be performed properly. Therefore, it is possible to provide the imaging device 100 that is more convenient to use.

Further, even when it is determined in step S28 that the smile level does not exceed the current smile level (step S28; NO) and automatic shooting is not executed, in step S2A, a predetermined shutter button is set by the user. Since the subject can be imaged based on the operation and the image data can be recorded and saved in the recording medium 3, the desired subject can be imaged without changing the sensitivity level when automatic photographing cannot be performed properly. It can be done properly.
Furthermore, the correspondence between the current smile level and the sensitivity level in the state table T1 can be updated based on the smile level of the image data newly acquired by imaging the subject. That is, the relationship between the current smile level and the sensitivity level in the state table T1 in consideration of not only the image data acquired by the automatic shooting process but also the smile level of the image data acquired based on the manual shooting instruction by the user. Therefore, it is possible to provide the imaging device 100 that is more convenient to use.

The present invention is not limited to the above-described embodiment, and various improvements and design changes may be made without departing from the spirit of the present invention.
For example, a case where a search process for specifying desired image data similar to a search target from a plurality of image data is performed as the image-related process will be described in Modification 1 below.

<Modification 1>
Hereinafter, an imaging apparatus of Modification 1 will be described with reference to FIGS. 7 and 8.
Note that the imaging apparatus of the first modification has substantially the same configuration as the imaging apparatus 100 of the above-described embodiment except that the search process is performed, and the description thereof is omitted.

  The recording medium 3 stores a plurality of image files as image storage means. Here, the image file may be generated, for example, by imaging an object by the imaging unit 1 or may be transferred from an external device via a predetermined communication unit.

The program stored in the program memory includes an image search processing routine in addition to a recognition processing routine, a specific processing routine, a determination processing routine, an automatic photographing control processing routine, and a change processing routine.
The image search processing routine is a program part for causing the CPU 8 to function as an image search means. That is, the image search processing routine includes a group of instructions for causing the CPU 8 to realize a function related to search processing for specifying a desired image file among a plurality of image files stored in the recording medium 3.
Specifically, according to this image search processing routine, the CPU 8 controls whether or not any one of the plurality of image files is specified as a desired image file in accordance with the determination result of the determination processing. . For example, the CPU 8 determines that the smile level of the face of the person in the search candidate image specified by the specifying process is based on the sensitivity level specified by the user and the current smile level of the face of the person associated with the state table T1. Is determined to be large, the search candidate image related to the determination is specified as a desired image file, while the smile degree of the face of the person in the search candidate image is determined to be less than or equal to the current smile degree. The search candidate image related to the determination is not specified as a desired image file.

Next, the search process will be described with reference to FIGS.
7 and 8 are flowcharts illustrating an example of operations related to search processing by the imaging apparatus.

As shown in FIG. 7, the CPU 8 determines whether or not the image search mode is set (step S101).
If it is determined that the search mode is set (step S101; YES), the CPU 8 determines whether or not an instruction to change the sensitivity level of the search process is input (step S102). If it is determined in step S102 that a sensitivity level change instruction has been input, that is, for example, an instruction to change the sensitivity from level 2 to level 1 is input (step S102; YES). ), The CPU 8 performs a process of setting the sensitivity level in accordance with the input sensitivity level change instruction (step S103).

Next, the CPU 8 determines whether or not a search target change instruction for the search process has been input (step S104). Also, when it is determined in step S102 that a sensitivity level change instruction has not been input (step S102; NO), the CPU 8 shifts the process to step S104.
If it is determined in step S104 that a search target change instruction has been input (step S104; YES), the CPU 8 performs a process of setting the search target in accordance with the input search target change instruction. This is performed (step S105).

Subsequently, the CPU 8 determines whether or not a search start instruction is input based on a predetermined operation of the operation input unit 5 by the user (step S106). Even when it is determined in step S104 that a search target change instruction has not been input (step S104; NO), the CPU 8 shifts the process to step S106.
If it is determined that a search start instruction has been input (step S106; YES), the CPU 8 searches for any one of the plurality of image files stored in the recording medium 3 by the recognition processing routine. After a candidate image file is newly acquired, a human face in a search candidate image related to the image file is detected. When the CPU 8 determines that a human face has been detected from the search candidate image (step S107; YES), the CPU 8 performs personal recognition processing for recognizing the face and identifying an individual (for example, Mr. A) (step S108). ).

As shown in FIG. 8, after that, the CPU 8 determines whether or not the face that is personally recognized is registered in the state table T1 (step S109).
Here, if it is determined that it is registered in the state table T1 (step S109; YES), the CPU 8 determines the smile degree determination template T2 from the smile state of the face of the person who has been personally recognized by the specific processing routine. It is used to determine and specify the smile level (step S10A).

