JP2013073309A - Method for extracting region of interest from image, and electronic apparatus, system and program for achieving the same method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an electronic apparatus and the like appropriately extracting a subject that a user desires to acquire without deviating from a region of interest.SOLUTION: The electronic apparatus according to the present invention includes: acquiring means for acquiring a monitor image; analysis means for analyzing a subject included in the monitor image; learning means for generating and retaining subject information on the subject as dictionary data; processing object image acquiring means for acquiring a processing object image; and processing object image analysis means for analyzing the subject included in the processing object image. The electronic apparatus further includes: region-of-interest extraction means for extracting a region of interest from the processing object image on the basis of a comparative determination obtained by comparing the subject information obtained by the processing object image analysis means with the dictionary data; and application operation control means for controlling the operation of an application on the basis of the region of interest extracted by the region-of-interest extraction means.

Description

The present invention relates to an image attention area extraction method, and more specifically, by learning an image (photograph) displayed on a screen of an electronic device such as a mobile terminal referred to by a user, The present invention relates to a method of extracting a close attention area.
The present invention also relates to an electronic device, a system, and a program for realizing the method.

In general, a region of interest such as the center of the image or a person is automatically extracted from a live view image or a captured image of a camera on a mobile terminal, highlighted based on the extracted region of interest, and various effect processing is performed during a slide show. However, there is a technique for generating an album, or performing autofocus (AF) or auto exposure correction (AE).
As a technique for extracting a region of interest, Patent Document 1 discloses a technique for enlarging a captured image around a center position of an image or a predetermined position where a person image or the like is located.

JP 2000-75416 A

However, when the image center or person as described in Patent Document 1 is trimmed around the center and an application such as a highlight display or a slide show is executed, there are the following problems.
The first problem is that, when the center of the image is determined as the attention area, a person, a part of the background structure, or the like deviates from the attention area.
Specifically, when the subject intended to be acquired or displayed by the photographer or the user of the electronic device is a person and a background structure, when the image is enlarged and trimmed with reference to the center of the image, a part of the person is obtained. In addition, there is a problem that a part of the structure is cut and an undesired image is obtained.
The second problem is that when a person is determined as an attention area, the structure of the background of the person is out of the attention area.
Specifically, in the same manner as described above, when a subject intended to be acquired or displayed by a photographer or a user of an electronic device is a person and a background structure, a certain region is extracted and trimmed with reference to the person. Then, there was a problem that the background structure was cut.

  Therefore, the present invention provides a method for appropriately extracting a subject intended to be acquired or displayed by a user without deviating from the attention area, an electronic device that realizes the method, an image attention area extraction support system, and a program. For the purpose.

A method for extracting a region of interest from an image according to the present invention includes:
Get a monitor image,
Analyzing the subject included in the monitor image,
Generating and storing subject information regarding the subject included in the monitor image as dictionary data;
Get the processing target image,
Analyzing a subject included in the processing target image;
By comparing subject information related to the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. To determine whether
When it is determined that one or more subjects that are the same or similar are included, an attention area is extracted from the processing target image so as to include the one or more subjects,
Application operation control is performed based on the attention area.

The electronic device according to the present invention is
Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
Processing target image acquisition means for acquiring a processing target image;
Processing target image analysis means for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information about the subject obtained by the processing target image analyzing means and the dictionary data held in the monitor image learning means, the processing target image is held in the monitor image learning means. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject being included are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Application operation control means for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
Is provided.

An image attention area extraction system according to the present invention includes:
Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Dictionary data acquisition means for acquiring dictionary data from the server;
Processing target image acquisition means for acquiring a processing target image;
Processing target image analysis means for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing unit with the dictionary data acquired by the dictionary data acquiring unit, the processing target image is acquired by the dictionary data acquiring unit. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Application operation control means for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
An electronic device with
Is provided.

