Abstract: A CPU detects the available space A of a first recording medium, the available space B of a second recording medium and a preprogrammed image information amount C necessary for preprogrammed recording by first and second recording medium space managing portions and the contents of preprogrammed recording input from an operation portion by the user. When the preprogrammed image information amount C is larger than the available space A of the first recording medium, an amount of shortage in recording space for preprogrammed information D is obtained from the CPU by subtracting the available space A of the first recording medium from the preprogrammed image information amount C. A larger amount of image information than the recording space shortage D is selected from the image information stored on the first recording medium, and the selected image information is moved to the second recording medium.

Abstract: An image retrieval system for retrieving image similarities from a database is proposed. The image retrieval system uses a universal query mechanism (UQM) to locate statistically silent common features among sample query images from different feature sets. The UQM also adjusts the weight factor for each feature to meet a user's query demand.

Abstract: An image retrieval system for retrieving a plurality of images recorded in a recording medium, records data concerning operations and processing for image files as history data. A desired image is found based on the history data. Further, an image is found based on a combination of photographing condition in a photographing operation, and the history data of the operations executed for the image file. Therefore, the image retrieval system allows the image to be efficiently, exactly, and conveniently found without a trouble of assigning key information to the image file.

Abstract: A non-invasive longitudinal method that is sensitive and objective for quantifying progressive loss of neurons in normal aging brains and brains that suffer from a neurodegenerative disease is provided. The method also provides clinicians, patients and drug companies with a method for evaluating the efficacy of various treatments and interventions by assessing a change in brain integrity. The method determines and localizes a change in brain integrity in a compartment of a brain from at least structural images and metabolite brain images, which are acquired for at least two time instances. The time period between two time instances is dependent on the disease pathology and disease progression and could, for instance, be at least 3 months between time instances as well as at least 6 or 12 months between time instances.

Abstract: A medical image is separated into an image body M1 and supplementary information M2 including patient privacy information. The supplementary information M2 is sent using a high security dedicated circuit 4 and the image body M1 is sent using a public circuit 3. Since the data volume of the supplementary information M2 is less than the data volume of the image body M1, communication costs for using the dedicated circuit 4 can be reduced compared to a case of sending and receiving a whole medical image.

Abstract: Embodiments of an architecture for processing gray-level images is disclosed.

Abstract: A traffic sensor system for detecting and tracking vehicles is describede. A video camera is employed to obtain a video image of a section of a roadway. Motion is detected through changes in luminance and edges in frames of the video image. Predetermined sets of pixels (“tiles”) in the frames are designated to be in either an “active” state or an “inactive” state. A tile becomes active when the luminance or edge values of the pixels of the tile differ from the respective luminance or edge values of a corresponding tile in a reference frame in accordance with predetermined criteria. The tile becomes inactive when the luminance or edge values of the pixels of the tile do not differ from the corresponding reference frame tile in accordance with the is predetermined criteria. Shape and motion of groups of active tiles (“quanta”) are analyzed with software and a neural network to detect and track vehicles.

Abstract: An image processing device and an image processing method calculate motion vectors with a small amount of calculation. A frame memory stores first and second image data, a memory includes multiple elements, and a control unit. Each element includes a pixel for storing a first pixel value of a first pixel of the first image data, a pixel for storing a second pixel value of a second pixel of the second image data, a minimal pixel difference storage unit for storing a first difference value, a motion vector storage unit for storing phase information, a comparison updating unit for comparing the first difference value stored in the minimal pixel difference storage unit, with a second difference value between the first pixel and the second pixel, updating the first difference value with the second difference value according to the results of comparison, and outputting updating information according to said updating, and an updating unit for updating the phase information according to the updating information.

Abstract: A method for implementing sliding-window image processing for associative operators such as MIN, MAX, AND, and OR is disclosed. For one dimension, the present method divides the image into blocks according to the sliding window size and for each block calculates two sets of partial results, one working from the left boundary of the block and the other working from the right boundary of the block. The partial results from two adjacent blocks can then be combined in one operation to give a final value for any window straddling two adjacent blocks. The total number of operations is proportional to 3M; where M is the scan length as compared to (n−1)M using prior art; where n is the length of the sliding window. The present invention can be extended to two-dimensional arrays and can be extended to support arbitrary window sizes.

Abstract: A combine having a camera system is disclosed in which pictures of the ground in front of the vehicle are processed to extract the slope and intercept of a characteristic line indicative of the boundary between the cut and uncut portions of the field. A fuzzy logic algorithm compares the slope and intercept using four input membership functions and a single output membership function. If the slope and intercept extracted from the image are deemed acceptable, they are used to navigate the vehicle through the field. If they are not acceptable, the combine continues to use slope and intercept values previously deemed acceptable to guide the vehicle. This process of image data extraction and quality analysis continues repetitively as the combine traverses the field harvesting crops.

