JP6074928B2 - Image processing apparatus, image processing method, and program - Google Patents

Description

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

As a conventional technique, there is a technique that can detect a subject included in a captured image. The subject is, for example, a person's face, but the angle varies depending on the image.
In order to detect such faces at various angles, a technique is disclosed in which face detection is performed by a plurality of classifiers each having face information at different angles (see Patent Document 1).

JP 2007-66010 A

  However, according to the technique of the above-mentioned Patent Document 1, a discriminator that does not need to be used is used for face detection depending on the angle of the face of the subject. was there.

  The present invention has been made in view of such a situation, and an object thereof is to reduce the processing burden of detecting a specific image region.

In order to achieve the above object, an image processing apparatus according to an aspect of the present invention includes:
Storage means for storing a plurality of types of detection information for detecting a specific image region;
Acquisition means for sequentially acquiring images;
Detecting means for detecting the specific image region in the image data acquired by the acquiring means using a plurality of types of detection information stored in the storage means;
Selection means for selecting specific detection information from the plurality of types of detection information based on a detection result by the detection means;
With
The storage means stores the detection information not selected by the selection means among the detection information as not used for the detection of the next specific image area, and the selection selected by the selection means Is stored as information used for detection of the next specific image area,
Based on the detection result by the detection means, the detection information that is no longer selected among the specific detection information is updated to the end of the detection information queue that is not used for detection, and is detected. Storage control means for controlling to update the first detection information among the detection information that is not used for the specific detection information ;
It is characterized by that.

  According to the present invention, the processing load for detecting a specific image region can be reduced.

It is a block diagram which shows the structure of the hardware of the imaging device which concerns on one Embodiment of this invention. FIG. 2 is a functional block diagram showing a functional configuration for the imaging apparatus of FIG. 1 to execute face detection processing. It is a figure explaining the functional structure which uses some kind of several types of discriminators in a discriminator control part preferentially. 3 is a flowchart illustrating a flow of face detection processing executed by the imaging apparatus of FIG. 2. It is a flowchart explaining the flow of the discriminator priority process which the imaging device of FIG. 2 performs.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram showing a hardware configuration of an imaging apparatus 1 as an embodiment of an image processing apparatus according to the present invention. The imaging device 1 can be configured by a digital camera, for example.

  The imaging device 1 includes a CPU (Central Processing Unit) 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, an image processing unit 14, a bus 15, an input / output interface 16, and an imaging unit. 17, an operation unit 18, a display unit 19, a storage unit 20, a communication unit 21, and a drive 22.

  The CPU 11 executes various processes according to a program recorded in the ROM 12 or a program loaded from the storage unit 20 to the RAM 13. The RAM 13 also stores data necessary for the CPU 11 to execute various processes as appropriate.

The image processing unit 14 is configured by a DSP (Digital Signal Processor), a VRAM (Video Random Access Memory), and the like, and performs various image processing on image data in cooperation with the CPU 11.
Here, in this embodiment, the processing unit of the image by the imaging apparatus 1 is one still image, and the still image as such a processing unit is referred to as a “frame image” in this specification. That is, in the present embodiment, the moving image is composed of a plurality of frame images, and processing is executed for each frame image. Therefore, hereinafter, unless otherwise specified, an image means a frame image and an image data means frame image data.
For example, the image processing unit 14 performs image processing such as noise reduction, white balance, and camera shake correction on image data output from the imaging unit 17 described later.

  The CPU 11, ROM 12, RAM 13, and image processing unit 14 are connected to each other via a bus 15. An input / output interface 16 is also connected to the bus 15. An imaging unit 17, an operation unit 18, a display unit 19, a storage unit 20, a communication unit 21, and a drive 22 are connected to the input / output interface 16.

Although not shown, the imaging unit 17 includes an optical lens unit and an image sensor.
The optical lens unit is configured by a lens that collects light, for example, a focus lens or a zoom lens, in order to photograph a subject.
The focus lens is a lens that forms a subject image on the light receiving surface of the image sensor. The zoom lens is a lens that freely changes the focal length within a certain range.
The optical lens unit is also provided with a peripheral circuit for adjusting setting parameters such as focus, exposure, and white balance as necessary.

