Abstract: An optical character recognition (OCR) scanning system utilizes a memory device, a registry, a scanning application, a processor, and a scanning device to scan the text of documents into memory. The scanning device is configured to capture an image of a document in response to a scan command from the scanning application. The scanning application locally stores a set of current parameter values indicating the location in the memory device of the OCR package that should be used to currently analyze and interpret images produced by the scanning device. If the scanning application receives a message to update the current parameter values, the scanning application retrieves new parameter values from the registry and stores these values in the memory device as the current parameter values. If the scanning application receives a message to initiate a document scan, the scanning application transmits the scan command to the scanning device and retrieves the current parameter values from the memory device.

Abstract: An image processor performs color correction corresponding to an environment light. An input device inputs white information of a recording medium and environment light information, and a correction device performs correction corresponding to a fluorescent whitening effect, for the white information of the recording medium on the basis of the environment light information. A color correction device performs color correction for an input color image information on the basis of the corrected white information of the recording medium.

Abstract: A block based hybrid compression method with compression ratio control. The input page is classified as SOLID, TEXT, SATURATED TEXT or IMAGE type, and the compression method most appropriate for each class is chosen on a block by block basis. The compression methods shown include Block Truncation Coding, Lossy or Lossless Differential Pulse Code Modulation, Run Length Coding and Discrete Cosine Transforms, but other algorithms may also be used. The compression ratio is dynamically controlled by selection of the compression algorithm, and by the adjustment of control parameters on a block by block or a row of blocks basis. The methods shown will execute very efficiently on a Texas Instruments TMS302C82 multiprocessing Digital Signal Processor.

Abstract: The coded block parameters used to code blocks of image samples into structures called macroblocks are compressed more efficiently by exploiting the correlation between chrominance and luminance blocks in each macroblock. In particular, the coded block pattern for chrominance and luminance are combined into a single parameter for the macroblock and jointly coded with a single variable length code. To further enhance coding efficiency, the spatial coherence of coded block patterns can be exploited by using spatial prediction to compute predicted values for coded block pattern parameters.

Abstract: A method of encoding a visual object. The method includes encoding the visual object to obtain compressed coded data using at least one of a plurality of different operations which can be performed on a block by block basis. The method also includes encoding information associated with a computational complexity of decoding the compressed coded data. The encoded information relates to the number of times each of the plurality of different operations is performed.

Abstract: Template regions are set on a single radiation image, among a plurality of radiation images. Template matching is carried out, with which the template regions are matched with the radiation images other than the single radiation image. At least three corresponding points are thereby obtained in each of the radiation images. The corresponding points in a single radiation image, among the plurality of radiation images, are taken as reference corresponding points, and factors of affine transformation are calculated with the method of least squares. Affine transformation is then carried out using the calculated factors of affine transformation. The values of coordinates of the corresponding points in the radiation images other than the single radiation image having the reference corresponding points are thus transformed into values of coordinates of the reference corresponding points such that the reference corresponding points and the corresponding points coincide with one another.

Abstract: An optimum data arrangement is provided such that each apparatus can efficiently deal with image data encoded using discrete wavelet transform. For that purpose, an image processing apparatus includes an input device for inputting first entropy encoded data. The first entropy encoded data is obtained by peforming entropy encoding of transform coefficients of a first data arrangement. The transform coefficients of the first data arrangement are obtained by performing wavelet transform of a predetermined image in each first unit.

Abstract: A three-dimensional surface profile imaging method and system uses a single spectral light illumination constraint to guarantee consistent RGB values corresponding to a given light spectrum, regardless of the surface reflectance characteristics of the object being imaged. In one embodiment, each light sheet projected onto the object contains only a single wavelength. As a result, the spectral composition of the projected light at any surface point of the object will be independent of the light intensity and the reflectance characteristics of the surface.

Abstract: A method and system is described which facilitates the proper association of radiographic film with a patient information. The invention maintains information for each patient to be examined in the current day and generates a unique identifying ID code for each patient to be examined. Before examining a patient, the current patient's unique identifier is imaged on an unexposed radiographic film. After the patient is examined and the film is exposed, the film is developed and digitized. Patient information is retrieved and associated with the digitized medical images by analyzing the digital image data in order to determine the patient's unique identifier. In this manner, the invention ensures the proper association of patient information with exposed radiographic film. Once properly associated, the digital image data and the patient information can be communicated to a Picture Archiving and Communication System.

Abstract: An area information storage section stores positional information on at least two target areas on the standard image of printed matter to be examined, the area of each of the target areas, their standard average densities, and the standard deviation of their density distribution. An average density computing section calculates the average density for each target area in the image data supplied from the image input section using positional information on each target area and its area supplied from the area information storage section. A density difference measuring means measures, target area by target area, the density difference between the average density and the standard average density supplied from the area information storage section. A density difference normalizing section normalizes the density difference and the standard deviation of the density distribution supplied from the area information storage section.