Abstract: The present invention provides a method for multi-job scanning used in an optical scanning device. The method comprises: configuring multiple scanning scopes; re-allocating the scanning scopes into multiple scanning areas such that each scanning area covers one of the scanning scopes, part of one of the scanning scopes, or multiple ones or parts of the scanning scopes; determining a scanning order according to the distance from each scanning area to the scanning starting position; configuring the resolution of each scanning area as the highest one of resolution requests of the scanning scopes overlapping with the scanning area; and scanning each scanning area by a CCD of the scanning device according to the scanning order and the configured resolution, where the CCD does not return to the starting position during scanning.

Abstract: To simplify the file operation of images recorded as a group of panorama images or the like. A character (ST) showing that it is included in a group, alphanumeric character assigned in order in each group, and characters showing file numbers in order of photographing are used as a file name of images to be recorded and a character showing an image compression method is used as the extension of a file name.

Abstract: An imaging processor microcircuit incorporating an integral image buffer, preferably a synchronous random-access memory device. Access to the image buffer is controlled by an image buffer access prioritizer. When the prioritizer detects that a device desires image buffer access, it signals all lower-priority devices to suspend accesses until the higher-priority device has completed access. An image sensor interface transfers image sensor data to the image buffer. As each pixel data is read, it is modified by reference data read from the image buffer then stored in the image buffer. The read, modify, write process takes three of a possible five cycles, leaving two unused cycles for image buffer access by other devices. The image buffer is also temporary image storage for an optional LCD and an optional print engine. The LCD interface uses the unused cycles to read LCD image data.

Abstract: A digital multifunctional apparatus includes a printer, a scanner and a memory. A document code is stored in the memory and printed on a management document when a scanned document is stored in the memory. The document code identifies the scanned document. The apparatus comprises a receiver configured to receive data from an external data source. The memory is configured to store the data received from the external data source. A generator generates a document code that identifies the data received by the receiver. Further, a transmitter transmits the document code to the external data source to enable access by the external data source to the data in the memory identified by the document code.

Abstract: A system and method for speed the video system optimization using genetic algorithms and memory storage, whereby previously evaluated chromosomes, and their associated image quality, are stored in a memory unit for fast retrieval, such as a hash table, to create a large savings of processing time for previously evaluated chromosomes (variations of video systems) that do not have to be re-tested.

Abstract: An image processor includes unit pixel circuits, each circuit outputting a pixel value, according to incident light, to an output line; and read circuits in each row and each column, each of which can read out a pixel value of each unit pixel circuit and a result of computing for projection for each row and each column. The unit pixel circuits of each row and column and the corresponding read circuits are connected to each other by discrete output lines. The result of computing for projection readout by the compression processing is an average of pixel values in the unit pixel circuits of each row and of each column.

Abstract: A CMOS digital integrated circuit digitally captures an image, generates a result surface on which a minima resides, and compares the result surfaces. The correlation of the result surfaces represents a best fit image displacement between image frames.

Abstract: A document image capture (scanning) system and control method are described for scanning and processing document images received live from a camera. A motion detector detects image motion between two image frames. When the image is stationary, image processing (such as OCR) is carried out automatically and made available to the operator. In one form, when movement is detected, the image processing results are discarded until the image is newly stationary, whereupon new image processing is carried out on the new image. In another form, the degree of movement is evaluated; if the movement is small, then at least some of the previous image processing results are re-used by re-mapping on to the new image.

Abstract: A method and apparatus that provides for the straightforward completion of preprinted forms with a word processor, or with another computer program suitable for generating text, is disclosed. The method and apparatus provide for the display of a scaled image of the form so that a user can accurately position text or other data for printing in the fields of the form. An image of the preprinted form is provided to a document having a background and a foreground. The image is displayed in the background Data is entered into the foreground. The data in the foreground is printed onto the preprinted form. The form can be scanned to create the image. The form is then provided to a printer. The image is provided to a word processing document as the background. The data is entered into the foreground with the word processor.

Abstract: A method for spatializing text content for enhanced visual browsing and analysis. The invention is applied to large text document corpora such as digital libraries, regulations and procedures, archived reports, and the like. The text content from these sources may be transformed to a spatial representation that preserves informational characteristics from the documents. The three-dimensional representation may then be visually browsed and analyzed in ways that avoid language processing and that reduce the analysts' effort.