The image sensor includes a photoelectric conversion element, AFE (Analog Front End), and the like.
The photoelectric conversion element is composed of, for example, a CMOS (Complementary Metal Oxide Semiconductor) type photoelectric conversion element or the like. A subject image is incident on the photoelectric conversion element from the optical lens unit. Therefore, the photoelectric conversion element photoelectrically converts (captures) the subject image, accumulates the image signal for a predetermined time, and sequentially supplies the accumulated image signal as an analog signal to the AFE.
The AFE performs various signal processing such as A / D (Analog / Digital) conversion processing on the analog image signal. A digital signal is generated by various signal processing and output as an output signal of the imaging unit 17.
Hereinafter, it is assumed that the output signal of the imaging unit 17 is “image data”. Therefore, image data is output from the imaging unit 17 and is appropriately supplied to the CPU 11, the image processing unit 14, and the like.

The operation unit 18 includes various buttons and the like, and accepts user instruction operations.
The display unit 19 is composed of a liquid crystal display or the like and displays various images.
The storage unit 20 is configured by a DRAM (Dynamic Random Access Memory) or the like, and temporarily stores image data output from the image processing unit 14 or the like. The storage unit 20 also stores various data necessary for processing by the image processing unit 14 and the like.
The communication unit 21 controls communication with other devices (not shown) via a network including the Internet.

  A removable medium 31 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately attached to the drive 22. The program read from the removable medium 31 by the drive 22 is installed in the storage unit 20 as necessary. The removable medium 31 can also store various data such as image data stored in the storage unit 20 in the same manner as the storage unit 20.

The imaging apparatus 1 having such a configuration starts live view imaging processing and live view display processing before and after imaging.
That is, the imaging device 1 continues the imaging operation by the imaging unit 17, and during that time, image data sequentially output from the image processing unit 14 in units of frame images via the imaging unit 17 is stored in a memory (in this embodiment). The data is temporarily stored in the storage unit 20). Such a series of processes is a “live view imaging process” referred to herein.
Further, the imaging apparatus 1 sequentially reads out each piece of image data temporarily recorded in units of frame images in a memory (storage unit 20 in the present embodiment) during live view imaging, and displays a frame image corresponding to each of the image data. 19 are sequentially displayed. Such a series of control processes is the “live view display process” referred to herein. The frame image displayed on the display unit 19 by the live view display process is hereinafter referred to as “live view image”.

The user can instruct to record image data by determining the composition while viewing the live view image and then pressing a shutter switch (not shown) of the operation unit 18 to the lower limit. The operation of pressing the shutter switch to the lower limit in this way is hereinafter referred to as “full press operation” or simply “full press”.
Hereinafter, in order to distinguish from imaging for live view imaging processing and live view display processing, imaging when a recording instruction is issued by a full-press operation is referred to as “recording imaging”.

Furthermore, in the present embodiment, the imaging apparatus 1 displays a frame indicating, for example, a focus area on a person's face as an example of a subject in a live view image. That is, the imaging device 1 according to the present embodiment detects a face in a frame image. Further, the imaging apparatus 1 according to the present embodiment executes the following series of processes in order to reduce the processing load for detecting a specific image region.
The imaging apparatus 1 executes an image data acquisition process that sequentially acquires image data.
In addition, the imaging apparatus 1 is an example of a specific image region in an image acquired by the image data acquisition process using some types of classifiers that are a plurality of types of detection information stored in the storage unit 20. The face detection process for detecting the face is executed.
Furthermore, based on the detection result of the face by the face detection process, a classifier priority process for preferentially selecting a specific type of classifier from the type of classifier used in the face detection process is executed.
Here, the face detection processing is performed according to various algorithms such as a neutral network (NN), adaboost (adaboost), or support vector machine (SVM) by each classifier, for example, for a reduced image data group described later. It can be performed by the processing. Since the face detection process using each of the neutral network (NN), Adaboost, and support vector machine (SVM) is a well-known technique, detailed description thereof is omitted.

