Abstract: A first image of two images to be compared for similarity is divided into small areas and one small area is selected for calculating the correlation with a second image using a correlative method. Then, the position difference, luminance ratio and similarity in an area where the similarity, which is the square of the correlation value, reaches its maximum, are found. Values based on the similarity are integrated at a position represented by the position difference and the luminance ratio. Similar processing is performed with respect to all the small areas, and at a peak where the maximum integral value of the similarity is obtained, its magnitude is compared with a threshold value to evaluate the similarity. By extracting the small area voted for that peak, it is possible to extract a similar area.

Abstract: A method of generating a binary Sel plane for image compression is disclosed. The method first generates a 2 bit gray selector (GraySel). This 2 bit selector is then processed in a second stage to produce a binary Sel decision which minimizes the compression noise evident in the reconstructed image. The method used here to generate the 2 bit GraySel applies a set of prioritized rules over a small 3×3 window that is well suited for segmenting synthetic, PDL generated images that are typically free of scanner noise. The method not only marks the proper sense of the selector when it is known, but also include a 3rd state that indicates that the selector decision is weak or unknown. This weak decision can then be optimized in the second stage process based on strong edges information in the neighborhood.

Abstract: A shape information coder divides the pixels in the shape information into subsets representing different subsamplings of the shape information. Each pixel in each subset is coded with reference to a context which may be derived from reference pixels in more than one of the subsets. The context preferably includes reference pixels located on all sides of the pixel being coded, which leads to efficient coding. The shape information coder may have two or more cascaded stages, each operating as above, with one subset of pixels passed from each stage to be coded in the next stage. The resulting coded shape information is useful in, for example, wavelet coding of pictures.

Abstract: A video coding system that codes video objects as scalable video object layers. Data of each video object may be segregated into one or more layers. A base layer contains sufficient information to decode a basic representation of the video object. Enhancement layers contain supplementary data regarding the video object that, if decoded, enhance the basic representation obtained from the base layer. The present invention thus provides a coding scheme suitable for use with decoders of varying processing power. A simple decoder may decode only the base layer of video objects to obtain the basic representation. However, more powerful decoders may decode the base layer data of video objects and additional enhancement layer data to obtain improved decoded output. The coding scheme supports enhancement of both the spatial resolution and the temporal resolution of video objects.

Abstract: The present invention provides a vehicle driving information storage apparatus capable of preserving condition changes of inside and outside of a vehicle and a driver as synchronized images. Inside a vehicle 1, a fisheye lens 5 is arrange at a position capable of simultaneously filming a driver's state and a state inside and outside the vehicle and filming is performed at a predetermined cycle and a predetermined number jmax of the latest images are always stored in the image storage unit M1. Upon detection of a driving condition sudden change such as a sudden brake and a collision, image update is performed the operations times of jmax−x1 (0<x1<jmax) and the image update is stopped so that x1 images before sudden change and jmax−x1 images after the sudden change are preserved in the image storage unit M1.

Abstract: In the digital image padding method according to the present invention, as shown in FIG. 2, every other pixels in an original image space 301 corresponding to an input digital image signal are extracted in the horizontal direction, and every other pixels are extracted in the vertical direction, the extracted plural pixels are rearranged to form four small image spaces 401-404, and pixels values in these small image spaces are padded.

Abstract: A method and apparatus for extracting information from symbolically compressed document images. A deciphering module generates first and second text strings by deciphering respective sequences of template identifiers in first and second symbolically compressed document images. A conditional n-gram module receives the first and second text strings from the deciphering module and extracts n-gram terms therefrom based on a predicate condition. A comparison module generates a measure of similarity between the first and second symbolically compressed document images based on the n-gram terms extracted by the conditional n-gram module.

