JP2015176422A - Device, system, method, and program for processing information - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an information processing device, system, method, and program, which allow for retrieving desired information.SOLUTION: An information processing device includes: attribute extraction means for extracting attributes from an acquired image; image extraction means for extracting images associated with the extracted attributes from storage means; display means for displaying the extracted images; input means which accepts a selection from the displayed images; search means which re-extracts images from the storage means based on the attributes associated with the selected image; and output means for outputting a search result.

Description

  The present invention relates to an information processing apparatus, system, method, and program.

  Various searches are performed on the web due to the development of the Internet. In addition to a method of extracting data from a database using characters as a query, a method of performing an information search using an image as a query is also known (see Patent Document 1).

JP 2009-193187 A

  By the way, for example, when traveling abroad, a traveler may not know the language of the destination. For this reason, even if a traveler tries to search for information such as products sold at a destination store, it may be difficult to create a query using appropriate words. In such a case, it would be convenient if information retrieval could be performed using product images.

  However, when an image is used as a query, it may not be possible to specify what the searcher has searched for. For example, when an image of a carbonated drink product becomes a query, the searcher may not want to search for the carbonated drink product itself but also search for another carbonated product or simply a drink product. It is possible.

  The above-described technique shows an example of searching for an image similar to a photographed image, but such a problem is not taken into consideration, and there is a possibility that desired information search cannot be performed.

  SUMMARY An advantage of some aspects of the invention is that it provides an information processing apparatus, system, method, and program capable of performing desired information retrieval.

  In order to achieve such an object, an embodiment of the present invention is an information processing apparatus, which extracts attribute from an acquired image, and extracts an image associated with the extracted attribute from a storage unit. Based on the attribute associated with the selected image, the image extracting means, the display means for displaying the extracted image, the input means for accepting the selection of the displayed image, and the replay of the image from the storage means. Search means for performing extraction, and output means for outputting the search results are provided.

  In addition, the present invention provides a transmission unit that transmits an image, a display unit that displays an image, an input unit that receives a selection of the displayed image and transmits it to the second information processing apparatus, and outputs a received search result An output means for extracting the attribute from the received image, an image associated with the extracted attribute from the storage means, and extracting the first information from the storage means. Image extraction means for transmitting to the processing apparatus; and search means for re-extracting the image from the storage means based on the attribute associated with the image selected by the first information processing apparatus. An information processing system including two information processing apparatuses is provided.

  Further, the present invention extracts an attribute corresponding to the acquired image, extracts an image associated with the extracted attribute, displays the extracted image, accepts selection of the displayed image, is selected An information processing method for re-extracting an image based on the attribute associated with the image and outputting a search result is provided.

  Further, the present invention displays, on a computer, an attribute extraction step for extracting an attribute from the acquired image, an image extraction step for extracting an image associated with the extracted attribute from the storage means, and the extracted image. A display step; an input step for receiving selection of the displayed image; a search step for re-extracting the image from the storage means based on the attribute associated with the selected image; and outputting a search result And an information processing program for executing the output step.

  The present invention provides an information processing apparatus, system, method, and program capable of performing desired information retrieval.

1 is a diagram illustrating a configuration example of an information processing device 1. FIG. 3 is a diagram illustrating an example of a storage unit 11. FIG. It is a figure which shows the operation | movement image of the image extraction part. FIG. 10 is a diagram illustrating a display example of the display unit 14. FIG. 10 is a diagram illustrating a display example of the display unit 14. FIG. 4 is a diagram showing an operation image of a search unit 16. FIG. 6 is a diagram illustrating an operation example of the first embodiment. 3 is a diagram illustrating an example of a storage unit 11. FIG. FIG. 5 is a diagram illustrating an operation image of the first embodiment. FIG. 10 is a diagram illustrating a display example of the display unit 14. FIG. 10 is a diagram illustrating a display example of the display unit 14. FIG. 5 is a diagram illustrating an operation image of the first embodiment. FIG. 10 is a diagram illustrating a display example of the display unit 14. It is a figure which shows the hierarchy example of an attribute. It is a figure which shows the hierarchy example of an attribute. 3 is a diagram illustrating an example of a storage unit 11. FIG. FIG. 10 is a diagram illustrating a display example of the display unit 14. 10 is a diagram illustrating an operation example of Embodiment 2. FIG. 10 is a diagram illustrating a configuration example of Embodiment 3. FIG. It is a figure which shows the modification of information processing apparatus.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In all the drawings, the same components are denoted by the same reference numerals, and description thereof will be omitted as appropriate.

