Abstract: An image processing section 10 calculates degree of similarity among a plurality of image frames of dynamic image data, determines scene-change frames based on the calculated degree of similarity, and performs automatic editing and preparation of a digest dynamic image of the dynamic image data by merging a specified duration of frames, giving priority to scenes whose scene-change frame has a low degree of similarity to an immediately preceding frame or some preceding frames, or by merging, from scenes delimited by a scene change, a specified duration of frames having a degree of similarity in keeping with the user's indication of whether or not a “little change digest” or a “much change digest” is to be prepared.

Abstract: An image processing section 10 calculates degree of similarity among a plurality of image frames of dynamic image data, determines scene-change frames based on the calculated degree of similarity, and performs automatic editing and preparation of a digest dynamic image of the dynamic image data by merging a specified duration of frames, giving priority to scenes whose scene-change frame has a low degree of similarity to an immediately preceding frame or some preceding frames, or by merging, from scenes delimited by a scene change, a specified duration of frames having a degree of similarity in keeping with the user's indication of whether or not a “little change digest” or a “much change digest” is to be prepared.

Abstract: This invention realizes, with low cost, an image search apparatus which can quickly obtain adequate search results upon searching for document images which are identical or similar to a predetermined document image. To this end, an image search apparatus of this invention has the following arrangement. That is, an image search apparatus for searching for images similar to a query image, includes a region division unit (204, 209) which extracts a plurality of partial regions which form an image, a region feature extraction unit (205, 210) which calculates the number of partial regions and center of gravity positions, and a feature amount updating unit (206) which saves the calculated number of partial regions and center of gravity positions in an image region management DB (216) as an index.

Abstract: This invention has as its object to allow high-precision and high-speed retrieval in consideration of position information of image feature amounts upon retrieving similar images based on image feature amounts, even when the position information includes some differences. To achieve such object, an image processing apparatus according to this invention has the following arrangement.

Abstract: An apparatus for generating a scaled image divides an image, which comprises a plurality of pixels, into a plurality of blocks by partitioning the image vertically and horizontally, whereby the color space of this image is divided into a plurality of subspaces, referred to as bins. The apparatus applies a histogram analysis, on a bin-by-bin basis, to the pixels constituting a block of interest among the plurality of blocks. Then, using the result of the histogram analysis, the apparatus decides the representative color of the block of interest in accordance with the average color of pixels belonging to a most frequent bin among the plurality of bins. A scaled image of this image is obtained by applying the above operation to all of the blocks.

Abstract: There is provided a scene change detection method which is independent from an encoder of a file, and can assure high real-time performance and effective, quick processes, and an image processing apparatus that can implement the method. Frame image data is extracted from moving image data (S11), the frame image data is segmented into a plurality of blocks (S12), labels are assigned in accordance with feature amounts acquired in units of blocks (S13), a sequential label set is generated by arranging the assigned labels in a predetermined block order (S14), similarities between the generated sequential label set and sequential label sets of a previous frame image data group are computed by two-dimensional DP matching and a scene change frame in the moving image is detected from a computed similarity group (S15, S16), and the detected scene change frame information is stored in correspondence with the frame image data.

Abstract: There is provided a scene change detection method which is independent from an encoder of a file, and can assure high real-time performance and effective, quick processes, and an image processing apparatus that can implement the method. Frame image data is extracted from moving image data (S11), the frame image data is segmented into a plurality of blocks (S12), labels are assigned in accordance with feature amounts acquired in units of blocks (S13), a sequential label set is generated by arranging the assigned labels in a predetermined block order (S14), similarities between the generated sequential label set and sequential label sets of a previous frame image data group are computed by two-dimensional DP matching and a scene change frame in the moving image is detected from a computed similarity group (S15, S16), and the detected scene change frame information is stored in correspondence with the frame image data.

Abstract: This invention provides a document processing apparatus and method for searching, for a specific document image, a database in which a plurality of document images are registered in correspondence with the attributes of partial regions. A document image associated with search is segmented into partial regions. The attribute of each partial region of the segmented document image associated with search is determined. At least one document image is selected from document images registered in the database on the basis of the number of partial regions for each attribute in the document image associated with search.

Abstract: A reference comparison image obtained from a printed material is input. The grayscale feature amount of the reference comparison image is extracted. Using the extracted grayscale feature amount, a target comparison image corresponding to the reference comparison image is retrieved from a plurality of electronic data stored as target comparison images in a storage medium. The retrieved image is extracted from the storage medium and processed.

Abstract: This invention is to simplify operations for photographing a subject and acquiring radio tag information. In this invention, when a radio tag information registration photographing mode is selected, and it is detected that the photographing button (shutter button) is pressed halfway, a radio tag detector generates a radio wave that excites a radio tag. Whether a response from the radio tag is received is then determined. When a response is received from the radio tag, and a radio tag ID can uniquely be decided, a status “photographing OK” is indicated. When the photographing button in the half-pressed state is pressed completely, image sensing processing is executed. Radio tag information and obtained image information are stored in an information format, in which they are paired.