Abstract: Provided are an image processing apparatus and method whereby even if shape data representing the shape of an object in a moving image undergoes a major change temporarily, a frame that is to be corrected can be detected and corrected in ideal fashion and it is possible to execute moving-image coding that is outstanding both visually and in terms of coding efficiency. In one example, a moving image composed of a plurality of frames is acquired from a image input unit (101) and the background image of the moving image is acquired by a background image generating unit (102). A background subtraction processor (103) extracts an object by comparing each of the frames constituting the moving image with the background image, and an abnormal-data discrimination unit (105) discriminates whether shape data representing the shape of the extracted object is abnormal or not. If the shape data is abnormal, a shape-data correction unit (106) corrects the shape data.

Abstract: The present method relates to a method for encoding image data using vector quantization. According to the invention, a small first codebook is determined. Each image vector of the image data is then encoded by determining a codevector within the first codebook that best approximates the image vector within the image data. A first index map is generated by replacing each image vector with an index indicative of the codevector's location within the first codebook. Then difference data are evaluated based on the original image data and the encoded image data. Each error vector of the difference data is then encoded using another small codebook. In another index map the error vectors are then replaced with an index indicative of the codevector's location within the other codebook. Evaluation of the error based on the difference data and the encoded difference data provides new difference data which is used to evaluate the fidelity of the approximation process performed for compression.

Abstract: Methods and systems of the present invention may be used to recognize digital image data arranged in rows and columns. Exemplary embodiments may include a feature extractor for extracting feature information from data representing the rows and columns of the digital image data, a feature compressor for compressing the extracted feature information, and a neural network for classifying the digital image data from the compressed, extracted feature information.

Abstract: In an image data coding and/or decoding system, a coding system performs the two-dimensional orthogonal transform of picture signals of all the pixels with respect to inside blocks and of only picture signals of pixels contained in a content with respect to edge blocks, in accordance with a map signal indicative of the position and shape of the content, and it codes the map signal. A decoding system selects an orthogonal transform coefficient necessary to reproduce an image of a desired resolution, from coded orthogonal coefficients on the basis of a coded and resolution-transformed map signal, and it performs the two-dimensional inverse orthogonal transform of all the coefficients with respect to the inside blocks and of only the coefficients contained in the content with respect to the edge blocks, to derive a resolution-transformed regenerative signal.

Abstract: The invention relates to a method and an apparatus for encoding images, more particularly to an encoding unit in conjunction with a library of pictorial entities and image qualifiers. The method and apparatus provide encoding an image by using a code factor table in conjunction with a set of element codes. The resulting image code allows the set pictorial elements of an image and their associated image qualifiers to be represented by a compact code uniquely representing a given configuration of pictorial elements. The use of the resulting image code facilitates the transmission and storage of images requiring only the code to be sent or stored. The invention further provides a computer readable medium comprising a program element that direct a computer to implement the encoding process.

Abstract: A system and method for image compression and decompression is provided. The method of image compression and decompression includes selecting a portion of image in a span of interest obtained from an acquired imaging sequence; applying lossless compression to the portion of image in a span of interest and obtaining a compressed image sequence; and applying decompression to the compressed image sequence and obtaining therefrom an analytically relevant image sequence.

Abstract: A method and apparatus for transferring a data signal includes a transmitter having an encoder and a receiver having a decoder. The encoder includes a segment selector for identifying a signal segment from a group of speech, audio, video and graphic signals, each selected segment comprising a representation of an information quantity. The encoder includes a plurality of encoder libraries, one of the libraries containing a generic representation corresponding to the information quantity and a symbolic code corresponding to the object. The decoder has a second plurality of libraries corresponding to the plurality of encoder libraries, and one of the decoder libraries generates the information quantity as output in response to matching of the symbolic code transmitted from the encoder.

Abstract: A decoding LSI adaptable to MPEG4 is provided with a padding means for performing padding on decoded texture data, an arithmetic decoding means for performing arithmetic decoding on coded shape data, and a composition means for compositing a plurality of texture data to generate composite image data. The padding means, the arithmetic decoding means, and the composition means are implemented by hardware circuits, i.e., a padding engine, an arithmetic decoding engine, and a composition engine, respectively. Therefore, the decoding LSI can perform high-speed decoding on a bitstream corresponding to plural objects, such as images, which are compressively coded by the MPEG4 coding method, with reduced cost of the hardware circuits performing the decoding process.