  In addition, each part which comprises the apparatus in the following description is comprised by hardware, such as a logic circuit. Each unit includes a computer control unit, a memory, a program loaded in the memory, a storage unit such as a hard disk for storing the program, a network connection interface, and the like, and may be realized by any combination of hardware and software. Good. And unless there is particular notice, the realization method and apparatus are not limited.

  In addition, the control unit that controls each unit in the embodiment includes a CPU (Central Processing Unit) and the like. The control unit operates an OS (Operating system) to control the entire apparatus and the like, and reads a program and data from a recording medium mounted on a drive device, for example, to a memory, and executes various processes according to the program and data. . The recording medium is, for example, an optical disk, a flexible disk, a magnetic optical disk, an external hard disk, a semiconductor memory, or the like, and records a computer program so that the computer can read it. The computer program may be downloaded from an external computer (not shown) connected to the communication network.

<Embodiment 1>
First, a first embodiment of the present invention will be described with reference to the drawings. FIG. 1 shows an example of an information management apparatus 1 according to the present embodiment.

  The information processing apparatus 1 includes a storage unit 11, an attribute extraction unit 12, an image extraction unit 13, a display unit 14, an input unit 15, a search unit 16, an output unit 17, a feature amount extraction unit 18, And a collation unit 19. The information processing apparatus 1 is a portable terminal such as a smartphone having a camera function, for example, but is not limited thereto. Hereinafter, an example in which the information processing apparatus 1 includes a camera function (not shown) will be described.

  The storage unit 11 stores images and attributes in association with each other. The image may be a feature amount of the image as well as the image itself. An attribute is information associated with an image, and is generally information indicating the characteristics of an image or its subject. For example, when the image is an image of a coffee beverage, the attributes are: product: “beverage”, color: “black”, taste: “bitter”, sales company name: “˜corporation”, and the like.

  FIG. 2 shows an example of correspondence between images and attributes stored in the storage unit 11. Here, the attributes 1 to 6 indicate different attributes. FIG. 2 shows that, for example, image A and attributes 1 to 3 are associated with each other.

  The attribute extraction unit 12 extracts an attribute corresponding to the acquired image from the storage unit 11. Here, the “acquired image” is, for example, an image captured by a camera included in the information processing apparatus 1. That is, the image is an image of a product or the like captured by the owner of the information processing apparatus 1 (hereinafter simply referred to as a user) with a camera or the like. Alternatively, when the information processing apparatus 1 has a communication function, the “acquired image” may be an image acquired from an external device. The “acquired image” may be an image extracted from the storage unit 11 or the like as an image similar to an image captured by a camera or the like. In this case, the feature amount extraction unit 18 and the collation unit 19 collate the feature amount of the image captured by the camera or the like with the feature amount of the image stored in the storage unit 11, and search for similar images. The retrieved image may be “acquired image”. The feature amount extraction unit 18 has a function of extracting a feature amount from an image. However, various methods for extracting the feature amount are known and will not be described in detail. The collation unit 19 has a function of searching the storage unit 11 and performing a matching process between the feature amounts of the images, and determining whether there is a similar image having a feature amount that matches a predetermined amount or more. Various methods are also known for such collation processing and will not be described in detail.

  When the attribute extraction unit 12 acquires an image, the attribute extraction unit 12 refers to the storage unit 11 and extracts an attribute corresponding to the acquired image. For example, if the acquired image is the image A, the attribute extraction unit 12 extracts attributes 1 to 3.