Another image attention area extraction system according to the present invention includes:
Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Processing target image acquisition means for acquiring a processing target image;
Processing target image transmission means for transmitting the processing target image acquired by the processing target image acquisition means to the server;
An electronic device with
An image attention area extraction system comprising:
The server
Processing target image receiving means for receiving the processing target image transmitted from the processing target image transmitting means;
Processing target image analysis means for analyzing a subject included in the processing target image received by the processing target image receiving means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing means with the dictionary data held in the monitor image learning means, the processing target image is acquired by the dictionary data acquiring means. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Attention area extraction image transmission means for transmitting an image from which the attention area has been extracted by the attention area extraction means to the electronic device;
Further comprising
The electronic device is
Attention area extraction image receiving means for receiving the attention area extraction image transmitted from the attention area extraction image transmission means;
Application operation control means for performing application operation control based on the attention area extraction image received by the attention area extraction image reception means;
Is further provided.

An image attention area extraction program according to the present invention is:
On the computer,
A function to acquire a monitor image;
A function of analyzing a subject included in the monitor image;
A function of generating and storing subject information regarding the subject included in the monitor image as dictionary data;
A function to acquire a processing target image;
A function of analyzing a subject included in the processing target image;
By comparing subject information regarding the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. The ability to determine whether or not
When it is determined that one or more subjects that are the same or similar are included, the processing target is included so as to include the one or more subjects that are determined to be the same or similar included in the processing target image. A function to extract a region of interest from an image;
A function for controlling the operation of the application based on the attention area;
Is executed.

  According to the present invention, a subject intended to be acquired by a user can be appropriately extracted without departing from the attention area.

1 is a system configuration diagram including a mobile terminal 1 according to a first embodiment. It is a block diagram of portable terminal 1 concerning a 1st embodiment. It is a flowchart (dictionary data generation process) which shows operation | movement of the portable terminal 1 which concerns on 1st Embodiment. It is a flowchart (attention area extraction process) which shows operation | movement of the portable terminal 1 which concerns on 1st Embodiment. It is explanatory drawing of the attention area extraction process of the portable terminal which concerns on 1st Embodiment. It is explanatory drawing of the attention area extraction process of the portable terminal which concerns on 1st Embodiment. It is explanatory drawing of the attention area extraction process of the portable terminal which concerns on 1st Embodiment. It is a block diagram of the image attention area extraction assistance system which concerns on 2nd Embodiment. It is a block diagram of the portable terminal 100 which concerns on 2nd Embodiment. It is explanatory drawing of the flowchart (attention area extraction process) which shows operation | movement of the portable terminal 100 which concerns on 2nd Embodiment. FIG.

(First embodiment)
Hereinafter, an embodiment of an electronic apparatus of the present invention will be described with reference to the drawings. This embodiment is an example in which the present invention is applied to the mobile terminal 1.
The mobile terminal 1 of the present invention is typically a mobile phone, a digital camera, a smartphone, or the like, but can also be applied to game machines, personal computers (including tablet PCs and notebook PCs), digital photo frames, and the like. is there. In short, the present invention can be widely applied to electronic devices that can perform certain processing based on dictionary data.
(1) System configuration

FIG. 1 is a diagram showing a configuration of a communication system according to an embodiment of the present invention.
In FIG. 1, a portable terminal 1 has a mobile radio communication function and a mail transmission / reception function. When a call is made using the mobile radio communication function, the mobile terminal 1 calls the originating exchange SW via the base station BS where the location is registered. In response to the outgoing call, the originating side exchange SW switches the terminating side exchange SW based on the called party number (subscriber number) and location registration information inquired from a subscriber registration server (not shown) provided in the wireless communication network RN. Call. The called side exchange SW calls the called side portable terminal (not shown) via the called side base station BS, and when the called side responds to the incoming call in response, the calling side exchange SW and the called side exchange SW A link with is established and a call becomes possible.

  Mail transmitted from the portable terminal 1 using the mail transmission / reception function is sent to the mail server MS connected to the Internet IN via the base station BS, the exchange SW, and a gateway server (not shown) provided in the wireless communication network RN. Is transmitted. The mail server MS transmits the mail to the mobile terminal 1 having the destination mail address through the reverse route.