Abstract: A method for coding video data according to the MPEG-2 standard is provided. Non-Intra fields are identified among Intra fields and various coding options exist for the non-Intra fields, including removal of temporal redundancy using a motion estimation algorithm and identification of predictor macroblocks for providing approximation according to a prediction mode selectable among respective predicting modes of the different types of non-Intra fields. The method includes calculating a discrete cosine transform (DCT) for blocks of data of the predictor macroblocks according to a frame mode of decomposition with the blocks being composed of lines of data belonging to even lines semifield and to odd lines semifield, or in a field mode of decomposition with the blocks being composed of lines of data belonging to the same semifield. The data resulting from the DCT carried out by blocks of data to be stored is quantized and coded.

Abstract: A method for characterizing objects within an image is presented. According to an embodiment of the present invention, a representative color of an object is first identified from an image. The contour of this same object is then determined by identifying regions of the image where the identified color changes to another color. Color and contour data from other images of the same object may be obtained using the above described method to compile a ranges of colors and a range contours which represent the object. This color and contour data (known as the “object signature”) is then associated with a name for this particular object and stored. Once an object signature has been defined for a particular object, a database of images may be searched to identify images which include objects matching the object signature. For example, once an object signature for a mountain is determined, this object signature may be used to search a database for all images which include a mountain.

Abstract: A system and method assists the driver of a motor vehicle in preventing accidents or minimizing the effects of same. In one form, a television camera is mounted on a vehicle and scans the roadway ahead of the vehicle as the vehicle travels. Continuously generated video picture signals output by the camera are electronically processed and analyzed by an image analyzing computer, which generates codes that serve to identify obstacles. A decision computer mounted in the controlled vehicle receives such code signals along with code signals generated by the speedometer or one or more sensors sensing steering mechanism operation and generates control signals. Such code signals may be displayed, and a synthetic speech or special sound generating and warning means used, to warn the driver of the vehicle of approaching and existing hazards.

Abstract: An image sensor (10) includes an array having an image sensing portion (12) and a control portion (14). Pixels (18) of the image sensing portion and devices (20) of the control circuitry portion each have a diode stack (34) of a back-to-back switching diode (36, 38, 40) and a photodiode (42, 44, 46). The photodiodes of the devices (20) are constantly illuminated in use so that they act as current sources in series with the switching diode. This provides a circuit device which has characteristics enabling its use in control circuitry.

Abstract: Three-dimensional data is generated by measuring an affected part using a computed tomography unit. Then, color information is allocated so as to correspond to voxel values of the three-dimensional data, and the allocated color information is added up along a ray irradiated from a radiation source. As a result, a digitally reconstructed radiograph (DRR) is generated and displayed.

Abstract: In a system for recognizing the environment around a vehicle with an image, to provide a system and method of detecting a road area without lowering the accuracy over the entire of the road area including an upper portion of the road area. The system comprises a computer 100 which is operated under control of a program, an image input device 110, and means for outputting road area data 120. The computer 100 comprises means for calculating statistic for each horizontal line 101, means for fitting the statistic to a function 102, means for processing a threshold value of the road image 103 and means for detecting the road area 104.

Abstract: An image processing system tiles an image data array. Each tile of image data is processed by applying a family of transform layers to the tile of image data so as to generate successive sets of transform coefficients. Each set of transform coefficients include edge coefficients positioned at outside boundaries of the set of transform coefficients and non-edge coefficients positioned at interior locations of the set of transform coefficients. The transform filters include a short edge transform filter that is applied to image data at boundaries of the tile and to coefficients positioned at and near boundaries of each of the earlier sets of transform coefficients so as to generate the edge coefficients, and a long interior filter that is applied to image data at interior locations of the tile and to coefficients at interior locations of the earlier sets of transform coefficients so as to generate the non-edge coefficients.

Abstract: An image coding apparatus inputs pixel data of a part image of high resolution. An upper layer coding portion (101), a second shape data generating portion (102), and a second shape data coding portion (103) perform coding of shape data and pixel data in the upper layer. A down sampling portion (104) generates pixel data of low resolution. A lower layer coding portion (105), a first shape data generating portion (106), and a first shape data coding portion (107) code shape data and pixel data in the lower layer.

Abstract: We improve text reproduction of a scanned and printed image by identifying text-contribution colors and also image-contribution colors that are in or near the text region of the color space. When input colors are encountered that contribute both to text and image we splice together text and image color transformations of the input color to produce a color in the printer color space. We improve background reproduction, i.e. reduce bleed-through artifacts, by identifying background-contribution colors and also image-contribution colors that are in or near the background region of the color space. When input colors are encountered that contribute both to background and image we splice together background and image color transformations of the input color to produce a color in the printer color space.

Abstract: In a prediction method usable with synthetic and natural hybrid coding (SNHC) field or a virtual reality markup language (VRML) the difference between immediately prior information (most adjacent information) and input property information is obtained, considering the immediately prior information as the prediction value. The difference is used as a prediction error signal. A predictor having an order of 1 is used. When the output value of the predictor is fixed to 0, the prediction error signal becomes identical to an original signal. Therefore, the operation is the same as in the case where there is no predictor. The correlation of the input property information is used in order to control two operation modes of the predictor. Namely, auto-correlation is obtained from the input property information.