Abstract: A map generation system comprising: a mobile device for acquiring location data of a vehicle and a status of the vehicle at a time of acquisition of the location; and a server for processing the acquired location data of the vehicle. The server comprises an input interface, a first storage unit, a processor and a second storage unit. The server includes a management unit for collecting a plurality of pieces of the track data obtained by a motion of the vehicle, an extraction unit for extracting feature points of the plurality of pieces of the track data on a road from which the plurality of pieces of the track data are collected to calculate a Spline curve satisfying the extracted feature points, and an update unit for adding the calculated Spline curve as a lane central line to the digital road map to update map data.

Abstract: A vehicle support system for supporting a man in safely crossing a road without crosswalks installed is provided.

Abstract: A collision avoidance assisting system for a vehicle, for expecting a risk of colliding upon a moving object (or a moving obstacle), including a pedestrian, more correctly, but without annoying a driver, excessively, by estimating the risk to be excessively high, comprises a moving object detecting means for detecting a moving object existing on periphery of the vehicle; a footway boundary detecting means for detecting a position and a configuration of a footway boundary object on periphery of the vehicle; a risk estimation means for estimating a risk that the moving object detected by said moving object detecting means collides on the vehicle; and an alarm means for calling an attention to a driver of the vehicle, upon basis of the risk of collision estimated by the risk estimation means, wherein the risk of collision between the moving object, which is detected by the moving object detecting means, and that vehicle is estimated by taking at least the position information of the moving object, the position i

Abstract: The mosaicing curling effect which causes a mosaic strip to curl is effectively mitigated in a system for generating a mosaic image from sequential images which partially overlap with one another. The system has a matrix estimating unit, an adjustment element calculating unit, and an image projecting unit. The matrix estimating unit estimates a transformation matrix for transformation between two adjacent images taken out from among the sequential images. The adjustment element calculating unit calculates an adjustment element of the estimated transformation matrix by decomposing the transformation matrix into a rotational component and a perspective component. The image projecting unit projects each image on the mosaic plane using the transformation matrix to which the calculated adjustment element has been applied.

Abstract: A map generation system comprising: a mobile device for acquiring location data of a vehicle and a status of the vehicle at a time of acquisition of the location; and a server for processing the acquired location data of the vehicle. The server comprises an input interface, a first storage unit, a processor and a second storage unit. The server includes a management unit for collecting a plurality of pieces of the track data obtained by a motion of the vehicle, an extraction unit for extracting feature points of the plurality of pieces of the track data on a road from which the plurality of pieces of the track data are collected to calculate a Spline curve satisfying the extracted feature points, and an update unit for adding the calculated Spline curve as a lane central line to the digital road map to update map data.

Abstract: A character recognition method that is robust under an unknown illumination condition is provided. An apparatus for realizing such robust character recognition includes plural different binarization, means for synthesizing character sub-image candidates that have been obtained from the binarization units, and means for analyzing character sub-image candidates and for recognizing an image as a character string consisting of character sub-image candidates.

Abstract: A character recognition method that is robust under an unknown illumination condition is provided. An apparatus for realizing such robust character recognition includes plural different binarization, means for synthesizing character sub-image candidates that have been obtained from the binarization units, and means for analyzing character sub-image candidates and for recognizing an image as a character string consisting of character sub-image candidates.

Abstract: A method and a machine for generating a dictionary of address phrase expressions. One embodiment of the invention includes an apparatus for generating a dictionary of target phrases that includes an input interface for receiving as its input a first address phrase included in a list of address phrase expressions, a memory for storing a dictionary of address phrase variants, including rules for generating variants of address phrase expressions, and a processing device for generating variants of address phrases which generates a second address phrase which is different in expression from the first address phrase to output the second address phrase to a storage device holding the dictionary of target phrases, based on the input first address phrase, and the knowledge of rules about variants included in the dictionary of address phrase variants.