In addition to this, the portable terminal 1 can access many servers including the homepage server HS and the electronic book server EBS, and obtains files including image data such as landscape images, person images, and animal images from these servers. can do.
(2) Configuration of mobile terminal

FIG. 2 is a block diagram of the mobile terminal 1 according to the embodiment of the present invention.
As shown in FIG. 2, the mobile terminal 1 includes a control unit 2, a wireless communication unit (transmission / reception unit) 3, an antenna 4, an audio signal processing unit 5, a microphone 6, a speaker 7, a display unit 8, and an operation unit 9. A ROM (Read Only Memory) 10, a RAM (Random Access Memory) 11, an imaging unit 12, and a recording medium 13.

The control unit 2 includes a CPU (Central Processing Unit), and controls the operation of each unit of the mobile terminal 1 according to a program stored in the ROM 10. The control unit 2 includes a monitor image analysis unit 2A, a monitor image learning unit 2B, a region of interest extraction unit 2C, and an application operation control unit 2D.
The monitor image analysis unit 2A acquires monitor image data from a home page, mail, electronic book, or the like browsed by the user, recognizes an image (photograph) portion, and analyzes the characteristics of the image. The monitor image to be analyzed may be an image acquired via the imaging unit 12 or the recording medium 13 in addition to those acquired from these.
Here, “monitor image” or “monitor image” means a reference image that is stored as dictionary data to be described later and is referred to when an attention area is extracted.
The monitor image analysis unit 2A analyzes and outputs the following subject information from the acquired image.

(A) Characteristics of subject (person, pet, accessory, building, mountain, sea, etc.) and their areas For example, by analyzing a monitor image acquired by the user, a person, pet, accessory, building, mountain, If the sea is included, it is analyzed in the possible range based on parameters such as contour, color tone, size, age, type, etc., and each characteristic point is obtained and converted into data.
For the area, for example, parameters relating to the area such as the ratio and position of the area occupied by the subject in the entire image are analyzed, and the characteristic points are obtained and converted into data.
(B) Composition For example, information on the composition is obtained by analyzing position information where a subject such as a building or a mountain is located with respect to the entire image. Alternatively, it is also possible to detect a straight line from the image by Hough transform and analyze the composition information using this as a composition line.
(C) Aspect ratio The aspect ratio here means the ratio of the long side to the short side of a two-dimensional object. That is, it refers to the aspect ratio of the subject included in the image, not the aspect ratio of the image itself (screen itself).
The monitor image analysis unit 2A passes the above analysis result to the monitor image learning unit 2B.

  Based on the analysis result of the monitor image analysis unit 2A, the monitor image learning unit 2B generates image features as dictionary data referred to by the attention area extraction unit 2C, and stores the generated image features in the dictionary data storage unit 11A.

The attention area extraction unit 2 </ b> C analyzes the image captured by the imaging unit 12 of the mobile terminal 1 and displayed in live view on the display unit 8, and the captured image recorded in the RAM 11 and the recording medium 13, and extracts the attention area. To do. Specifically, the attention area extraction unit 2C uses subject information about a subject included in an image displayed in a live view display and the dictionary data held in the monitor image learning unit 2B, as features such as an edge of the subject, a region By comparing based on at least one parameter of composition, aspect ratio, it is determined whether or not an image displayed in a live view or the like includes a subject that is the same as or similar to the subject held in the monitor image learning unit 2B. When it is determined that the subject is included, the subject that is the same or similar to the live view display or the like is as close as possible to the subject included in the dictionary data of the monitor image learning unit 2B. The region of interest is extracted and included so as to be included.
When a plurality of subjects that are the same as or similar to the subject of the dictionary data are detected in the image displayed in live view, the attention area extraction unit 2C extracts and outputs the attention area so as to include the plurality of objects. .

