Abstract: Embodiments disclose methods and apparatuses for camera motion analysis in a video, wherein one of the methods includes: analyzing, video segments with significant movement characteristics and video segments without any significant movement characteristic; for each segment without any significant movement characteristic, if a first motion type corresponding to a preceding neighboring video segment is different from a second motion type corresponding to a succeeding neighboring video segment, lowering detection criterions of the first type and the second type; judging whether the segment without any significant movement characteristic meets the lowered detection criterions; and merging the segment without any significant movement characteristic with a neighboring video segment according to the result of judgment.

Abstract: A computer-readable storage medium storing an image processing program that causes a computer to execute a process includes acquiring the same object identification information included in a plurality of image data items by referring to a storage unit that stores each of the image data items, object identification information that identifies an object included in the image data item, and a location information item that identifies a location of the object in the image data item in association with one another; acquiring the location of the object identified by the acquired object identification information in each of the image data items by referring to the storage unit; computing a difference between the acquired location information items; comparing the difference between the location information items with a predetermined location threshold value; and determining whether the image data items are to be in the same group.

Abstract: An image processing apparatus includes: a storage configured to store, for a plurality of areas in a target image, attributes and patterns associated with the attributes, each the attributes being assigned to each the plurality of areas, and each the pattern being created from areas having an identical attribute among the attributes; and a processor configured to: obtain an area that is specified in the target image and an attribute that is assigned to the specified area, search the storage for a pattern based on similarity between the pattern and a pattern created from a certain number of areas having the assigned attribute; and search for an area in the target image based on similarity between the area and the certain number of areas in accordance with the searched pattern.

Abstract: Embodiments describe an image retrieval apparatus. The image retrieval apparatus includes an unlabelled image selector for selecting one or more unlabelled image(s) from an image database; and a main learner for training in each feedback round of the image retrieval, estimating relevance of images in the image database and a user's intention, and determining retrieval results, wherein the main learner makes use of the unlabelled image(s) selected by the unlabelled image selector in the estimation. In addition, the image retrieval apparatus may also include an active selector for selecting, in each feedback round and according to estimation results of the main learner, one or more unlabelled image(s) from the image database for the user to label.

Abstract: This invention discloses an image retrieval apparatus. The image retrieval apparatus comprises an unlabelled image selector for selecting one or more unlabelled image(s) from an image database; and a main learner for training in each feedback round of the image retrieval, estimating relevance of images in the image database and a user's intention, and determining retrieval results, wherein the main learner makes use of the unlabelled image(s) selected by the unlabelled image selector in the estimation. In addition, the image retrieval apparatus may also include an active selector for selecting, in each feedback round and according to estimation results of the main learner, one or more unlabelled image(s) from the image database for the user to label.

Abstract: An image identifying device includes: a setting unit which sets a section having at least one image in a video; a first recognizing unit which calculates a plurality of feature amounts related to at least the one image and which acquires a plurality of identification results corresponding to each of the feature amounts from an identifier which may identify a plurality of objects belonging to a first category; a selecting unit which selects, based on the identification results, a second category of a third category ; and a second recognizing unit which calculates another feature amount related to an image included in another section and acquires another identification result corresponding to the feature amount from another identifier which may identify the objects included in the second category.

Abstract: A computer readable recording medium stores an information attachment program for attaching meta-information to multimedia data executed by a computer. The program causes the computer to perform an acquisition step of acquiring a search word of a text search done at a search site; a monitoring step of monitoring whether or not a search frequency of the search word acquired in the acquisition step satisfies a predetermined criterion; a determination step of determining whether or not at least a portion of the search word matches a character recognition processing result of the multimedia data when the search frequency of the search word is determined to satisfy the predetermined criterion in the monitoring step; and a registration step of registering the search word as meta-information of the multimedia data when, as a determination result of the determination step, the search word matches the character recognition processing result.

Abstract: A difference emphasizing apparatus aligns a first three-dimensional model and a second three-dimensional model in orientation and position in accordance with a predetermined rule, and gets data of respective apices of the first three-dimensional model and the second three-dimensional model. Based on the gotten data, the apparatus finds a corresponding point on the first three-dimensional model, which corresponds to the apex of the second three-dimensional model in a direction of a particular axis. When the corresponding point is detected, the apparatus calculates a difference between the first three-dimensional model and the second three-dimensional model in the direction of the particular axis based on the corresponding point and the apex of the second three-dimensional model. The apparatus enlarges the difference in the direction of the particular axis, and calculates a position of the apex of the second three-dimensional model after the enlargement.

Abstract: Embodiments disclose methods and apparatuses for camera motion analysis in a video, wherein one of the methods includes: analyzing, video segments with significant movement characteristics and video segments without any significant movement characteristic; for each segment without any significant movement characteristic, if a first motion type corresponding to a preceding neighboring video segment is different from a second motion type corresponding to a succeeding neighboring video segment, lowering detection criterions of the first type and the second type; judging whether the segment without any significant movement characteristic meets the lowered detection criterions; and merging the segment without any significant movement characteristic with a neighboring video segment according to the result of judgment.