  In the description of the present embodiment, a series of acquiring one image data in the imaging apparatus 1, detecting a face in the image data, and preferentially using a specific type of discriminator based on the detection result of the face. This process is called one “cycle”, the N-th cycle (N is an arbitrary integer value of 1 or more) is also called “cycle N”, and the N-th next cycle is also called “cycle N + 1”.

FIG. 2 is a functional block diagram illustrating a functional configuration for the image capturing apparatus 1 of FIG. 1 to execute face detection processing.
In FIG. 2, the CPU 11, the image processing unit 14, the imaging unit 17, the display unit 19, and the storage unit 20 are illustrated in the configuration of the imaging device 1 in FIG. 1.

In the image processing unit 14, when the face detection process is executed, the acquisition unit 41, the image processing unit 42, the detection unit 43, and the post-processing unit 44 function.
In the CPU 11, when the face detection process is executed, the discriminator control unit 51 and the display control unit 52 function.
The storage unit 20 stores a plurality of types of discriminators as detection information into a use discriminator group and a standby discriminator group.
Here, the use discriminator group and the standby discriminator group in the present embodiment are composed of a plurality of discriminators set to which one belongs by the discriminator control unit 51 described later.
Further, the “use discriminator group” in the present embodiment refers to a plurality of discriminators used when the detection unit 43 described later in cycle N detects a face from image data. Further, the “standby discriminator group” in the present embodiment refers to a plurality of discriminators that are not used when the detection unit 43 described later in cycle N detects a face from image data.
In the following description, the classifiers in the use classifier group are also referred to as use classifiers, and the classifiers in the standby classifier group are also referred to as standby classifiers.

  The acquisition unit 41 acquires image data captured by the imaging unit 17. This image data is image data for executing face detection processing, and the image size is a VGA (Video Graphics Array) image or a QVGA (Quarter-VGA) image, and is image data of a relatively small size.

  The image processing unit 42 converts the image data acquired by the acquiring unit 41 into image data of a luminance image, and a reduced image data group obtained by sequentially reducing the converted image data (hereinafter referred to as an image pyramid). Create

The detection unit 43 detects, for example, a face for each reduced image data of each resolution of the image pyramid created by the image processing unit 42 using a plurality of types of use identifiers stored in the storage unit 20. Further, the detection results for these reduced image data are integrated.
Further, the detection unit 43 applies all of the plurality of types of use discriminators to each of the plurality of reduced image data, calculates the number of detection results for each use discriminator, and stores it in the storage unit 20. Here, the “number of detection results” is the number of detection results indicating the number of reduced image data adapted to each use discriminator.

  The post-processing unit 44 displays, for example, a frame on the face portion of the live view image displayed on the display unit 19 via the display control unit 52 based on the detection result by the detection unit 43.

The discriminator control unit 51 preferentially selects a specific type of discriminator from a plurality of types of discriminators based on the detection result of the face by the detection unit 43 in cycle N, and the detection unit 43 uses it in cycle N + 1. Set the classifier.
Further, the discriminator control unit 51 sets the classifiers and standby discriminator groups set in the use discriminator group stored in the storage unit 20 based on the face detection result by the detection unit 43 in the cycle N. The set plural kinds of discriminators are replaced with each other.
That is, the classifier control unit 51 reads the number of detection results of the classifier calculated by the detection unit 43 from the storage unit 20, determines the magnitude relationship between the number of detection results and the predetermined value, and the number of detection results is equal to or greater than the predetermined value. If it is, it is determined that the classifier is suitable in cycle N, and if the number of detection results is less than a predetermined value, it is determined that the classifier is not suitable in cycle N.
For example, in this embodiment, the discriminator control unit 51 sets the predetermined value to 1 and determines that the discriminator is suitable in cycle N if the number of detection results is 1 or more, and the number of detection results is less than 1 (that is, 0), it is determined that the discriminator is not suitable in cycle N.
Then, the discriminator control unit 51 moves the discriminator determined not to be a discriminator conforming to this cycle N from the use discriminator group to the end in the queue of the standby discriminator group and waits for the standby discriminator group. The discriminator that was first in the matrix is moved to the use discriminator group. That is, in the present embodiment, the classifier control unit 51, when the number of search results of all the classifiers of the used classifier is 1 or more, a plurality of types set in the used classifier group or the standby classifier group. Do not replace classifiers with each other.
The discriminator control unit 51 sets such discriminators used by the detection unit 43 in cycle N + 1 by executing such processing for all the use discriminators in cycle N.
A functional configuration in which a specific type of discriminator is preferentially used from among a plurality of types of discriminators in the discriminator control unit 51 will be specifically described with reference to FIG.