  The application operation control unit 2D controls the application operation corresponding to the function of the mobile terminal 1 based on the output result of the attention area extraction unit 2C. For example, display control is performed by performing various effect processes on the display unit 8 during highlight display or slide show. Alternatively, an album is generated and recorded in the RAM 11 or the recording medium 13. Alternatively, at the time of camera photographing, imaging control such as autofocus (AF) and auto exposure correction (AE) is performed while performing display control so that the extraction area is displayed on the display unit 8.

When the mobile terminal 1 performs a voice call, the wireless communication unit 3 demodulates a received signal (wireless signal) received via the antenna 4 and converts it into received data.
The audio signal processing unit 5 provides an analog reception signal obtained by D / A converting the reception data to the speaker 7, and the speaker 7 generates a reception voice based on the provided analog reception signal.
The microphone 6 converts the input transmission voice into an analog transmission signal and provides it to the voice signal processing unit 5. The voice signal processing unit 5 performs A / D conversion on the provided analog transmission signal and transmits the transmission data. Get.
The wireless communication unit 3 modulates transmission data into a transmission signal, and the transmission signal is transmitted via the antenna 4.

  Further, when the mobile terminal 1 receives an image, the wireless communication unit 3 decodes the encoded image data included in the packet and provides the image data to the control unit 2. The decoded image data is displayed on the display unit 8.

  The display unit 8 includes a liquid crystal display and a liquid crystal driving device, and displays information such as the other party's telephone number, radio wave state, remaining battery level, etc. when receiving a call, and the contents of e-mails, websites, e-books and the like. The display unit 8 also displays an image captured by the imaging unit 12 and an image recorded on the recording medium 13.

  The operation unit 9 includes keys for operating the mobile terminal 1. Specifically, the operation unit 9 includes a power key, an input key for inputting numbers and characters, an application key for instructing activation and termination of an application, and the like. The operation unit 9 also has keys for selecting a monitor image reference mode and a normal mode, which will be described later.

  The ROM 10 stores a program for executing flowcharts shown in FIGS. 2 and 3 to be described later, and an application program for executing various applications.

The RAM 11 includes various storage units (not shown) that store various data. For example, an address book information storage unit for storing address book information (name, telephone number, mail address, etc.) of the address book function, a mail information storage unit for storing contents of transmitted / received mails and attached images, and URL information of websites A Web information storage unit for storing images is provided.
The RAM 11 also includes a dictionary data storage unit 11A that stores image data extracted from these various storage units (not shown) as dictionary data.

The imaging unit 12 includes an imaging mechanism such as a lens (not shown), a TTL (Through the Lens) exposure meter, a CMOS (Complementary Metal Oxide Semiconductor) sensor, an A / D conversion circuit, and a frame memory.
The image captured by the imaging unit 12 is displayed in live view on the display unit 8. The imaging unit 12 captures a subject by performing functions such as auto focus (AF) and auto exposure correction (AE) based on the photometric result of the TTL exposure meter during imaging by a user operation.
An image captured based on the user's imaging instruction is recorded in the RAM 11 or the storage medium 13.

The recording medium 13 is a detachable recording medium such as a memory card provided with a flash memory. The recording medium 13 can record an image captured by the imaging unit 12, and can also capture an image captured without using the mobile terminal 1. 1 can be captured. This captured image can be an image stored in the dictionary data storage unit 11A.
(3) Mobile terminal operation

Next, the operation of the mobile terminal 1 according to the first embodiment described above will be described. The following processes are all executed by the control unit 2 (or the monitor image analysis unit 2A, the monitor image learning unit 2B, the attention area extraction unit 2C, or the application operation control unit 2D).
(3.1) Dictionary data generation processing

FIG. 3 is a flowchart for explaining an operation related to the dictionary data generation processing of the mobile terminal 1.
First, the control unit 2 determines whether or not a dictionary data generation instruction has been issued by the operation of the operation unit 9 by the user. The generation of dictionary data refers to a process of generating image data as dictionary data serving as a comparison reference that is referred to in an attention area extraction process described later.
When the controller 2 determines that a dictionary data generation instruction has been issued by a user operation, the dictionary data generation process of FIG. 3 is entered.
As described above, in addition to the case where a dictionary is generated by a user instruction, an image may be analyzed in the background to generate dictionary data.