Abstract: An image coding method and apparatus for coding each block of a digital image divided into a plurality of two-dimensional blocks, wherein each block has a plurality of pixels. A coding mode for a target block is determined by a code mode determining section to output mode information of the target block. The mode information of the target block is coded, by a mode information coding section, using mode information of previously coded blocks at the periphery of the target block. Pixel data of the target block is then coded by a block data coding section according to the mode information of the target block. A computer readable recording medium that contains an image coding program is also disclosed.

Abstract: The present invention selectively applies one of VLC tables stored in a memory for encoding a coded block pattern of a macroblock according to the number of blocks having an object within the macroblock, the number of blocks obtained using shape information, thereby reducing the amount of data transmitted and increasing coding efficiency.

Abstract: An apparatus and method for image-compression encoding and decoding using an adaptive transform in which, where different transform coefficients are outputted in accordance with a change of the transform direction order for an input image signal block, encoding and decoding procedures are conducted, based on the transform direction order selected in accordance with the characteristics of the input image signal block. In accordance with the present invention, an orthogonal transform and a inverse orthogonal transform for blocks are controlled, based on a determination made about whether signals within a block, to be currently encoded, have a higher correlation in a vertical direction or in a horizontal direction, using information about blocks encoded or both information about blocks encoded and information about the current block.

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: Three-dimensional position information is used to segment objects in a scene viewed by a three dimensional camera. At one or more instances of an interval, the head location of the user is determined. Object-based compression schemes are applied on the segmented objects and the detected head.

Abstract: A method and process for improving the quality of multi participant video conferencing over Internet Protocol. The method uses a unique grayscale area map that represents objects in 3-D space to determine area boundaries and object priority for culling prior to transport. The method uses an objects depth map to determine the highest energy magnitude for motion estimation and compensation. By controlling the flow rate of objects over the temporal domain and the re-creation of object based predictive frames, a constant bit-rate scalable video compression algorithm has been shown. Spatial and temporal hierarchical significance trees are used to build maps of significant energy on a per-object basis. Thus, the bit-rate of compressed video is dynamically adjusted by the limitation of data transport through the network.

Abstract: A progressive coding and decoding method of three-dimensional (3D) mesh data used in the fields of motion picture experts group-4 synthetic and natural hybrid coding (MPEG-4 SNHC), virtual reality modelling language (VRML) and the like. In transmitting 3D objects composed of 3D mesh data, it is very important to progressively restore transmitted data as well as to effectively code the 3D mesh data. In the progressive restoration, in the event that a transmission data error is generated, partial restoration of the transmitted data is allowed. Thus, it is possible to minimize the amount of mesh data to be transmitted again. The progressive restoration method which is resistant to such transmission errors can be effectively applied in wireless communications or low transmission rate communications.

Abstract: A method for the geometric transformation of a compressed image, stored on a source appliance connected to one or more other appliances by a computer communication network, comprising the steps of choosing a set of appliances in the computer communication network adapted to implement a geometric transformation of an image in compressed form; selecting an appliance in the set for implementing the geometric transformation of the image in compressed form; of transmitting the compressed image to the selected appliance if it is different from the source appliance; and geometrically transforming the image in compressed form by means of the selected appliance. This method is used notably for a computer and printer installed on a network.

Abstract: There is provided an image decoding apparatus for decoding a coded image signal having an image identifier based on a data structure of the image signal. This apparatus comprises a data analyzer for analyzing the coded image signal with reference to the image identifier to decide whether the coded image signal is a coded arbitrary shape signal including both of coded shape bit streams obtained by coding a shape signal which represents the shape of each object as one of the components of a display image and coded pixel value bit streams obtained by coding a pixel value signal representing the gradation of the object, or a coded binary signal including only coded shape bit streams obtained by coding a shape signal representing a display image of binary information; a first decoder for decoding the coded shape bit streams by a first decoding process; and a second decoder for decoding the coded pixel value bit streams by a second decoding process.