Subsequently, the CPU 8 determines the smile level of the face of the person specified in the specifying process, the designated sensitivity level (for example, level 1), and the person associated with the state table T1 by the determination process routine. A comparison is made with the current smile level of the face (for example, smile level 50 in the case of Mr. A) to determine whether or not the smile level exceeds the current smile level (step S10B).
If it is determined that the smile level has exceeded the current smile level (step S10B; YES), the CPU 8 determines that the search candidate image according to the determination matches the search target by the image search processing routine, and the desired value is obtained. (Step S10C). Then, the CPU 8 displays a desired image on the display unit 4 as the search result (step S10D).

  On the other hand, if it is determined in step S10B that the smile level does not exceed the current smile level (step S10B; NO), the CPU 8 determines that the search candidate image according to the determination does not match the search target by the image search processing routine. (Step S10E).

  Further, when it is determined in step S109 that the personally recognized face is not registered in the state table T1 (step S109; NO), it is determined in step S107 that a human face has not been detected. If it is determined (step S107; NO), or if it is determined in step S106 that a search start instruction is not input (step S106; NO), the image search mode is not set in step S101. Even when it is determined that the CPU 8 determines (step S101; NO), the CPU 8 ends the search process.

  The CPU 8 sequentially executes the recognition process, the identification process, the determination process, and the image search process for each of the plurality of image files stored in the recording medium 3.

  Since the table update process is executed every time a new image is acquired, as in the above embodiment, detailed description thereof is omitted.

Therefore, according to the imaging apparatus of the first modification, when image data is newly acquired by automatic photographing processing or the like, the current smile level of the state table T1 is based on the past smile level including the smile level of the image data. And the sensitivity level are updated, it is possible to appropriately perform the search process in consideration of the smile state of the person in the subsequent execution determination of the search process.
That is, when the sensitivity level of the search process execution determination is set to a user-desired level among the plurality of sensitivity levels, the execution determination is not uniformly performed by a plurality of persons according to the sensitivity level. The correspondence between the current smile level and the sensitivity level in the state table T1 can be internally set in consideration of the smile state, so that a person with a small change in facial expression or a person with a large change in facial expression can be selected. However, it is possible to appropriately perform the search process by determining the search condition based on a determination criterion more suitable for each person without changing the sensitivity level.
In particular, the current smile level and the sensitivity level of the state table T1 in consideration of a predetermined number of smile levels from the newest ones registered in the past smile history of the state table T1, that is, newer changes in the smiles of each person The search condition is determined in consideration of the newer change state of the person's smile when a person who has little change in facial expression recently laughs well recently. be able to.
Thus, the search process can be performed more appropriately, and the usability of the imaging device can be further improved.

  In the first modification, the recording medium 3 is exemplified as the image storage unit. However, the present invention is not limited to this, and a plurality of image data may be stored in the built-in memory 7.

  In the first modification, an image related to a desired image file specified by the search process is displayed on the display unit 4, but the present invention is not limited to this, and the desired image file is recorded. You may make it store in the predetermined folder (illustration omitted) of the medium 3 or the internal memory 7. FIG.

In the above-described embodiment, the smile degree determination template T2 is used for determining the smile level of a person's face in steps S27, S34, and S10A. However, the smile level determination method is not limited to this. For example, the determination may be made based on the degree of change of eyes and mouth.
That is, for example, by checking all the images of the person involved in the determination of the smile degree, calculating the maximum displacement (difference) of the coordinates of the eyes and mouth, and making the person with a large change a person with a rich expression, You may make it set the smile degree corresponding to the sensitivity levels 1-3 separately as a person with few expressions with a person with little change.
Alternatively, a plurality of faces laughed by each person may be photographed in advance, and a reference image among them may be set in association with sensitivity levels 1 to 3.

  In the above-described embodiment, the automatic image capturing process and the search process are exemplified as the image related process. However, the image related process is not limited to these, and the image related process performed by an image processing apparatus such as an imaging apparatus or an image search apparatus. Any processing can be used.

Furthermore, in the above embodiment, the facial expression of a person, in particular, the smile level is exemplified as the reference state of the object related to the image-related processing, but the reference state of the object is not limited to this, For example, it may be defined based on the direction of the eyes or face, the posture, or the like.
Moreover, although a person, especially a person's face was illustrated as a target object, it is not restricted to these.
In the above case, a state table may be provided corresponding to the type of the object, for example, the direction of the eyes or face, the posture, or the like. As a result, it is possible to execute image-related processing by switching to a user-desired condition among a plurality of determination conditions such as a person's smile level, eye and face orientation, and posture.