In step S1, the monitor image analysis unit 2A acquires an image used as a monitor image from a homepage, mail, electronic book, or the like browsed by the user. The image acquisition source is not limited to these, and may be an image captured through the imaging unit 12 or an image recorded on the recording medium 13.
In step S2, the monitor image analysis unit 2A performs analysis for grasping information on the subject with respect to the image acquired in step S1. For example, subject information includes information about the subject, such as the features of the subject (person, pet, accessory, building, mountain, sea, etc.) and its area, image composition (that is, subject position information), and subject aspect ratio. To grasp as.

In step S3, the monitor image learning unit 2B generates dictionary data for reference by the attention area extraction unit 2C described later with reference to FIG. 4 based on the analysis result of the monitor image analysis unit 2A.
In step S4, the monitor image learning unit 2B holds the dictionary data generated in step S3 in the dictionary data storage unit 11A.
(3.2) attention area extraction processing

FIG. 4 is a flowchart for explaining the operation related to the attention area extraction processing of the mobile terminal 1.
First, the control unit 2 determines whether or not the monitor image reference mode is selected by the operation of the operation unit 9 by the user. When the monitor image reference mode is selected, the control unit 2 controls the operation of the application while referring to the dictionary data held in the dictionary data storage unit 11A as described below.
That is, when the control unit 2 determines that the monitor image reference mode is selected, the process enters the routine of FIG.

In step S <b> 21, the attention area extraction unit 2 </ b> C acquires an image displayed in live view on the display unit 8 or an image recorded in the RAM 11 or the recording medium 13 as a processing target image.
In step S22, the attention area extraction unit 2C performs analysis on the processing target image acquired in step S21. The analysis procedure is the same as step S2 described above.

  In step S23, the attention area extraction unit 2C compares the dictionary data stored in the dictionary data storage unit 11A with the analysis data acquired in step S22. The comparison is performed along parameters that both image data have.

In step S24, the attention area extraction unit 2C extracts the attention area from the processing target image acquired in step S21 based on the comparison result in step S23.
This point will be described with reference to FIGS.
In FIG. 5, an image held as dictionary data through the previous steps S1 to S4 is shown as a “learning image”. In addition, the image acquired in step S21 is shown as a “processing target image”.
As shown in FIG. 5, the processing target image is analyzed in step S22, and the learning image is compared with the analysis result in step S22 in step S23.
When data indicating the presence of a subject that is the same as or similar to the subject included in the learning image is included in the analysis result in step S22 in step S23, the control unit 2 is the same as or similar to the subject of the learning image from the processing target image. A region of interest is extracted as an “extracted image” as shown in FIG. 5 so that the subject to be included is included as close as possible to the dictionary data.

If a certain area is extracted with reference to the central portion of the processing target image, for example, a building and a person may be cut as shown in “center extraction image” in FIG.
Further, when a certain area is extracted with the face recognition function based on the face portion of the processing target image, the building may be cut like the “face recognition extracted image” in FIG.
According to the present embodiment, the extraction region is determined in step S24 so as to include a subject that is the same as or similar to the subject of the learning image with reference to the center of the processing target image. Therefore, the attention area can be extracted without causing these disadvantages.
Note that the image extraction includes the learning image while positioning the face of the person detected by the face recognition function at, for example, one of the golden division points and the three division points without using the center of the processing target image as a reference. May be extracted.
Further, the image may be extracted by outputting a region (area) where the region of interest exists as shown by a thick broken line in FIG.