Abstract: A method and device for producing an image effect, applied to an image residing in an image buffer, is used to increase the flexibility of the image effect module. The device includes an image effect module, an access call-back function unit, and a buffer manager. The application program obtains the source image through the access call-back function unit and transfers the source image as well as the access call-back function unit to the image effect module. The image effect module then performs the image effect processing and the image accessing through the collaboration of the access call-back function unit and the buffer manager. After the image effect module returns the destination image to the application program, the application program receives the pixel values of the destination image for display. This image effect module can be commonly shared by different software applications that have their own access call-back function units without further modification.

Abstract: The present invention may be introduced to an architecture such as a personal computer or an amusement equipment for realizing a high-speed graphic processing and provides an optimum arrangement along the flow of information in the case where a frame buffer, a command memory and an image processor are incorporated in one chip in order to improve the drawing performance of an image processing device. Thereby, unnecessary drawing-around of wiring is eliminated and it is possible to reduce the chip area. Further, since the wiring length is shortened, signal delay becomes small, thereby enabling a high-speed operation.

Abstract: A pixel calculating device for performing vertical filtering that includes 16 pixel processing units 1 to 16 and an input buffer group 22 storing 16 pieces of pixel data and filter coefficients. Each of the pixel processing units performs operations using the pixel data and a filter coefficient supplied from input buffer group 22, and then acquires pixel data from an adjacent pixel processing unit. Further operations are performed by each of the pixel processing units using the acquired pixel data and operation results are accumulated. Filtering is carried out through a repetition of this acquiring and accumulation process, the number of taps being determined by the number of repetitions.

Abstract: An apparatus for testing a compression decoder, includes a compression encoder having a picture input for receiving picture material and a coding decision input for receiving coding decisions from a set of legal coding decisions, where the compression encoder is adapted to encode picture material utilising the received coding decisions, a generator for generating random coding decisions from the legal set, and a playback device for communicating encoded picture material from the encoder to a decoder under test.

Abstract: An image processing method using memory management and pre-computed look up tables to speed up computations. Application of filters along directions other than image rows is simplified using several structured processing approaches that improve image data cache-ability. Time consuming or repeated computations are pre-computed and stored as look up tables to reduce the time required for image processing and to remove or reduce the need for special purpose image processing hardware.

Abstract: A method and system for employing image recognition techniques to produce a photocollage from a plurality of images wherein the system obtains a digital record for each of the plurality of images, assigns each of the digital records a unique identifier and stories the digital records in a database; automatically sorts the digital records using at least one date type to categorize each of the digital records according at least one predetermined criteria; and generates a first draft of a photocollage from the digital records. The method and system provides for alterations of the first draft using either a sticker selected from a plurality of stickers which each have a unique identifier within a data base or a digital file format that allows drag and drop features of both the photocollage and alternative images to be placed within the photocollage.

Abstract: The present invention discloses apparatus for, and a method of, rendering image data prior to outputting of the resulting image. A graphics co-processor (224) is utilized together with a host CPU (202), the former having a plurality of data calculation streams (241, 242, 243) arranged in parallel fashion. Only one of the data calculation streams (241, 242, 243) is operated at any one time. Preferably at least one (242) of the data calculation streams is able to be reconfigured.

Abstract: A method and system for employing image recognition techniques to produce a photocollage from a plurality of images wherein the system obtains a digital record for each of the plurality of images, assigns each of the digital records a unique identifier and stories the digital records in a database; automatically sorts the digital records using at least one date type to categorize each of the digital records according at least one predetermined criteria; employs means responsive to the sorting step to compose a photocollage from the digital records. The method and system employ data types selected from pixel data; metadata; product order information; processing goal information; or customer profile to automatically sort data typically by culling or grouping to categorize according to either an event, a person, or chronologically.

Abstract: A user of a portable terminal writes sentences to be transmitted as an e-mail, a mail address, and information indicating that service a host device is requested to provide is “mail transmission” on paper as a memo. By using an image input unit installed in the portable terminal, the paper or the like is imaged. The portable terminal transmits the image data thus taken in to the host device. The host device analyzes received image data by using an image recognition unit. Upon recognizing by characters that the service requested by the portable terminal is “mail transmission”, the host device starts a mail transmitting/receiving unit. The mail transmitting/receiving unit transmits the content of the written memo included in the image data to a terminal specified by the mail address included in the image data.