FIG. 3 is a diagram illustrating a functional configuration in which a specific type of discriminator is preferentially used from a plurality of types in the discriminator control unit 51.
In FIG. 3, classifiers A to M are examples of a plurality of types of detection information. Specifically, a front face classifier, a rotation left 30 degree face classifier, a rotation right 30 degree face classifier, and a left 30 A face classifier, a right 30 degree face classifier, and the like.
(A) has shown the use discriminator group of the cycle N. FIG. (B) shows a standby discriminator group of cycle N. (C) shows the number of search results calculated by the detection unit 43 for each use discriminator in cycle N.
(D) shows the use discriminator group of cycle N + 1. (E) shows the standby discriminator group of cycle N + 1. (F) shows the number of search results calculated by the detection unit 43 for each use discriminator in cycle N + 1.
(G) shows the use discriminator group of cycle N + 2. (H) shows the standby discriminator group of cycle N + 2.

In the cycle N, the detection unit 43 detects a face using the classifiers A, B, C, D, E, F, G, H, and I shown in FIG. The number of detection results of each discriminator shown in FIG.
The discriminator control unit 51 sequentially moves the discriminators B, E, F, and G having the number of detection results of 0 to the end of the queue of the standby discriminator group of cycle N + 1, and the standby discriminator group of cycle N The discriminators K, L, and M are sequentially moved from the discriminator J at the head of the queue to the use discriminator group in cycle N + 1. Thereby, the use discriminator group of cycle N + 1 shown in (d) and the standby discriminator group of cycle N + 1 shown in (e) are set.
Then, in the cycle N + 1, the detection unit 43 detects a face using the use classifier group in the cycle N + 1 shown in (d), and calculates the number of detection results of each classifier shown in (f). Similar to cycle N, the discriminator controller 51 sets a use discriminator group of cycle N + 2 shown in (g) and a standby discriminator group of cycle N + 2 shown in (h).

  Returning to FIG. 2, under the control of the post-processing unit 44, the display control unit 52 displays, for example, a frame indicating the focus area on the face portion of the live view image displayed on the display unit 19. .

Next, with reference to FIG. 4, the face detection process realized by the functional configuration of FIG. 2 will be described among the processes of the imaging apparatus 1.
FIG. 4 is a flowchart for explaining the flow of face detection processing executed by the imaging apparatus of FIG.

The face detection process of FIG. 4 is a process executed when imaging by the imaging unit 17 is performed.
That is, at least the live view imaging process and the live view display process have been started, and the face detection process is executed before the recording operation is performed after the user presses the button fully.

In step S <b> 1, the classifier control unit 51 reads a use classifier stored in the storage unit 20.
In step S <b> 2, the acquisition unit 41 acquires image data captured by the imaging unit 17.
In step S3, the image processing unit 42 converts the image data acquired in step S2 into image data of a luminance image.
In step S4, the image processing unit 42 creates an image pyramid by sequentially reducing the image data converted into the luminance image in step S3.

In step S5, the detection unit 43 performs face detection on each reduced image data of each resolution of the image pyramid created in step S4 using a plurality of types of usage identifiers. Further, the detection unit 43 calculates the number of detection results for each use classifier and stores it in the storage unit 20.
In step S6, the detection unit 43 integrates the detection results for the reduced image data in step S5.