  The image extraction unit 13 extracts an image associated with the attribute extracted by the attribute extraction unit 12 from the storage unit 11. For example, if the attribute extracted by the attribute extraction unit 12 is 1 to 3, the image extraction unit 13 extracts an image associated with the attributes 1 to 3.

  FIG. 3 shows an operation image of the image extraction unit 13 that extracts images associated with the attributes 1 to 3. Referring to FIG. 2, the images corresponding to attribute 1 are image A and image C. The images corresponding to attribute 2 are image A, image B, and image C. The images corresponding to attribute 3 are image A and image E. Therefore, the image extraction unit 13 extracts these images. The image extraction unit 13 may extract these images for each attribute. In that case, the same image may be extracted in duplicate. For example, in FIG. 3, images A and C are extracted in duplicate.

  The display unit 14 displays the extracted image. For example, the display unit 14 may display an image extracted for each attribute in association with the attribute. FIG. 4 shows an example in which images are displayed in rows on the display unit 14 for each attribute. In FIG. 4, images A and C corresponding to attribute 1 are arranged in the left column, images A, B and C corresponding to attribute 2 are arranged in the center column, and images A and E corresponding to attribute 3 are arranged. Lined up in the right column. Although the attribute name is displayed on the display unit 14 in FIG. 4, the attribute name is not necessarily displayed. An example in which an image extracted for each attribute is displayed in association with the attribute is not limited to the aspect of FIG. Other examples will be described later.

  The input unit 15 has a function of accepting selection of a displayed image. For example, as shown in FIG. 5, the input unit 15 may be a touch panel provided integrally with the display unit 14. The input unit 15 may be a key button or the like that can select an image. Here, a case where the input unit 15 is the touch panel shown in FIG. 5 will be described as an example. The user touches on the image in order to select the image displayed on the display unit 14. The touched image is displayed so as to be distinguishable from other images. For example, in FIG. 5, the selected image is circled. The user can select an image similar to the image that he / she wanted to search through the input unit 15. FIG. 5 shows that the user has selected images B and E.

  The search unit 16 re-extracts the image from the storage unit 11 based on the attribute associated with the selected image. For example, when the user selects images B and E, the search unit 16 extracts images based on attributes corresponding to the images B and E, respectively.

  FIG. 6 shows an operation image of the search unit 16. Referring to the storage unit 11, the attributes corresponding to the image B are 2 and 4. The attributes corresponding to the image E are 3, 4, and 6. Here, the search unit 16 calculates an attribute having a predetermined number or more of attributes. For example, in this example, there are one attribute 2, 3, 6 and two attribute 4. Therefore, if the predetermined number is 2, attribute 4 is calculated. In this embodiment, the predetermined number is assumed to be 2.

  Next, the search unit 16 extracts an image corresponding to the calculated attribute from the storage unit 11. In this example, since the predetermined number is 2, attribute 4 is calculated. Therefore, the search unit 16 extracts an image corresponding to the attribute 4 from the storage unit 11. Referring to FIG. 2, the images corresponding to attribute 4 are B, C, D, and E. Therefore, the search unit 16 extracts these images.

  The output unit 17 outputs the search result. The output is a display on the display unit 14 or an audio notification by a microphone (not shown). The output of the search result includes displaying the extracted image. The search result output includes displaying an information search result corresponding to the extracted image. For example, if a URL (Uniform Resource Locator) is stored in the storage unit 11 in association with each image, the output unit 17 directly presents the URL destination information to the user without displaying the extracted image. May be.

  Next, the operation of the information processing apparatus 1 in the present embodiment will be described with reference to FIG. First, a camera (not shown) of the information processing apparatus 1 images an object such as a product (step S1). The feature quantity extraction unit 18 performs feature quantity extraction from the image (step S2). The collation unit 19 searches the storage unit 11 to determine whether a similar image exists (step S3).