Abstract: It is an object to encode an image signal or a shape signal more efficiently than the prior art. As a means to accomplish the object, the change pixel detector 2 receives the input signal 1 as an input signal and detects the pixel which changes the two-valued pixel value. Further, the change pixel predictor 4 also reads out the reference image stored in the memory 3, and predicts the change pixel of the particular input signal. The difference value calculator 5 subtracts the output of the change pixel predictor 4 from the output of the change pixel detector 2. The difference value rounder 7 compares the tolerance value e and the prediction error D, and outputs x which requires the minimum bit number for being encoded in the value D−e≦x≦D+e. The output of the difference value rounder 7 is encoded by the decoder 8 to become the encoded signal 9.

Abstract: A method and apparatus for performing selective quantization by manipulation of refinement bits is described. In one embodiment, the method comprises performing a refinement coding pass to bit-planes of a code block to create refinement bits and setting refinement bits to the more probable symbol (MPS).

Abstract: A method and apparatus for performing scalar quantization with a power of two step size is described. In one embodiment, the method comprises receiving a sequence of image data to compress and specifying scalar quantization with a power of two step size using three bit values to apply to the sequence of image data.

Abstract: An image data coding system comprises a screen-area determining means for determining the area of a screen reproduced on the basis of an input image data; a code-amount assigning control means for controlling regions to which data on the screen are to be assigned and the code amount assigned to each of the regions, on the basis of the results determined on the area of the reproduced screen; and a coding means for coding the image data signal inputted in accordance with the code amount assigned to each of the regions.

Abstract: A method and apparatus for outputting a codestream as multiple tile-part outputs with packets from tiles being output in each tile-part is described. In one embodiment, the method comprises coding of each tile of an input codestream, outputting packets of each tile as part of an output codestream as a first complete tile-part, storing remaining layers of each tile in a buffer, and outputting additional packets of each tile from the remaining layers as a second complete tile-part.

Abstract: A method and apparatus for clipping coefficient values after application of each wavelet transform is described. In one embodiment, the method comprises applying an inverse wavelet transform to data repeatedly for a plurality of decomposition levels, and clipping, after each application of the inverse wavelet transform, any value generated as a result of application of the inverse wavelet transform that exceeds a predetermined range associated with that decomposition level subband of the inverse wavelet transform.

Abstract: In an apparatus performing object-by-object coding by using coordinate position information (FMJpos) which indicates the positional relationship between a composite image coordinate system and an object coordinate system, and area position information (OBJpos) which indicates the position of a rectangle area in the object coordinate system, position disturbance information (pos offset) the value of which varies from frame to frame is generated, and the position disturbance information (pos offset) is superposed on the coordinate position information (FMpos) and the area position information (OBJpos) so that the position of the rectangle area corresponding to each object, which position is decided on the composite image coordinate system in accordance with these position information, does not change. Therefore, it is possible to make illegal reuse of an image signal corresponding to each object difficult, without degrading the image quality.

Abstract: A digital image processing method determines the extent of blocking artifacts in a digital image by first forming a column difference image and averaging the values in the columns in the column difference image to produce a column difference array. The average of the values in the column difference array that are separated by one block width are computed to produce a block averaged column difference array. Then, the peak value in the block averaged column difference array is located, and the mean value of the block averaged column difference array (excluding the peak value) is calculated to produce a column base value, and the ratio between the peak value and the base value are computed to produce a column ratio. The foregoing steps are repeated in the row direction to produce a row ratio. Finally, the column and row ratios are employed as a measure of the extent of blocking artifacts in the digital image.

Abstract: Systems and methods for performing clustering of a document image are disclosed. A property of an extracted mark from a document is compared to the properties of the existing clusters. If the property of the mark fails to match any of the properties of the existing clusters, the mark is added as a new cluster to the existing cluster. One property that can be utilized is x size and y size, which is the width and height, of the existing clusters. Another property that can be employed is ink size, which refers to the ratio of black pixels to total pixels in a cluster. Yet another property that can be utilized is a reduced mark or image, which is a pixel size reduced version the bitmap of the mark and/or cluster. The above properties can be employed to identify mismatches and reduce the number of bit by bit comparisons performed.