Abstract: In an image processing apparatus, a moving picture storage module stores moving picture data. A scene designation module designates at least one scene in the moving picture data, and sets a key frame and importance level of the designated scene. A frame feature extraction module acquires an image feature amount of the designated key frame. A scene feature information storage module generates scene feature information including the duration, key frame, importance level, and image feature amount of the key frame of the scene designated by the scene designation module, and stores the generated information in a memory in correspondence with the moving picture data. Based on the scene feature information, digest playback for playing back only principal part of the designated moving picture data is executed, or desired moving picture data is found by a similar image search using the key frame.

Abstract: An image data selecting unit selects image data which stores image attribute information to be additionally registered, and image data to which new image attribute information is to be additionally registered, from those displayed by a search result display unit. An image attribute information additional registration unit additionally registers image attribute information selected by an image attribute information selecting unit to the image data which is selected by the image data selecting unit and to which the new image attribute information is to be additionally registered. By automatically assigning attribute information which is not assigned upon registration of image data, the load on the user upon registration is reduced.

Abstract: A reproduction apparatus includes a prediction unit that predicts a reproducible time based on remaining power of a battery and a decision unit that decides whether the digital data selected by the user can be reproduced to the end or not based on the reproducible time, wherein when the digital data cannot be reproduced to the end, an alarm is issued indicating that the digital data cannot be reproduced to the end.

Abstract: This invention discloses an image processing apparatus which divides moving image data at appropriate positions and sets key frames at appropriately distributed positions in the entire moving image. This image processing apparatus records action information (e.g., a zoom action) associated with actions made during image sensing and environment information (e.g., rotation information due to a pan action) associated with an image sensing environment during image sensing as additional information of the moving image data. Then, the apparatus divides moving image data for one shot into a plurality of sub-shots (S807, S811) in accordance with at least one of the recorded action information and environment information (S802-S806, S808-S810).

Abstract: A document management system which can flexibly cope with an access right range of a secret document while efficiently sharing document data is provided. The document management system has a data server, a full-text search service server connected to the LAN, and a fire wall arranged between the full-text search service server and the data server. When the user wants to refer to document/document image data accumulated in the data server, a client terminal designates a character train included in the document/document image data to be referred to, thereby performing the searching process. When the user wants to designate an access-limited character train as a search word, a password for the access-limited character train is simultaneously designated. When the access-limited character train and the password are not designated, the document including the access-limited character train is not displayed as a search result but is seen as if the document including the access-limited character train does not exist.

Abstract: A reproduction apparatus that requests a distribution apparatus to distribute digital data selected by the user, comprises a prediction unit that predicts a reproducible time using remaining power of a battery and a determination unit that determines whether the digital data can be reproduced to the end or not based on the reproducible time. When it is determined that the digital data cannot be reproduced to the end, an alarm is issued indicating that the digital data cannot be reproduced to the end.

Abstract: The two-dimensional power spectrum of an input image, which is obtained by computing its two-dimensional Fourier transform, is segmented into a plurality of blocks (5×5) on the two-dimensional coordinate system, and the standard deviations of power spectrum components of blocks (5×3) of interest of those segmented blocks are computed. By masking the computed standard deviations in units of blocks (matrix of standard deviations) using predetermined mask patterns prepared in units of directions of interest, the sums of the standard deviations are computed as feature amounts in units of directions, and the directionality of the input image is determined based on the feature amounts. The feature amounts computed for the input image and the directionality determination result are stored in correspondence with each other, and a similar image search is made using the stored information.

Abstract: In a moving image playback apparatus, periods A which represent human utterance periods, and other periods B are determined on the basis of sub-information contained in moving image data. Based on the moving image data, periods A undergo high-speed moving image playback with playback voice within the speed range from a normal speed to a predetermined speed (e.g., 1.5 to 2 times of the normal speed) at which the user can recognize playback contents, while periods B undergo high-speed moving image playback with at least playback voice in a small tone volume or silent high-speed moving image playback at a speed (e.g., 5 to 10 times of the normal speed) higher than the predetermined speed. During the playback, the moving image playback speeds can be adjusted in accordance with user attribute information registered in a user profile (14).

Abstract: An image feature amount extraction unit and feature amount label matrix generation unit generate a label sequence from image data. An image management DB stores image data stored in an image storage unit and label sequences corresponding to the image data in correspondence with each other. A label sequence index registers, in units of labels, image data including the labels and the numbers of labels included in those image data. Upon search, a pattern matching unit extracts label sequences which are similar to the label sequence of a query image to some extent from the label sequence index, computes similarities between the extracted label sequences, and the label sequence of the query image, and outputs images, in which the computed similarities exceed a predetermined value, as search results.

Abstract: Image data and their image feature amounts are managed in correspondence with each other using an image storage unit and an information management DB. A desired one of query conditions each of which is defined by image feature amounts set with ambiguity levels is designated by an input unit. A matching unit matches the image feature amounts that define the designated query condition, with corresponding managed image data. Image data as search results are output to a display on the basis of the matching results.