  If a similar image exists, the attribute extraction unit 12 extracts the attribute associated with the image from the storage unit 11 (step S4). Next, the image extraction unit 13 extracts attributes associated with the extracted image from the storage unit 11 (step S5). Next, the display unit 14 displays an image (step S6). Next, the user selects an arbitrary image from the displayed images via the input unit 15 (step S7). The search unit 16 extracts attributes associated with the selected image (step S8). Next, the search unit 16 calculates an attribute having a predetermined number or more of attributes (step S9). Note that the search unit 16 may select an attribute having the largest number of attributes instead of calculating an attribute having a predetermined number or more of attributes. Next, the search unit 16 extracts an image associated with the calculated attribute from the storage unit 11 (step S10). Finally, the output unit 17 outputs the searched image (step S11).

  By such an operation, the user can search for desired information. The reason is as follows. First, the user takes an image of an object for which information is desired. At this time, a similar image is searched based on the feature amount of the image, but the similar image may not necessarily be an image desired by the user. Therefore, in the present invention, an attribute associated with a similar image is referred to and another image associated with the attribute is displayed. The user can select an image according to his / her intention from the displayed images. At this time, if images are displayed together for each attribute, the user can easily select images. The image selected by the user reflects the user's intention. Thus, by performing an image search again based on the attribute of the selected image, it is possible to search for an image or information regarding the image that the user wanted.

  For example, in the above-described example, since the image most similar to the image captured by the user is A, the image A is the “acquired image” described above. However, since the images extracted based on the attributes of the image A include B, C, and E in addition to the image A, these images are displayed (step S6). When the user browses and selects a display image, it is presumed that the image or image information desired by the user relates to the image B or E, not the image A (FIG. 5, step S7). Therefore, the images displayed after the re-search are not the image A but the images B, C, D, and E having similar attributes (FIG. 6, step S11).

  The image or image information desired by the user may need to reflect not only the information about the feature amount obtained from the appearance of the image subject but also the information (attribute) of the object that is the subject. According to the present invention, an image can be searched in consideration of the attribute of the subject of the image, so that the user can perform desired information search.

<Specific Example of Embodiment 1>
A specific example of the first embodiment of the present invention will be supplementarily described with reference to the drawings. FIG. 8 shows an example of correspondence between images and attributes stored in the storage unit 11. Here, “beverage˜” (˜ is a number) indicates an image of the beverage. “Beverage 1” is associated with company A, carbonic acid, beverage, and black as attributes. This can be understood, for example, that the product or the like that is the subject of the image of “beverage 1” is a carbonated beverage manufactured by A company and the color is black.

  In this example, it is assumed that an image related to “beverage 1” is acquired, for example. This includes a case where the user selects an image of “beverage 1” stored in the storage unit 11 by some method. Further, as described above, an image relating to “beverage 1” has been acquired. The image obtained by photographing the subject with the camera and the image stored in the storage unit 11 are collated and “beverage 1” is obtained. This includes the case where the image “is acquired by the image collation unit or the like (steps S1 to S3).

  The attribute extraction unit 12 extracts an attribute associated with the acquired image “beverage 1” (step S4). Thereby, as shown in FIG. 9, the attributes of company A, carbonic acid, beverage, and black are extracted. Next, the image extraction unit 13 extracts an image associated with the extracted attribute (step S5). As a result, as shown in FIG. 9, “beverage 1”, “beverage 2”, and “beverage 3” are extracted for the attribute “Company A”. For the attribute “carbonic acid”, “beverage 1”, “beverage 2”, and “beverage 6” are extracted. For the attribute “beverage”, “beverage 1” “beverage 2” “beverage 3” “beverage 4” “beverage 5” “beverage 6” are extracted. For the attribute “black”, “beverage 1”, “beverage 5”, and “beverage 6” are extracted.

  The image display unit 14 displays the extracted image (step S6). FIG. 10 shows an example in which these images are displayed side by side for each attribute. The size and gap of the image may be changed as appropriate. Although all images are displayed on one screen in FIG. 10, screen scrolling may be required to display all images. Further, although the images are arranged in the vertical direction for each attribute, the images may be arranged in the horizontal direction or in other shapes. For example, as shown in FIG. 13, an image may be displayed as a cluster having a group for each attribute. Although the attribute name is displayed in FIGS. 11 and 13, the attribute name need not be displayed. When an attribute name is displayed, an image corresponding to the attribute may be displayed near the attribute name.