Returning to FIG. 4, in step S <b> 25, the application operation control unit 2 </ b> D controls the application operation according to the function of the mobile terminal 1 based on the extracted image. For example, highlight display, slide show effect, display control for album generation, auto focus (AF) and auto exposure correction (AE) control during camera shooting are performed.
In order to control the operation of the application, even if you perform an application such as highlight display or slide show by trimming around the center of the image or person, a part of the structure of the person or background Will not fall out of the highlight display or slide show. That is, it is possible to appropriately extract a subject intended to be acquired or displayed by the photographer or the user of the mobile terminal 1 without departing from the attention area, and to optimally operate applications such as highlight display and slide show.
(Second Embodiment)

The second embodiment relates to an image attention area extraction support system in which a dictionary data generation function is performed by a server.
Hereinafter, this system will be described with reference to FIGS.
As shown in FIG. 8, the attention area extraction support system for an image according to the present embodiment carries a dictionary function providing server DS that provides a dictionary function service, and extracts the attention area from the image in response to the provision of this service. Mobile terminal 100, which are connected via the Internet IN or the like. The configuration for mediating the portable terminal 100 and the dictionary function providing server DS is the same as that of FIG.
The dictionary function providing server DS includes a CPU, ROM, RAM, and the like (not shown), generates dictionary data in the same procedure as in FIG. 3 according to the first embodiment, and the generated dictionary data is distributed from the mobile terminal 100. Delivered on request.
The mobile terminal 100 uses the same reference numerals for the same parts as the mobile terminal 1 according to the first embodiment, as shown in FIG. 9, except that the monitor image analysis unit 2A and the monitor image learning unit 2B are unnecessary. The mobile terminal 1 has the same configuration.

The mobile terminal 100 executes processing according to the flowchart of FIG.
As is clear from the comparison between FIG. 10 and FIG. 4, steps S31, S32, S35, and S36 of FIG. 10 correspond to steps S21, S22, S24, and S25 of FIG. Only the point will be described below.
In the processing procedure of FIG. 10, the control unit 2 acquires dictionary data from the dictionary function providing server DS in step S33, and stores the acquired data in the dictionary data storage unit 11A.
In step S34, the attention area extraction unit 2C compares the dictionary data stored in the dictionary data storage unit 11A with the analysis data acquired in step S32.

As a modified embodiment of the second embodiment, more processing may be realized on the server side like a so-called thin client.
For example, on the mobile terminal side, minimum processing related to acquisition of the processing target image, transmission of the acquired image to the server, reception of the processed image (region of interest extraction image), and application operation control is executed. On the other server side, in addition to dictionary data generation processing, processing for analyzing an image received from a mobile terminal and comparing it with learning data, extraction of a region of interest, and transmission of an image from which the region of interest has been extracted to a mobile terminal May be executed.

The program code that realizes the procedure of the flowchart shown above may be provided by a recording medium that records the program code. For example, it may be provided by a USB memory, a CD-ROM, a magneto-optical disk, or the like.
(Appendix 1 to Appendix 9)