Abstract: An address reader method and apparatus for recognizing a receiver address on a surface of mail. An image of the surface of the mail is input and segmented into at least one character string candidate. At least one address area candidate is extracted from the image based upon the segmented character string candidate. One address area candidate extracted from the image is selected as a receiver address by analyzing each address area candidate based on predetermined position information indicating a usual position of a receiver address area, character direction information indicating a character direction of a character string appropriate for the predetermined position information, and key character string information indicating a character string most likely to exist in a receiver address. Characters in character strings of the selected address area candidate are recognized as a receiver address.

Abstract: An address reader method and apparatus for recognizing a receiver address on a surface of mail. In the invention an image of the surface of the mail is input and segmented into at least one character string candidate. At least one address area candidate is extracted from the image based upon the segmented character string candidate. One of the address area candidates extracted from the image is selected as a receiver address of the mail by analyzing each of the address area candidates based on predetermined position information indicating a usual position of a receiver address area, character direction information indicating a character direction of a character string appropriate for the predetermined position information, and key character string information indicating a character string most likely to exist in a receiver address. Characters in character strings of the selected address area candidate are recognized as a receiver address which is used to sort the mail.

Abstract: An address reader method and apparatus for recognizing a receiver address on a surface of mail. In the invention an image of the surface of the mail is input and segmented into at least one character string candidate. At least one address area candidate is extracted from the image based upon the segmented character string candidate. One of the address area candidates extracted from the image is selected as a receiver address of the mail by analyzing each of the address area candidates based on predetermined position information indicating a usual position of a receiver address area, character direction information indicating a character direction of a character string appropriate for the predetermined position information, and key character string information indicating a character string most likely to exist in a receiver address. Characters in character strings of the selected address area candidate are recognized as a receiver address which is used to sort the mail.

Abstract: A character reading method has enhanced character segmentation accuracy and character string recognition accuracy for reading correctly hand-written addresses on postal matters. The method extracts provisional character patterns from image information of the address character string (step 206), creates a table 219 of tentative character patterns and implements the character classification for the tentative character patterns (step 207), extracts, specifically for characters of the street number portion of the address character string, periphery information (vertical and horizontal lengths, vertical/horizontal length ratio, pattern spacings, etc.) of tentative character patterns (step 212), and segments the character string into characters accurately based on the information (step 215).

Abstract: In an apparatus for and a method of processing document information, according to a requirement of a writer of document information, the document information is generated, referenced, and re-constructed. Further, according to a requirement of a reader of the document information, the information is referenced and re-constructed. The apparatus includes a reader terminal including means for inputting a requirement of a reader of document information and means for outputting document information referenced and re-constructed according to the requirement, and a writer terminal for inputting therefrom a requirement of a writer of document information and creating document information. The apparatus further includes a document processing unit connected to the reader terminal and the writer terminal.

Abstract: A document recognition system includes various recognitive steps for document recognition, and various correctional steps corresponding to the recognitive steps. The operation modes of the system are a "sequential mode" (sequential recognition operation) in which the respective recognitive steps are executed in "step by step" fashion, an "auto mode" (batch recognition operation) in which all the recognitive steps are collectively executed, and a "retry mode" (re-recognition operation) in which the execution of any of the correctional steps is automatically followed by the execution of a necessary one of the recognitive steps. In the "sequential mode", any of the recognitive steps having been executed can be shifted, not only to the correctional step corresponding to the executed recognitive step, but also to the correctional step preceding the execution.

Abstract: A file document image input can have shading removed to produce a deshaded image that is useful for highly efficient compression encoding, to be thereafter stored and transmitted in such efficient encoded form. When the image is retrieved or received, the decoded and deshaded image may have shading returned to it by combining with a shaded template image stored in the template image memory or by synthesizing shading in specified regions. By removing shading from regions, optical character recognition, shading identification or other processing such as smear prevention can be enhanced.