  The user selects an image from the input unit 15 for the image displayed on the display unit 14 (step S7). FIG. 11 shows an example in which images “beverage 2” and “beverage 6” corresponding to the attribute “carbonic acid” and “beverage 5” corresponding to the attribute “black” are selected. In FIG. 11, images of the same beverage are displayed in duplicate. However, since the images are displayed side by side for each attribute, the user intuitively grasps the attributes common to the arranged images by looking at the images. can do. Therefore, even if the attribute name is not displayed on the display unit 14, the user can select a desired image.

  Next, the search unit 16 extracts an attribute associated with the selected image (step S8). As shown in FIG. 12, the attributes associated with the selected images “beverage 2”, “beverage 6” and “beverage 5” are Company A, Carbonated, Beverage, Transparent, Company B, Carbonated, Beverage, Black, Coffee The beverage is black.

  The search unit 16 calculates an attribute having a predetermined number or more of attributes (step S9). Here, the predetermined number is 2. As shown in FIG. 12, two or more of the extracted attributes are carbonated, beverage, and black.

  The search unit 16 searches for an image corresponding to the calculated attribute (step S10). Since the images corresponding to all the attributes of carbonic acid, beverage, and black are “beverage 1” and “beverage 6”, the search unit 16 extracts these images from the storage unit 11.

  Through such a series of operations, the user can obtain a desired image. The reason is as follows. First, it is assumed that the user wants to obtain information regarding a black carbonated drink. Therefore, when a user finds a black carbonated drink product, the user acquires an image of the product using a camera or the like. At this time, according to normal image collation, an image of “beverage 1” having an appearance similar to that of the product can be obtained. On the other hand, since the user wants information on the product of the black carbonated drink, the user may desire an image of the black carbonated drink in addition to “Beverage 1”. In that case, according to the present invention, an image of “beverage 6” which is a black carbonated beverage can be obtained by the above-described processing. Therefore, the user can also obtain information regarding the black carbonated drink regardless of the appearance of the product.

  As described above, the present invention can search for an image in consideration of the attribute of the image (subject), so that the user can search for desired information.

<Embodiment 2>
Next, a second embodiment of the present invention will be described. The present embodiment is different from the above example in that the attributes described in the first embodiment have a hierarchical structure. Below, it demonstrates focusing on a different point from Embodiment 1. FIG.

  FIG. 14 shows an example of attribute hierarchization. FIG. 14 shows, for example, that the attributes 11, 12, and 13 exist in the immediately lower hierarchy of the attribute 1. FIG. 14 shows that, for example, the upper layer of the attribute 1111 is the attribute 111, the attribute 11, and the attribute 1. The attributes in the present embodiment have such a hierarchical structure, and there are upper and lower attributes in the own attributes. Information indicating such attribute hierarchization is stored in the storage unit 11 to the external storage unit.

  In the present embodiment, the attribute extraction unit 12 also extracts higher-level attributes. This will be described using a specific example. FIG. 15 shows a hierarchical example related to the genre attribute of food. Here, sushi, eel and tempura are positioned in the lower hierarchy of Japanese food, and tuna, shrimp and how much are positioned in the lower hierarchy of sushi. These correspondences are stored in the storage unit 11 and other storage units. FIG. 16 shows the correspondence between images and attributes stored in the storage unit 11. Here, it is assumed that the tuna sushi photo 1 is acquired by the information processing apparatus 1. In this case, in the above-described embodiment, the attribute extraction unit 12 extracts “tuna sushi photo 1” and “tuna sushi photo 2” corresponding to the attribute “tuna”. On the other hand, the attribute extraction unit 12 in the present embodiment also extracts higher-level attributes in addition to the attribute “tuna”. In this example, the attribute “sushi” and the attribute “Japanese food” are higher layers than the attribute “Tuna”. Therefore, the attribute extraction unit 12 extracts tuna, sushi, and Japanese food for the attribute.