Hereinafter, additional aspects of the present invention will be described.
A part or all of the above-described embodiment can be described as in the following supplementary notes, but is not limited thereto.
(Appendix 1)
FIG. 11 is a configuration diagram of Supplementary Note 1.
As shown in this figure, the invention according to Appendix 1 is
Monitor image acquisition means 41 for acquiring a monitor image;
Monitor image analysis means 42 for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means 43 for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
Processing target image acquisition means 44 for acquiring a processing target image;
Processing target image analysis means 45 for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information about the subject obtained by the processing target image analyzing means and the dictionary data held in the monitor image learning means, the processing target image is held in the monitor image learning means. Comparison determination means 46 for determining whether or not one or two or more subjects that are the same as or similar to a certain subject are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means 47;
Application operation control means 48 for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
Is an electronic device.
(Appendix 2)
The invention according to appendix 2
The monitor image analyzing unit and the processing target image analyzing unit analyze the subject with respect to at least one parameter of the feature, area, composition, and aspect ratio of the subject,
The comparison determination unit is the electronic apparatus according to attachment 1, wherein the comparison determination unit determines whether the images are the same or similar based on at least one of these parameters.
(Appendix 3)
The invention according to appendix 3
The monitor image learning means generates and holds subject information as dictionary data by performing statistical processing of similar images based on the analysis result of the monitor image analysis means to learn, and either 1 or 2 It is an electronic device described in one.
(Appendix 4)
The invention according to appendix 4
Get a monitor image,
Analyzing the subject included in the monitor image,
Generating and storing subject information regarding the subject included in the monitor image as dictionary data;
Get the processing target image,
Analyzing a subject included in the processing target image;
By comparing subject information related to the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. To determine whether
When it is determined that one or more subjects that are the same or similar are included, an attention area is extracted from the processing target image so as to include the one or more subjects,
Performing application control based on the region of interest;
This is a method for extracting a region of interest from an image.
(Appendix 5)
The invention according to appendix 5
In the analysis of the monitor image and the analysis of the processing target image, the subject is analyzed with respect to at least one parameter of the feature, area, composition, and aspect ratio of the subject,
In the comparison determination, the method according to supplementary note 4, wherein it is determined whether or not the subject is the same or similar based on at least one of these parameters.
(Appendix 6)
The invention according to appendix 6
When the dictionary data is held, subject information is held as dictionary data by performing statistical processing of similar images based on the analysis result of the monitor image, and learning, according to any one of appendix 4 or 5 It is a method.
(Appendix 7)
The invention according to appendix 7
Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Dictionary data acquisition means for acquiring dictionary data from the server;
Processing target image acquisition means for acquiring a processing target image;
Processing target image analysis means for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing unit with the dictionary data acquired by the dictionary data acquiring unit, the processing target image is acquired by the dictionary data acquiring unit. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Application operation control means for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
An electronic device with
Is a system that supports extraction of an image attention area.
(Appendix 8)
The invention according to appendix 8
Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Processing target image acquisition means for acquiring a processing target image;
Processing target image transmission means for transmitting the processing target image acquired by the processing target image acquisition means to the server;
An electronic device with
An image attention area extraction system comprising:
The server
Processing target image receiving means for receiving the processing target image transmitted from the processing target image transmitting means;
Processing target image analysis means for analyzing a subject included in the processing target image received by the processing target image receiving means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing means with the dictionary data held in the monitor image learning means, the processing target image is acquired by the dictionary data acquiring means. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Attention area extraction image transmission means for transmitting an image from which the attention area has been extracted by the attention area extraction means to the electronic device;
Further comprising
The electronic device is
Attention area extraction image receiving means for receiving the attention area extraction image transmitted from the attention area extraction image transmission means;
Application operation control means for performing application operation control based on the attention area extraction image received by the attention area extraction image reception means;
Further equipped with,
This is an image attention area extraction system.
(Appendix 9)
The invention according to appendix 9
On the computer,
A function to acquire a monitor image;
A function of analyzing a subject included in the monitor image;
A function of generating and storing subject information regarding the subject included in the monitor image as dictionary data;
A function to acquire a processing target image;
A function of analyzing a subject included in the processing target image;
By comparing subject information regarding the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. The ability to determine whether or not
When it is determined that one or more subjects that are the same or similar are included, the processing target is included so as to include the one or more subjects that are determined to be the same or similar included in the processing target image. A function to extract a region of interest from an image;
A function for controlling the operation of the application based on the attention area;
This is a program for extracting a region of interest from an image for executing.

