Abstract: Exemplary embodiments of the invention provide an eye-flow guiding level calculating system which can plan miniaturization and low cost of a device and surely obtain a suitable eye flow. A layout device, first, detects each vertex of an image object as guiding reference points, based on vector image data. And then, for every guiding reference point, two auxiliary lines are virtually formed to intersect the guiding reference point along an outline of the image object. Subsequently, the direction in which a bisector line of an obtuse angle among angles, made by the virtual auxiliary lines, extends outward from the guiding reference point is calculated as an eye-flow guiding direction. Further, for every guiding reference point, the distance from the center G of the image object up to the guiding reference point is calculated as an eye-flow guiding intensity. According to this construction, it is possible to quantitatively calculate in which direction the image object tends to guide the eye-flow.

Abstract: Aspects of the invention can provide a sight line inducing information display device, a sight line inducing information display program and a sight line inducing information display method able to precisely estimate the flowing direction of a sight line of an observer from the arrangement of partial areas itself. After image information of a visual document, etc. is divided into partial areas and is recognized, an initial noticing probability every partial area, its sight line inducing direction and its probability can be respectively calculated. The initial noticing probability, its sight line inducing direction and the probability can be respectively displayed. On the basis of these displays, the flowing path of the sight line of the user observing this visual document can be estimated. Thus, the flowing direction of the sight line of the observer can be precisely estimated from the arrangement of the partial areas itself.

Abstract: The invention can provide an image processor, an image processing method and a program capable of reducing an oddness of appearance when plural images of different color tones photographed in different conditions, etc. are arranged on the same page. The image processor can unify the color tones of plural correcting object images, and is characterized in that a reference color which is a representative color of the correcting object image is set for every correcting object image, and the color tone of a partial area or an entire area of the correcting object image is corrected so as to conform the reference color for every correcting object image.

Abstract: To provide an image processing apparatus, an image processing method, and an image processing program of detecting an obscure portion that cannot be divided by clear edges as a boundary region and of controlling image information on the boundary region so as to be suitable for a background image in the case of dividing a target image into image object regions, a boundary region having intermediate characteristics between the characteristics of a target image object and the characteristics of an adjacent image object that are two adjacent image objects is detected from a target image. Pixel information on the pixels that belong to the boundary region is generated based on the changes in the characteristics of the pixels from the pixels of the boundary region which contact the target image object region having the characteristics of the target image object to the pixel of the boundary region that contacts an adjacent image object region having the characteristics of the adjacent image object.

Abstract: The invention provides an image processing device, an image processing method, and a program with which the color of a reproduced image that is reproduced based on the corrected pixel information can be brought close to the memorized color by correcting the pixel information of the pixels constituting an image region based on the region characteristics of this image region for each image region obtained by segmenting the target region.

Abstract: To provide a document extracting device, a document extracting program, and a document extracting method, having a low cost and a small amount of computation required to extract documents, a document extracting device includes similarity computing device computing all degrees of similarity between a plurality of documents to be candidates for extraction, and document extracting device to extract a combination of documents whose sum of the degrees of similarity between the documents computed by the similarity computing device is the smallest when any number of documents are extracted from among a group of the documents. As a result, since the cost required for works of giving keywords to the respective documents is not required to extract the documents, and even when the number of documents is increased, the amount of computation required to extract the documents is not increased extremely.

Abstract: The invention provides a similarity calculation device which is well suited to effectively calculate the similarities of words in such a way that the words are impartially reflected on the calculation of the similarities in correspondence with their frequencies of occurrences. The invention can include first, document vectors that are generated on the basis of a plurality of document data. Each of the document vectors can have elements corresponding to respective morphemes, and each of the elements can be calculated so as to become a value conforming to the frequency of occurrences of the corresponding morpheme. Subsequently, word vectors are generated using the transposed matrix of a document word matrix in which the generated document vectors are gathered.

Abstract: The invention provides a data management device which is well suited to grasp featuring parts from among a huge amount of data, which are capable of enhancing the reliability of extraction and which can immediately comply with a user's request. In particular, feature data for calculating the temporal transition of similarities concerning the contents of document data can be extracted from the document data of a document data registration database, the change point of the similarities can be specified on the basis of the extracted feature data, and document data are retrieved from within the document data registration database on the basis of the specified change point. In the retrieval, the document data which belong to the specified change point or the vicinity thereof can be retrieved.

Abstract: The invention concerns quantitatively evaluating retrieval performance of retrieving systems that allow information retrieval when natural sentences are input as retrieval requests. Text and a title (heading) thereof are recognized as a pair of documents, and multiple documents individually having the texts and the headings are prepared as retrieval-target documents. In this, for example, each of the headings is used as contents of a retrieval request, and each of the texts is used as retrieval-target information. One of the headings is input to a retrieving device, and retrieving processing is performed, results of retrieval performed ranked for the headings according to the above, and retrieval-process evaluation is performed according to the ranks. The same processing is repeated for the following headings, and total retrieval processing is performed for the retrieving system according to the individual results of retrieval.

Abstract: [Object] To provide a differential communication system that is preferable for performing differential communication in a dynamically configured network.

Abstract: A graphic image retrieving system suitable for sensuous image of a hair style graphic image advantageous in view point of work load and time, is provided. An expression word map 60, in which a plurality of expression words are arranged on a virtual space 50 depending upon degree of association of sensuous image, and hair style graphic images jpg01 to jpg09 are stored with correspondence with the expression words. When graphic image map 80 is generated, coordinates of the expression word corresponding to each hair style graphic image jpg01 to jpg09 in the virtual space 50 is derived with reference to expression word map 60. On the basis of the given retrieving word, when sensuous image retrieval of the hair style graphic image is performed, the coordinates of the retrieving word in the virtual space 50 is derived with reference to the expression word map 60.

Abstract: When searching information from the Internet, for example, it is difficult to effectively and accurately obtain the information which the user desires. Moreover, it is also difficult to display the searched information which the user desires. Several types of processing managers (called editors) are described with icons and displayed, respectively, on the display screen of the personal computer or the like, and characteristics that show what kind of searching and editing each editor performs are also displayed. Searching and editing are performed in accordance with the characteristic of an editor selected by the user, and the edited result is displayed.

Abstract: To provide a service-providing system suited to increase security of a user's privacy by preventing a user's personal information from be externally leaked out.