In step S <b> 7, the post-processing unit 44 displays, for example, a frame on the face portion of the live view image displayed on the display unit 19 via the display control unit 52 based on the detection result by the detection unit 43.
In step S8, the display control unit 52 determines whether or not the end of the live view imaging process is selected by an instruction operation of the operation unit 18 by the user. When it is determined that the end is selected, this process ends. If it is not determined that the end is selected, the process proceeds to step S9.

  In step S9, the discriminator control unit 51 executes discriminator priority processing. As will be described in detail later, in the classifier priority processing, the classifier control unit 51 preferentially selects a specific type of classifier from a plurality of types of classifiers based on the detection result of step S5 in cycle N, The selected discriminator is set as the discriminator used by the detection unit 43 in cycle N + 1.

Next, classifier priority processing realized by such a functional configuration of FIG. 2 among the processing of the imaging apparatus 1 will be described with reference to FIG.
FIG. 5 is a flowchart for explaining the flow of discriminator priority processing executed by the imaging apparatus of FIG.
In FIG. 5, the classifier priority processing in cycle N will be described as an example.

In step S11, the discriminator control unit 51 determines whether the number of used discriminators stored in the storage unit 20 has looped. If it is determined that the loop has occurred, the process proceeds to step S1 (see FIG. 4). If it is not determined that the loop has occurred, the process proceeds to step S12.
Here, the “loop” in the present embodiment is one loop until the process transitioned from step S11 returns to step S11 again. That is, the loop immediately after the start of the classifier priority processing is 0, and the number of loops when returning to step S11 n times (n is an integer) is n.
In addition, the classifier control unit 51 executes each process for a plurality of types of use classifiers in the cycle N in one loop. For example, the number of use discriminators in the present embodiment is nine.
Therefore, when it is determined that the number of times of returning to step S11 is the ninth time, the classifier control unit 51 can execute each process on all the used classifiers by moving the process to step S1.

In step S12, the discriminator controller 51 determines whether or not the discriminator is adapted in cycle N based on the detection result calculated by the detector 43 in step S5. The process returns to step S11, and if it is not determined that the classifier is suitable, the process proceeds to step S13.
Specifically, the classifier control unit 51 reads the number of detection results of the classifier calculated by the detection unit 43 from the storage unit 20, determines whether or not the number of detection results is 0, and the number of detection results is When the number is 1 or more, it is determined that the classifier is suitable for cycle N, and when the number of detection results is 0, it is determined that the classifier is not suitable for cycle N.

In step S13, the discriminator control unit 51 moves the discriminator determined not to be the discriminator matched in cycle N in step S12 from the use discriminator group to the end in the queue of the standby discriminator group.
In step S14, the discriminator control unit 51 uses the discriminator that is the head in the queue of the standby discriminator group as the discriminator is moved to the end in the queue of the standby discriminator group in step S13. Move to the instrument group.

As described above, the imaging apparatus 1 according to the present embodiment includes the storage unit 20, the acquisition unit 41, the detection unit 43, and the classifier control unit 51.
The storage unit 20 stores a plurality of classifiers for detecting a person's face.
The acquisition unit 41 acquires image data sequentially.
The detection unit 43 detects a face in the image data acquired by the acquisition unit 41 using some types of classifiers from the plurality of types of classifiers stored in the storage unit 20.
The discriminator control unit 51 selects a specific type of discriminator from some discriminators based on the detection result of the face by the detection unit 43.
Accordingly, for example, out of a plurality of types of classifiers for detecting a human face, based on the detection result, only the types of classifiers that are considered to be effective in the subsequent face detection processing can be preferentially used. .
Therefore, the processing load for detecting a specific image region can be reduced as compared with the case where detection is performed using all of the plurality of types of discriminators for detecting the specific image region.