Abstract: A system and method facilitating compression of bi-level images with explicit representation of ink clusters is provided. The present invention includes a cluster shape estimator that analyzes connected component information, extracts clusters and stores the cluster in a global dictionary, a page dictionary or a store of unclustered shapes. A bitmap estimation from clusters component determines dictionary positions for clusters stored in the global dictionary which are then encoded. A cluster position estimator determines page positions of clusters of the global dictionary and/or the page dictionary that are then encoded. Further, the global dictionary, the page dictionary and the store of unclustered shapes are also encoded.

Abstract: Methods and systems consistent with this invention decode image data. Such methods and systems decode a coded map signal indicative of the position and shape of a content in a screen inputted for every square block of picture signals, perform the resolution transform of the decoded map signal, decode coded orthogonal transform coefficients, perform the two-dimensional inverse orthogonal transform of the orthogonal transform coefficients, and derive a regenerative picture signal by taking out the values of pixels inside of the content from the results of the two-dimensional inverse orthogonal transform based on the resolution-transformed map signal, with respect to the blocks containing the boundary portion of the content.

Abstract: An image data coding system comprises a screen-area determining means for determining the area of a screen reproduced on the basis of an input image data; a code-amount assigning control means for controlling regions to which data on the screen are to be assigned and the code amount assigned to each of the regions, on the basis of the results determined on the area of the reproduced screen; and a coding means for coding the image data signal inputted in accordance with the code amount assigned to each of the regions.

Abstract: In a chroma subsampled image, since an extracted object contains a color outside the object upon extracting the object, the color of an object boundary portion becomes unnatural upon reproduction, and coding efficiency lowers. In this invention, the object is extracted while determining pixels on the object boundary as those outside the object. Upon object extraction, the value of a chroma pixels that extends across the object boundary is calculated based on the chroma values of its surrounding pixels. With this process, the coding efficiency can be improved, and natural color reproduction can be realized, since chroma data that extends across the boundary is synthesized on the basis of the ratio between background data and object data upon object synthesis.

Abstract: The method and apparatus have a shape-adapted transformation coding is in which in the intra-image coding and the inter-image coding different shape-adapted transformation codings are carried out. A first shape-adapted transformation coding takes place in the intra-image coding, and a second shape-adapted transformation coding, different from the first shape-adapted image coding, takes place in the inter-image coding.

Abstract: An accurate encoding of image data representing a source image, which data is divided into a multiplicity of blocks is performed in accordance with features of the source image by defining a plurality of sub-areas each of which including one or more blocks; quantizing the multiple blocks; counting the number of valid coefficients among the quantization coefficients in each sub-area; adjusting the quantization coefficients of the plural sub-area in accordance with a distribution of the number of valid coefficients over the plural sub-areas (that is, a degree of appearance of the valid coefficients of each sub-area); and encoding the adjusted quantization coefficients. In addition to the accuracy, encoding of image data using sub-areas enhances a speed of processes.

Abstract: A shape information coder divides the pixels in the shape information into subsets representing different subsamplings of the shape information. Each pixel in each subset is coded with reference to a context which may be derived from reference pixels in more than one of the subsets. The context preferably includes reference pixels located on all sides of the pixel being coded, which leads to efficient coding. The shape information coder may have two or more cascaded stages, each operating as above, with one subset of pixels passed from each stage to be coded in the next stage. The resulting coded shape information is useful in, for example, wavelet coding of pictures.

Abstract: A system, method and computer program product are provided for the compression of characters with a predetermined size. Initially, a plurality of characters are received. Thereafter, the characters are compressed. Information is stored with the compression. Such information is capable of being used to modify the characters upon the characters being displayed with a predetermined size.

Abstract: An image data coding system comprises a screen-area determining means for determining the area of a screen reproduced on the basis of an input image data; a code-amount assigning control means for controlling regions to which data on the screen are to be assigned and the code amount assigned to each of the regions, on the basis of the results determined on the area of the reproduced screen; and a coding means for coding the image data signal inputted in accordance with the code amount assigned to each of the regions.