  Next, the image extraction unit 13 extracts an image corresponding to the extracted attribute. In this example, images corresponding to the attributes of tuna, sushi, and Japanese food are extracted.

  Next, the display unit 14 displays the extracted images collectively for each attribute. FIG. 17 shows a display example. As shown in FIG. 17, an image corresponding to each attribute of tuna, sushi, and Japanese food is displayed. The user selects an image via the input unit 15. The subsequent operations of the search unit 16 and the output unit 17 are the same as those in the first embodiment.

  FIG. 18 shows an operation example of this embodiment. Steps S1 to S3 are the same as those in the first embodiment. Next, in step S21, the attribute extraction unit 12 extracts an attribute associated with the image and an attribute located in a higher hierarchy of the attribute. The subsequent operation is the same as that after step S5 in the first embodiment.

  An example of use of this embodiment will be described. For example, the user photographs tuna sushi with the camera of the information processing apparatus 1. As a result, the information processing apparatus 1 acquires the “tuna sushi photo 1” having high similarity to the tuna sushi as described above. Thereafter, various images are displayed on the display unit 14 as shown in FIG. If the image selected by the user is a "photo with multiple nigiri sushi" or "a roll of sushi", the user may want information about the sushi image, not just the tuna sushi. I understand. Therefore, in subsequent information retrieval, it is possible to perform information retrieval regarding sushi in general, not tuna sushi. For example, if a URL (Uniform Resource Locator) is stored in the storage unit 11 in association with each image, the output unit 17 may directly present the URL destination information to the user in step S11.

  According to the present embodiment, it is possible to present information to the user at an appropriate hierarchical level by hierarchizing attributes. Therefore, information retrieval desired by the user can be performed in consideration of not only the characteristics of the image itself but also the attributes of the subject of the image.

<Embodiment 3>
Next, a third embodiment of the present invention will be described. The information processing apparatus 1 according to the present embodiment includes a storage unit 11, an attribute extraction unit 12, an image extraction unit 13, a display unit 14, an input unit 15, a search unit 16, and an output unit 17. .

  The storage unit 11 stores images and attributes in association with each other. The attribute extraction unit 12 extracts an attribute corresponding to the acquired image from the storage unit 11. Note that the attribute extraction unit 12 may extract attributes by analyzing an image. That is, the attribute extraction unit 12 analyzes attributes from a predetermined viewpoint with respect to the acquired image. The predetermined viewpoint is, for example, a feature amount such as a color, a logo, or a shape of the subject. In this case, the attribute extraction unit 12 may extract an attribute analyzed from a predetermined viewpoint without extracting the attribute corresponding to the acquired image from the storage unit 11. As described above, the attribute extracting unit 12 extracts an attribute from an image at least through the storage unit 11 and may not be used. These are collectively referred to as “extract attributes from an image”. The image extraction unit 13 extracts an image associated with the extracted attribute from the storage unit 11. The display unit 14 displays the extracted image. The input unit 15 receives selection of the displayed image. The search unit 16 re-extracts the image from the storage unit 11 based on the attribute associated with the selected image.

  According to such a configuration, the image can be searched in consideration of the attribute of the image (subject), and thus the user can search for desired information.