In addition, the detection unit 43 calculates the number of detection results by the detection unit 43 based on a plurality of types of detection information and sequentially acquired image data, and determines whether the number of detection results is equal to or greater than a predetermined value. To do.
The discriminator control unit 51 selects a specific discriminator from a specific type of discriminator based on the determination result by the detection unit 43.
Thereby, for example, the discriminator control unit 51 sets the predetermined value to 1 and if the number of detection results is 1 or more, the discriminator determines that the discriminator is suitable in cycle N, and the number of detection results is less than 1 (that is, 0 ), It is determined that the discriminator is not suitable in cycle N.
Therefore, the processing load for detecting a specific image region can be reduced as compared with the case where detection is performed using all of the plurality of types of discriminators for detecting the specific image region.

Further, the discriminator control unit 51 uses the discriminator not selected as a specific type of discriminator from a part of the discriminators (use discriminators) based on the detection result and the use discriminator among the plural types of discriminators. At least a part of classifiers (standby classifiers) other than the classifiers are replaced with each other. That is, the discriminator control unit 51 selects a discriminator having a detection result number less than a predetermined value from among the used discriminators based on the detection result of the detection unit 43, and replaces it with a part of a plurality of types of standby discriminators. .
Thereby, for example, among a plurality of types of used classifiers, a classifier that is suitable for detection of a specific image region is left, and a classifier that is not matched (a classifier whose detection result number is less than a predetermined value) is classified into a plurality of types. Since it can be replaced with a part of the standby discriminator, the detection accuracy can be improved while reducing the processing load for detecting a specific image region.

  In addition, this invention is not limited to the above-mentioned embodiment, The deformation | transformation in the range which can achieve the objective of this invention, improvement, etc. are included in this invention.

  In the above-described embodiment, the classifiers A to M are a plurality of types of classifiers corresponding to the face angle. However, the classifiers are not limited to this, but are different in race, age, brightness, night view (use of flash Or the like).

  In the above-described embodiment, the discriminator control unit 51 determines a plurality of types of discrimination set in the use discriminator group or the standby discriminator group when the number of search results of all the discriminators in the use discriminator is not zero. Although the devices are not replaced with each other, the determination of replacement in the classifier control unit 51 is not limited to this, and the classifier control unit 51 can determine whether the number of search results of all the classifiers of the used classifiers is not zero. For example, it is possible to replace a certain number of classifiers with a smaller number of search results in the used classifier group and the certain number of classifiers in the standby classifier group.

  In the above-described embodiment, the discriminator control unit 51 executes the discriminator priority processing for all the used discriminators in one cycle, but the discriminator priority processing of the discriminator control unit 51 is performed in this manner. For example, when there are nine use discriminators, the discriminator control unit 51 executes the discriminator priority process for three use discriminators in one cycle, and sets all the use discriminators in three cycles. The classifier priority processing can also be executed for the same. As a result, the processing load is reduced, and the face in the frame image can be detected quickly.

  In the above-described embodiment, the discriminator control unit 51 selects a discriminator (detection information) to be used for detection in the next cycle N + 1 from a plurality of types of discriminators (detection information) in cycle N. However, the classifier to be selected (detection information) is not limited to this, and may be selected for detection after the cycle N + 2. That is, the discriminator control unit 51 may select a discriminator (detection information) to be used at the time of detection of any subsequent cycle in the cycle N from a plurality of types of discriminators (detection information).

  In the above-described embodiment, the image processing apparatus to which the present invention is applied has been described as an example configured as an image processing apparatus such as a digital camera. However, the present invention is not particularly limited to an image processing apparatus, and in general, an electronic apparatus that can execute the above-described image processing regardless of the presence or absence of an imaging function (data of captured images may be acquired from another apparatus). Can be applied. Specifically, for example, the present invention can be applied to a personal computer, a video camera, a portable navigation device, a portable game machine, and the like.

The series of processes described above can be executed by hardware or can be executed by software.
In other words, the functional configuration of FIG. 2 is merely an example and is not particularly limited. That is, it is sufficient that the image processing apparatus has a function capable of executing the above-described series of processing as a whole, and what functional block is used to realize this function is not particularly limited to the example of FIG.
In addition, one functional block may be constituted by hardware alone, software alone, or a combination thereof.

