Abstract: A camera (32) captures successive images of light stripes (22) projected onto an object by a light curtain (18) positioned by a light source positioner (28). A background image is subtracted (616) therefrom, and the resulting image is boosted by binning (618), binarized with a thresholding algorithm (620), skeletonized (622), interpolated (624) and stored (626). Interpolated images are acquired for a plurality of light stripes (22). A processor (30) generates (1604) a 3-D surface model from Cartesian coordinates computed for non-zero camera pixels. A volumetric representation is determined (1610) from the offset of the object surface model relative to a model of a proximate surface, e.g. a seating surface (24). The object is classified (1614), e.g. by a trainable pattern recognitions system, responsive to 3-D shape descriptors (1606) of the 3-D surface model and to the volumetric representation (1610) or portions (1612) thereof.

Abstract: The invention relates to a method for reducing visual artefacts in a digital image, which is coded by blocks (B1, B2, B3, B4) and then decoded. In the method filtering is performed to reduce visual artefacts due to a boundary (R12, R13, R24, R34) between a current block and an adjacent block (B1, B2, B3, B4). The filtering is performed after the current block (B1, B2, B3, B4) is decoded and there is a boundary available for filtering between the current block and a previously decoded block.

Abstract: An obstacle recognition apparatus is provided which can recognize an obstacle by accurately extracting a floor surface. It includes a distance image generator (222) to produce a distance image using a disparity image and homogeneous transform matrix, a plane detector (223) to detect plane parameters on the basis of the distance image from the distance image generator (222), a coordinate transformer (224) to transform the homogeneous transform matrix into a coordinate of a ground-contact plane of a robot apparatus (1), and a floor surface detector (225) to detect a floor surface using the plane parameters from the plane detector (223) and result of coordinate transformation from the coordinate transformer (224) and supply the plane parameters to an obstacle recognition block (226).

Abstract: A mesh is placed over an image of an element thereby dividing the image (element) into a plurality of solids. Each of the solids is then divided equally into the even number of parts. Inclusion-ratio determination-points, which are points where the straight lines and the mesh intercross, are decided. Moreover, it is determined whether the inclusion-ratio determination-points are inside or outside of the element. An analytical model for the element is created based on whether the inclusion-ratio determination-points are inside or outside of the element.

Abstract: For the entropy coding of image data after subjected to orthogonal transforation and quantization, a plurality of entropy coding units are provided in parallel. The plurality of entropy coding units can be operated efficiently and the entropy coding can be executed at high speed.

Abstract: The invention relates to the reading of addresses on mailings whereby the images with the addresses are videocoded in several video-coding sites by means of a job distribution device. At fixed intervals a current individual error rate, for first-pass video coding for each video-coded addresses which are not successful on the first pass in the video coding units with the highest current individual error rates, is determined with respect to the total coding error rate to be maintained, by means of the video coding units coming free which have the lowest current individual error rates.

Abstract: Signals encoded with watermark information are generated and broadcast into a protected area for capture by illicit recording devices along with their intended targets. An illicit recording in which at least a portion of the broadcast watermark signals are recorded is obtained and correlated with a known position of the broadcast watermark signals to yield the location of illicit recording devices. In an alternate embodiment, a surveillance device, being image and time synchronized with a signal broadcasting device, monitors and records the protected area. Illicit recordings containing the broadcast watermark are obtained and correlated with corresponding recordings taken by the surveillance device to identify the location of illicit recording devices. In an alternate embodiment, the surveillance device further monitors the quality of the broadcast watermark signals and adjusts them accordingly to achieve a desired quality level.

Abstract: In a place where the personal authentication is requested, if there occurs an emergency, e.g., an authenticatee is forced to unlock a key under threat against the authenticatee's will, there is provided an urgency report system that has lowered both a danger of an authentication apparatus's false operation and a risk of being detected from those around the authenticatee. In the personal authentication technology based on a finger-vein authentication, the employment of the following methods makes it possible to enter a rescue mode and to issue an urgency report: Actively deforming the finger-vein pattern in captured image, pushing a switch, which becomes a trigger for starting the authentication, longer than a predetermined time, or using a rotational motion of the finger.

Abstract: Demosaicing of graphical content is provided. In an illustrative implementation a demosaicing engine executing one or more demosaicing algorithms is employed to operate on graphical content to provide better quality and higher resolution images. In operation, the demosaicing engine operates in two modes, a training/learning mode, and a run time mode. During training, training-images are analyzed to generate a codebook of mosaic filter table entries, such that each table entry has an associated list of similar training pixel blocks and their associated filters. During run time, a run-time image is broken into pixel blocks. Each pixel block is then compared with the entries of the codebook to find the closest match filter. The list associated with the entry is then processed using a least-squares algorithm to locate the optimal mosaic filter. As a result, higher resolution is achieved without requiring more pixels.

Abstract: A method of coarse representation of a visual object's shape for search/query/filtering applications uses a binding box that fully encompasses the object of interest within the image to extract a feature vector. Once the feature vector is available, matching based on specific queries may be performed using a search engine to compare the query number to an appropriate element of the feature vector, performing sorting to pick the best matches.

Abstract: Disclosed is a method, system, and program for receiving line work data and control data for pixels on a sheet from objects. The control data for one pixel indicates whether to use the line work color data for the pixel or contone raster object for the pixel. Further, multiple objects may provide line work data and control data for a same pixel. Line work and control data are simultaneously decompressed for a same set of pixels from the multiple objects and decompressed line work and control data are simultaneously aligned for a same set of pixels from the multiple objects. The simultaneously aligned line work and control data for the pixel from the multiple objects are buffered in a third buffer.