Claims (9)

Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
Processing target image acquisition means for acquiring a processing target image;
Processing target image analysis means for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information about the subject obtained by the processing target image analyzing means and the dictionary data held in the monitor image learning means, the processing target image is held in the monitor image learning means. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject being included are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Application operation control means for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
With electronic equipment. The monitor image analyzing unit and the processing target image analyzing unit analyze the subject with respect to at least one parameter of the feature, area, composition, and aspect ratio of the subject,
The electronic apparatus according to claim 1, wherein the comparison determination unit determines whether the subject is the same or similar based on at least one of these parameters.   3. The monitor image learning unit according to claim 1, wherein the monitor image learning unit holds subject information as dictionary data by performing statistical processing of similar images based on the analysis result of the monitor image analysis unit and learning. The electronic device described. Get a monitor image,
Analyzing the subject included in the monitor image,
Generating and storing subject information regarding the subject included in the monitor image as dictionary data;
Get the processing target image,
Analyzing a subject included in the processing target image;
By comparing subject information related to the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. To determine whether
When it is determined that one or more subjects that are the same or similar are included, an attention area is extracted from the processing target image so as to include the one or more subjects,
Performing application control based on the region of interest;
Image attention area extraction method. In the analysis of the monitor image and the analysis of the processing target image, the subject is analyzed with respect to at least one parameter of the feature, area, composition, and aspect ratio of the subject,
5. The image attention region extraction method according to claim 4, wherein in the comparison determination, it is determined whether or not the subject is the same or similar based on at least one of these parameters.   6. When the dictionary data is held, subject information is generated and held as dictionary data by performing statistical processing of similar images based on the analysis result of the monitor image and learning. 2. The image attention area extraction method according to item 1. Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Dictionary data acquisition means for acquiring dictionary data from the server;
Processing target image acquisition means for acquiring a processing target image;
Processing target image analysis means for analyzing a subject included in the processing target image acquired by the processing target image acquisition means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing unit with the dictionary data acquired by the dictionary data acquiring unit, the processing target image is acquired by the dictionary data acquiring unit. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Application operation control means for controlling the operation of the application based on the attention area extracted by the attention area extraction means;
An electronic device with
An image attention area extraction system. Monitor image acquisition means for acquiring a monitor image;
Monitor image analysis means for analyzing a subject included in the monitor image acquired by the monitor image acquisition means;
Monitor image learning means for generating and holding subject information relating to the subject obtained by the monitor image analysis means as dictionary data;
A server with
Processing target image acquisition means for acquiring a processing target image;
Processing target image transmission means for transmitting the processing target image acquired by the processing target image acquisition means to the server;
An electronic device with
An image attention area extraction system comprising:
The server
Processing target image receiving means for receiving the processing target image transmitted from the processing target image transmitting means;
Processing target image analysis means for analyzing a subject included in the processing target image received by the processing target image receiving means;
By comparing the subject information relating to the subject obtained by the processing target image analyzing means with the dictionary data held in the monitor image learning means, the processing target image is acquired by the dictionary data acquiring means. Comparison determination means for determining whether or not one or more subjects that are the same as or similar to the subject of the dictionary data are included;
A region of interest for extracting a region of interest from the processing target image so as to include the one or more subjects when the comparison / determination unit determines that the same or similar subjects are included. Extraction means;
Attention area extraction image transmission means for transmitting an image from which the attention area has been extracted by the attention area extraction means to the electronic device;
Further comprising
The electronic device is
Attention area extraction image receiving means for receiving the attention area extraction image transmitted from the attention area extraction image transmission means;
Application operation control means for performing application operation control based on the attention area extraction image received by the attention area extraction image reception means;
Further equipped with,
Image attention area extraction system. On the computer,
A function to acquire a monitor image;
A function of analyzing a subject included in the monitor image;
A function of generating and storing subject information regarding the subject included in the monitor image as dictionary data;
A function to acquire a processing target image;
A function of analyzing a subject included in the processing target image;
By comparing subject information regarding the subject included in the processing target image with the dictionary data, the processing target image includes one or more subjects that are the same as or similar to the subject included in the monitor image. The ability to determine whether or not
When it is determined that one or more subjects that are the same or similar are included, the processing target is included so as to include the one or more subjects that are determined to be the same or similar included in the processing target image. A function to extract a region of interest from an image;
A function for controlling the operation of the application based on the attention area;
An image attention area extraction program for executing

Images