When a series of processing is executed by software, a program constituting the software is installed on a computer or the like from a network or a recording medium.
The computer may be a computer incorporated in dedicated hardware. The computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

  The recording medium including such a program is not only constituted by the removable medium 31 of FIG. 1 distributed separately from the apparatus main body in order to provide the program to the user, but also in a state of being incorporated in the apparatus main body in advance. It is comprised with the recording medium etc. which are provided in this. The removable medium 31 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), or the like. The magneto-optical disk is configured by an MD (Mini-Disk) or the like. In addition, the recording medium provided to the user in a state of being preliminarily incorporated in the apparatus main body includes, for example, the ROM 12 in FIG. 1 in which a program is recorded, the hard disk included in the storage unit 20 in FIG.

In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series along the order, but is not necessarily performed in time series, either in parallel or individually. The process to be executed is also included.
Further, in the present specification, the term “system” means an overall apparatus configured by a plurality of devices, a plurality of means, and the like.

  As mentioned above, although embodiment of this invention was described, this embodiment is only an illustration and does not limit the technical scope of this invention. The present invention can take other various embodiments, and various modifications such as omission and replacement can be made without departing from the gist of the present invention. These embodiments and modifications thereof are included in the scope and gist of the invention described in this specification and the like, and are included in the invention described in the claims and the equivalents thereof.

The invention described in the scope of claims at the beginning of the filing of the present application will be appended.
[Appendix 1]
Storage means for storing a plurality of types of detection information for detecting a specific image region;
Acquisition means for sequentially acquiring images;
Detecting means for detecting the specific image region in the image data acquired by the acquiring means using a plurality of types of detection information stored in the storage means;
Selection means for selecting specific detection information from the plurality of types of detection information based on a detection result by the detection means;
An image processing apparatus comprising:
[Appendix 2]
Calculation means for calculating the number of detection results by the detection means based on the plurality of types of detection information and the sequentially acquired images;
Determination means for determining whether the number of detection results calculated by the calculation means is equal to or greater than a predetermined value;
Further comprising
The selection unit selects the specific detection information from the plurality of types of detection information based on a determination result by the determination unit.
The image processing apparatus according to appendix 1, wherein:
[Appendix 3]
The selection means selects a plurality of types of the specific detection information,
The storage means further stores other types of detection information different from the types of detection information,
A discriminator that alternates between the plurality of types of specific detection information selected by the selection unit and at least some types of detection information in the other types of detection information stored by the storage unit. Further comprising an exchange means,
The image processing apparatus according to appendix 1 or 2, characterized in that:
[Appendix 4]
The image processing according to any one of appendices 1 to 3, wherein the detection unit further detects the specific image region based on the specific detection information selected by the selection unit. apparatus.
[Appendix 5]
The image according to any one of appendices 1 to 4, wherein the specific image region is a region including a human face, and the detection information is a discriminator for detecting the human face. Processing equipment.
[Appendix 6]
An image processing method executed by an image processing apparatus including a storage unit that stores a plurality of types of detection information for detecting a specific image region,
An acquisition step of sequentially acquiring images;
A detection step of detecting the specific image region in the image acquired by the processing of the acquisition step using a plurality of types of detection information stored in the storage means;
A selection step of selecting specific detection information from the plurality of types of detection information based on a detection result by the detection step;
An image processing method comprising:
[Appendix 7]
A computer that controls an image processing apparatus including a storage unit that stores a plurality of types of detection information for detecting a specific image region;
Acquisition means for sequentially acquiring images;
Detection means for detecting the specific image region in the image acquired by the acquisition means using a plurality of types of detection information stored in the storage means;
Selection means for selecting specific detection information from the plurality of types of detection information based on a detection result by the detection means;
A program characterized by functioning as