Abstract: The invention provides a method and apparatus for acquiring descriptive information of a plurality of images and an image matching method. The method for acquiring descriptive information of a plurality of images includes: performing a feature point detection with respect to each image of the plurality of images, so as to obtain a plurality of feature points of each image; acquiring 0-level descriptive information of the plurality of images; and the following steps are performed for each image: performing a division of the image for the (n?1)th time, so as to obtain a plurality of (n?1)-level sub-images of the image; and (n?1)-level descriptive information of the image is generated in accordance with a plurality of nth local feature descriptors for the image and a plurality of nth visual words, where n=2,3, . . . , K+1, and K is a positive integer.

Abstract: Embodiments disclose a method and apparatus for detecting a camera motion type in a video, the method including: estimating a first zoom motion parameter between adjacent frames in the video; estimating a second zoom motion parameter between frames having an interval of a preset number in a corresponding video segment when the first zoom motion parameter meets a first preset condition; and identifying the camera motion type of the video segment as slow zoom when the second zoom motion parameter meets a second preset condition. With the embodiments of the invention, the motion type of a camera in the video can be detected more effectively and accurately.

Abstract: A rule discovery program which enables discovery of a rule by automatically searching for a feature portion which is effective for generation of a rule in multimedia data. When sample data items are inputted, a search unit selects evaluation positions on a data array constituting each of the sample data items so as to generate a selection pattern. Next, an integration unit integrates the evaluation positions in the selection pattern so as to generate a predetermined number of evaluation regions, and a rule-candidate generation unit generates a rule candidate indicating a relationship common to the sample data items. A rule-candidate evaluation unit evaluates the generated rule candidate, and an output unit outputs, as a rule, the rule candidate when the rule candidate satisfies a predetermined criterion.

Abstract: A computer-readable storage medium storing an image processing program that causes a computer to execute a process includes acquiring the same object identification information included in a plurality of image data items by referring to a storage unit that stores each of the image data items, object identification information that identifies an object included in the image data item, and a location information item that identifies a location of the object in the image data item in association with one another; acquiring the location of the object identified by the acquired object identification information in each of the image data items by referring to the storage unit; computing a difference between the acquired location information items; comparing the difference between the location information items with a predetermined location threshold value; and determining whether the image data items are to be in the same group.

Abstract: The present invention relates to three-dimensional model retrieval apparatus and method.

Abstract: A multimedia integrated retrieval apparatus includes a feature value extracting unit calculating a feature value of single media data; a media information storage unit storing the feature value and storing composite media data in association with the single media data; a retrieval processing unit identifying other pieces of single media data corresponding to the single media data; a retrieval controlling unit, generating structural body data that includes a first node indicative of the single media data, a second node indicative of the another piece of single media data, a first link connecting the first node to the second node, a third node indicative of another composite media data, and a second link connecting the third node to the second node, if the another piece of composite media data including the another piece of single media data is present; and a display unit displaying the structural body data.

Abstract: The present invention discloses a shape comparison apparatus and method based on contour decomposition and correspondence. The apparatus comprises a polygonal approximation unit for approximating an image object contour as a polygon, namely representing the image object contour into an ordered contour primitive sequence; an attribute generation unit for calculating attribute value for contour primitive and contour primitive composition; and a comparison unit for establishing correspondence of polygons and hence calculating similarity between contours. Preferably, the apparatus further comprises an image object contour extraction unit for extracting, in the case the input into the apparatus is an image object rather than an image object contour, an image object contour of an image object inputted into the apparatus.

Abstract: According to an aspect of an embodiment, a method for searching image data representing an image from a database by using a query image, the image data including information indicative of a shape of a contour of the image, comprising: obtaining a query image data representing the query image; extracting information indicative of a shape of a contour of the query image; and determining the image data in the database on the basis of correlation of the topological characteristics of the shapes of the contours of the images and the query image.

Abstract: A design support apparatus extracts feature data corresponding to design data to be searched upon receiving the design data to be searched. The apparatus checks the extracted feature data against the feature data associated with the feature associated information, ordering the design data associated with the feature associated information in descending order of similarity to the design data to be searched, retrieving one piece of the ordered design data. The apparatus generates a classification hierarchy consisting of pieces of classification data obtained by classifying a set of the retrieved design data based on a degree of feature similarity using the feature data associated with the feature associated information. The apparatus selects the design information closely associated with the classification data by fetching the design information corresponding to the design data contained in the classification data from the design associated information associating the design data and the design information.

Abstract: This invention is to enable retrieving of a content the searcher imagines in mind. The search method includes: obtaining a query brain image representing a brain activity state of a searcher when perceiving or imagining the content to be retrieved; identifying the content corresponding to the query brain image by using a structure associating a content with a brain image representing the brain activity state when perceiving the content; and outputting the content corresponding to the query brain image. Thus, by using the query brain image, without specifically indicating the content such as a drawing, the searcher can extract the pertinent content only by imaging the content.

Abstract: A pattern retrieving unit includes an acquiring unit that acquires a representative pattern image; a setting unit that sets a use condition of a type of shape feature of the representative pattern image; a receiving unit that receives a query pattern image used as a query; a determining unit that determines the type of shape feature of the representative pattern image to be the type of shape feature of the query pattern image, based on the use condition; a retrieving unit that retrieves a pattern image identical or similar to the query pattern image, using determined type of shape feature; and an output unit configured to output a result of retrieval by the retrieving unit.