  While the present invention has been described with reference to the embodiments, the present invention is not limited to the above embodiments. The configuration of the present invention can be variously modified by those skilled in the art within the scope of the present invention. For example, what is described as being composed of one component can be composed of a plurality of components. For example, as shown in FIG. 20, the information processing apparatus is divided into two, and the information processing apparatus 2 includes an image acquisition function, an image communication function (communication unit), an image display selection function, and the like (display unit 14, input unit 15). , Only the output unit 17) may be provided. In this case, the information processing apparatus 1 has a function of performing the above-described search processing on an image acquired through communication and returning a search result (communication unit, feature amount extraction unit 18, collation unit 19, attribute extraction unit 12, storage Section 11, image extraction section 13, search section 16). That is, an information processing system including two information processing apparatuses is realized. More specifically, the information processing device 2 receives a selection of the displayed image and a transmission unit (communication unit) that transmits an image to the information processing device 1, a display unit 14 that displays the image, and the information processing device 1 And an output unit 17 for outputting the received search results. Although the input unit 15 is different from the above-described embodiment in that the input unit 15 includes a communication function for transmitting the selected image, the communication unit may perform communication. On the other hand, the information processing apparatus 1 includes a storage unit 11 that stores an image and an attribute in association with each other, and an attribute extraction unit 12 that extracts an attribute corresponding to the image received from the information processing apparatus 2 from the storage unit 11. In addition, the information processing apparatus 1 includes an image extraction unit 13 that extracts an image associated with the extracted attribute from the storage unit 11 and transmits the image to the information processing apparatus 1. Although the image extraction unit 13 is different from the above-described embodiment in that it has a communication function, communication may be performed by the communication unit. Further, the information processing apparatus 1 includes a search unit 16 that re-extracts an image from the storage unit 11 based on an attribute associated with the image selected by the information processing apparatus 2. According to such a configuration, the effect of the present invention can be realized by the information processing device 2 while simplifying the configuration of the information processing device 2 itself. As described above, the configuration of the present invention can be variously modified by those skilled in the art within the scope of the present invention.

DESCRIPTION OF SYMBOLS 1 Information processing apparatus 11 Storage part 12 Attribute extraction part 13 Image extraction part 14 Display part 15 Input part 16 Search part 17 Output part 18 Feature-value extraction part 19 Collation part

Claims (10)

Attribute extraction means for extracting attributes from the acquired image;
Image extracting means for extracting an image associated with the extracted attribute from the storage means;
Display means for displaying the extracted image;
Input means for accepting selection of the displayed image;
Search means for re-extracting the image from the storage means based on the attribute associated with the selected image;
An output means for outputting the search results;
An information processing apparatus comprising:   The information processing apparatus according to claim 1, wherein the display unit displays the extracted image and the attribute in association with each other. The attribute is stored in the storage means in association with another attribute,
The information processing apparatus according to claim 1, wherein the attribute extraction unit extracts the attribute corresponding to the acquired image and the other attribute associated with the attribute from the storage unit. A transmission means for transmitting an image;
Display means for displaying an image;
Input means for accepting selection of the displayed image and transmitting it to the second information processing apparatus;
An output means for outputting the received search results;
A first information processing apparatus comprising:
Attribute extraction means for extracting attributes from the received image;
Image extracting means for extracting an image associated with the extracted attribute from the storage means and transmitting it to the first information processing apparatus;
Search means for re-extracting an image from the storage means based on the attribute associated with the image selected by the first information processing apparatus;
An information processing system comprising: a second information processing apparatus comprising: An attribute extraction step for extracting attributes from the acquired image;
An image extraction step of extracting from the storage means an image associated with the extracted attribute;
A display step for displaying the extracted image;
An input step for accepting selection of the displayed image;
A search step of re-extracting the image from the storage means based on the attribute associated with the selected image;
An output step for outputting the search results;
An information processing program that causes a computer to execute.   The information processing program according to claim 5, wherein in the display step, the extracted image and the attribute are displayed in association with each other. The attribute is stored in the storage means in association with another attribute,
The information processing program according to claim 5 or 6, wherein, in the attribute extraction step, the attribute corresponding to the acquired image and the other attribute associated with the attribute are extracted from the storage unit. Extract attributes from the acquired image,
Extract the images associated with the extracted attributes,
Display the extracted image,
Accept selection of displayed image,
Based on the attribute associated with the selected image, re-extracting the image,
An information processing method for outputting search results.   The information processing method according to claim 8, wherein the extracted image and the attribute are displayed in association with each other. Storing the attribute in association with another attribute;
The information processing method according to claim 8 or 9, wherein the attribute corresponding to the acquired image and the other attribute associated with the attribute are extracted.

Images