  DESCRIPTION OF SYMBOLS 1 ... Imaging device, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Image processing part, 15 ... Bus, 16 ... Input / output interface, 17 ... Image capturing unit, 17 ... operation unit, 19 ... display unit, 20 ... storage unit, 21 ... communication unit, 22 ... drive, 31 ... removable media, 41 ... acquisition , 42 ... Tracking image processing unit, 43 ... Detection unit, 44 ... Post-processing unit, 51 ... Discriminator control unit, 52 ... Display control unit

Claims (8)

Storage means for storing a plurality of types of detection information for detecting a specific image region;
Acquisition means for sequentially acquiring images;
Detecting means for detecting the specific image region in the image data acquired by the acquiring means using a plurality of types of detection information stored in the storage means;
Selection means for selecting specific detection information from the plurality of types of detection information based on a detection result by the detection means;
With
The storage means stores the detection information not selected by the selection means among the detection information as not used for the detection of the next specific image area, and the selection selected by the selection means Is stored as information used for detection of the next specific image area,
Based on the detection result by the detection means, the detection information that is no longer selected among the specific detection information is updated to the end of the detection information queue that is not used for detection, and is detected. Storage control means for controlling to update the first detection information among the detection information that is not used for the specific detection information ;
An image processing apparatus. The storage control means stores the specific detection information selected by the selection means as a first group, and the detection information not selected by the selection means among the detection information is set as a second group. The image processing apparatus according to claim 1 , wherein the image processing apparatus is stored. Calculation means for calculating the number of detection results by the detection means based on the plurality of types of detection information and the sequentially acquired images;
Determination means for determining whether the number of detection results calculated by the calculation means is equal to or greater than a predetermined value;
Further comprising
The selection unit selects the specific detection information from the plurality of types of detection information based on a determination result by the determination unit.
The image processing apparatus according to claim 1 or 2, characterized in that. The selection means selects a plurality of types of the specific detection information,
The storage means further stores other types of detection information different from the types of detection information,
A discriminator that alternates between the plurality of types of specific detection information selected by the selection unit and at least some types of detection information in the other types of detection information stored by the storage unit. Further comprising an exchange means,
The image processing apparatus according to any one of claims 1 to 3, characterized in that. Said detecting means further based on the specific detection information selected by the selecting means, an image according to claim 1, any one of 4, wherein the detecting the specific image area Processing equipment. The said specific image area | region is an area | region containing a person's face, The said information for a detection is a discriminator for detecting a person's face, The any one of Claim 1 to 5 characterized by the above-mentioned. Image processing device. An image processing method executed by an image processing apparatus including a storage unit that stores a plurality of types of detection information for detecting a specific image region,
A storage step of storing a plurality of types of detection information for detecting a specific image region;
An acquisition step of sequentially acquiring images;
A detection step of detecting the specific image region in the image acquired by the processing of the acquisition step using a plurality of types of detection information stored in the storage means;
A selection step of selecting specific detection information from the plurality of types of detection information based on a detection result by the detection step;
Including
The storing step stores the detection information not selected by the selection step among the detection information as not used for the detection of the next specific image region, and the selection selected by the selection step. Is stored as information used for detection of the next specific image area ,
Based on the detection result of the detection step, the detection information that is no longer selected among the specific detection information is updated to the end of the detection information queue that is not used for detection, and is detected. The image processing method further includes a storage control step of controlling to update the first detection information among the detection information that is not used for the specific detection information . A computer for controlling the image processing apparatus;
Storage means for storing a plurality of types of detection information for detecting a specific image region;
Acquisition means for sequentially acquiring images;
Detection means for detecting the specific image region in the image acquired by the acquisition means using a plurality of types of detection information stored in the storage means;
Selection means for selecting specific detection information from the plurality of types of detection information based on a detection result by the detection means;
Function as
The storage means stores the detection information not selected by the selection means among the detection information as not used for the detection of the next specific image area, and the selection selected by the selection means Is stored as information used for detection of the next specific image area ,
Based on the detection result by the detection means, the detection information that is no longer selected among the specific detection information is updated to the end of the detection information queue that is not used for detection, and is detected. A program that further functions as a storage control unit that controls to update the detection information at the head of the detection information that is not used for the detection as the specific detection information .

Images