Abstract: A pixel padding procedure is disclosed. The padding procedure provides a method for filling pixels in a block in accordance with intensities of pixels in preceding and succeeding pixels of the same row or column. This padding procedure may include filling pixels with simultaneous logic operations; transposing blocks before and after horizontal padding; case detecting for simple or complex padding; simple pixel filling, where no pixels need to be averaged; and complex pixel filling, which contains pixels to be averaged. In one embodiment, this procedure may be performed in an MMX™ implementation for MPEG-4 repetitive padding.

Abstract: A video image decoding and composing apparatus includes: a composing information memory for storing composition information; an arbitrary shape object decoding means for decoding a coded signal of an arbitrary shape object video image; a shape memory for storing a shape signal which is decoded by the arbitrary shape object decoding means; a texture memory for storing a texture signal which is decoded by the arbitrary shape object decoding means; a rectangular shape object decoding means for decoding a coded signal of a rectangular shape object video image; a video image memory for storing a video image signal which is decoded by the rectangular shape object decoding means; a composing means for composing the shape signal stored in the shape memory, the texture signal stored in the texture memory, and the video image signal stored in the video image memory, in accordance with the composition information stored in the composition information memory; a position indicating means for indicating a position in the c

Abstract: A scene description generating apparatus and method, an object extracting method, and a recording medium extract an object from an input image. Positional information on the extracted object is output. Based on the positional information, scene description information about a placement position of the object in a scene is generated. When the object is deformed, reference to the positional information is made, and the scene description information is generated in which the object deformation is reflected. Accordingly, the object is placed at a desirable position in the scene.

Abstract: A technique implicitly encodes shape information by using a chroma-key color. A frame including an object is received and a box bounding the object is created. The pixels in the bounding box outside the object are identified and replaced with a key color. The object is coded. A first bitstream is output that includes the coded data for the pixels in the bounding box, and a second bitstream is output that includes a node containing the key color and chroma-key thresholds for the object. In one embodiment, the node is a MaterialKey node. In a further embodiment, the node comprises a transparency field, an isKeyed field, an isRGB field, a keycolor field, a lowThreshold field, and a highThreshold field.

Abstract: A shape information coder divides the pixels in the shape information into subsets representing different subsamplings of the shape information. Each pixel in each subset is coded with reference to a context which may be derived from reference pixels in more than one of the subsets. The context preferably includes reference pixels located on all sides of the pixel being coded, which leads to efficient coding. The shape information coder may have two or more cascaded stages, each operating as above, with one subset of pixels passed from each stage to be coded in the next stage. The resulting coded shape information is useful in, for example, wavelet coding of pictures.

Abstract: A video coding system that codes video objects as scalable video object layers. Data of each video object may be segregated into one or more layers. A base layer contains sufficient information to decode a basic representation of the video object. Enhancement layers contain supplementary data regarding the video object that, if decoded, enhance the basic representation obtained from the base layer. The present invention thus provides a coding scheme suitable for use with decoders of varying processing power. A simple decoder may decode only the base layer of video objects to obtain the basic representation. However, more powerful decoders may decode the base layer data of video objects and additional enhancement layer data to obtain improved decoded output. The coding scheme supports enhancement of both the spatial resolution and the temporal resolution of video objects.

Abstract: A system, method and computer program product are provided for compression of characters. Upon receipt of a plurality of characters, at least one test is performed on the characters to determine if an outline of the characters is capable of being approximated by a mathematical approximation. If the outline of the characters is capable of being approximated, the characters are approximated using the mathematical approximation.

Abstract: An image coding system that codes a map signal indicative of the position and shape of a content in a screen inputted for every block of picture signals to be coded; performs the orthogonal transform of the picture signals in accordance with the map signal to output an orthogonal transform coefficient; and codes the orthogonal transform coefficient. The coding system may perform the two-dimensional orthogonal transform of the picture signals of all the pixels with respect to the blocks located inside of the content, and may perform the orthogonal transform of only the signals of the pixels contained in the content with respect to the blocks containing the boundary portion of the content.