  Furthermore, in the above-described embodiment, the sensitivity level of execution determination in the automatic shooting process and the search process is set to a user-desired level. However, the present invention is not limited to this, and it is uniformly at a predetermined sensitivity level. It may be fixed.

In addition, the configuration of the imaging apparatus 100 is merely an example illustrated in the above embodiment, and is not limited thereto.
Furthermore, although the imaging device 100 has been exemplified as the image processing device, the image processing device is not limited to this, and other image processing devices such as an image search device may be used as long as they perform image-related processing.

  In addition, in the above-described embodiment, the function as the specifying unit, the determining unit, the changing unit, the automatic photographing control unit, and the image searching unit is realized by the CPU 8 executing a predetermined program or the like. However, the present invention is not limited to this. For example, a logic circuit or the like for realizing various functions may be used.

It is a block diagram which shows schematic structure of the imaging device of Embodiment 1 to which this invention is applied. It is a figure which shows typically an example of state table T1 which concerns on the automatic imaging | photography process by the imaging device of FIG. It is a figure which shows typically an example of the template T2 for smile degree determination which concerns on the automatic imaging | photography process by the imaging device of FIG. 3 is a flowchart illustrating an example of a main operation performed by the imaging apparatus in FIG. 1. 3 is a flowchart illustrating an example of an operation related to automatic imaging processing by the imaging apparatus of FIG. 1. 3 is a flowchart illustrating an example of an operation related to table update processing by the imaging apparatus of FIG. 1. 10 is a flowchart illustrating an example of an operation related to a search process performed by an imaging apparatus according to a first modification. It is a flowchart which shows the continuation of the search process of FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 100 Imaging device 1 Imaging part 3 Recording medium 5 Operation input part 8 CPU

Claims (11)

Level designation means for designating a sensitivity level related to execution of image-related processing;
A table storage unit that stores a state table in which a reference state and a sensitivity level of an object related to a determination criterion as to whether to execute the image-related processing are associated with each other;
Identifying means for identifying the state of the object in the newly acquired image;
Changing means for changing a correspondence relationship between the sensitivity level of the state table and a reference state of the object based on the state of the object specified by the specifying means;
An image processing apparatus comprising: And a determination unit for comparing and determining the state of the object specified by the specifying unit, the sensitivity level specified by the level specifying unit, and a reference state of the object associated with the state table. ,
The changing means is a correspondence relationship between the sensitivity level of the state table and the reference state of the object based on the state of the object determined by the determining means to exceed the reference state of the object. The image processing apparatus according to claim 1, wherein: Imaging means for imaging a subject as the object;
The image-related processing further includes automatic photographing control means for controlling automatic photographing processing for automatically photographing the subject by the imaging means,
The image processing apparatus according to claim 2, wherein the automatic photographing control unit controls whether or not the imaging unit automatically images the subject according to a determination result by the determination unit. Image storage means for storing a plurality of images;
Image search means for performing a search process for searching for a desired image related to the object among the plurality of images stored in the image storage means as the image-related processing,
The image search means controls whether or not to specify any one of the plurality of images as the desired image according to a determination result by the determination means. The image processing apparatus described. In the state table, each of the plurality of sensitivity levels is associated with each of the reference states of the plurality of objects,
The determining means is specified by the specifying means and any one of the plurality of sensitivity levels specified by the level specifying means and the reference state of the object associated with the state table. The image processing apparatus according to claim 2, wherein the image processing apparatus compares and determines the state of the object. Past state storage means for storing a plurality of past states of the object identified so far by the specifying means;
The changing unit is configured to determine the sensitivity level of the state table based on a predetermined number of past states of the target object from the newest among the past states of the plurality of target objects stored in the past state storage unit. The image processing apparatus according to claim 1, wherein a correspondence relationship between the object and a reference state of the object is changed.   The image processing apparatus according to claim 1, wherein the object is a person.   The image processing apparatus according to claim 1, wherein the object is a human face. In the state table, each of the plurality of sensitivity levels is associated with each of the reference states of the plurality of objects,
The image processing apparatus according to claim 8, wherein the reference state of the object is defined based on a facial expression of the person.   The image processing apparatus according to claim 1, wherein a plurality of the state tables are provided according to a type of the object. A level designating unit that designates a sensitivity level related to the execution of the image-related processing, and a state table that associates the reference state of the target object and the sensitivity level related to the determination criterion as to whether to execute the image-related processing are stored. A table storage means, and a computer of an image processing apparatus,
Identification means for identifying the state of the object in the newly acquired image;
Changing means for changing a correspondence relationship between the sensitivity level of the state table and a reference state of the object based on the state of the object specified by the specifying means;
A program characterized by functioning as

Images