Abstract: Image data of a test pattern is transmitted to an image processor and image processing is effected by the image processor based on the test pattern. The image outputted (the results of the image processing) from this test pattern image processing and the original image are compared to each other. If they are different, the image processing by the current image processor is judged to be abnormal. In this case, the image processor (hardware process) is switched promptly and automatically to be emulated by an auto set-up engine (software process). Further, in the image processor section, ordinarily, three frame memories are used to effect processes including reading of image data, image processing, and outputting of image data at the same time and in parallel. Image processing can be switched in such a manner that when any one of the frame memories is judged to be abnormal, the two remaining frame memories judged as normal are used to execute image processing.

Abstract: An artificial retina chip in a camera unit of an image processor according to the present invention converts an input image taken by the camera unit to analog signals, and outputs an image signal differential between each dot in a sensor-cell array in the artificial retina chip and a specific standard dot, as an analog signal. A signal converter converts the analog signal to binary digit, and stores the converted signals. When converted signals for one input image are stored, the signal converter outputs the converted signal to an identification unit as a digital signal. Namely, the data output from the camera unit is represented by the analog signal indicating the image signal differential between the dots, and the data output from the signal converter is represented by binary digit which is converted from the analog signal. Accordingly, the amount of the transmitted data is decreased.

Abstract: Data, on which one page of original image data should be image-processed, indicates a first block image (G1) constructed of continuous “n” lines of the original image, commenced from a top line thereof; and a second block image (G2) through an M-th block image (GM). Each of the second to M-th block images is comprised of continuous “n” lines of the original image, and overlapped portions for “d” lines are present between the first to (M−1)-th block images (G1 to GM−1) and the second to M-th block images (G2 to GM), respectively. With respect to each of the block images, (n×W) pieces of pixel data indicative of this block image are supplied to an image processing circuit in both a column positional order and a line positional order, while the column position owns a top priority.

Abstract: An image processing apparatus has a script interpreting section for obtaining a script wherein an execution order for a plurality of image processes, which is permitted in a simultaneous execution, is represented in a predetermined form, and for interpreting the execution order represented by the script; and an image processing section for executing the plurality of image processes in accordance with the execution order interpreted by said script interpreting section.

Abstract: The present invention relates to an image processor (242) comprising a control register block (1470), a decoding block (1468), a data object processor (1462), and flow control logic. The control register block (1470) stores all the relevant information about the image processing operation. The decoding block (1468) decodes the information into configuration signals, which configure an input data object interface (1460). The input data object interface (1460) accepts and stores data objects from outside, and distributes these data objects to the data object processor (1462). For some image processing operations, the input data object interface (1460) may also generate addresses for data objects, so that the source of these data objects can provide the correct data objects. The data object processor (1462) performs arithmetic operations on the data objects received. The flow control logic controls the flow of data objects within the data object processing logic (1462).

Abstract: A data communication unit (1) receives input image data of a first data format which comprises coordinate data of the end points of vectors forming an image and various modifying information of the vectors, and stores them in an input buffer (2). A data analyzer unit (3) converts the input image data into image data of a second data format and stores the data in a storage unit (6). The second data format holds the various modifying information independently of the coordinate data of the end points, decreasing the amount of data compared with the first data format. Based on the image data of the second data format, the data analyzer unit (3) generates, in a band-by-band manner, intermediate codes comprising coordinate data that constitute the contours of the vectors reflecting the various modifying information. The intermediate codes are converted into corresponding raster data in a band-by-band manner, and are printed as an image by a printer unit (10).

Abstract: A CMOS digital integrated circuit (IC) chip on which an image is captured, digitized, and then processed on-chip in substantially the digital domain. A preferred embodiment comprises imaging circuitry including a photo cell array for capturing an image and generating a representative analog signal, conversion circuitry including an n-bit successive approximation register (SAR) analog-to-digital converter for converting the analog signal to a corresponding digital signal, filter circuitry including a spatial filter for edge and contrast enhancement of the corresponding image, compression circuitry for reducing the digital signal storage needs, correlation circuitry for processing the digital signal to generate result surface on which a minima resides representing a best fit image displacement between the captured image and previous images, interpolation circuitry for mapping the result surface into x- and y-coordinates, and an interface with a device using the chip, such as a hand-held scanner.

Abstract: An image processing apparatus is provided with a linear processor array which includes a plurality of linearly coupled processing elements. The apparatus further includes a plurality of local memories each of which takes a form of one-dimensional pixel data memories. The local memories are respectively assigned to the plurality of processing elements. Further, the local memories are arranged so as to store in combination a two-dimensional pixel image to be processed. A plurality of buffers are respectively assigned to the processing elements. Each buffer stores pixel location information of at least one center pixel from which a unique pixel value is to be propagated if the center pixel exists on a corresponding local memory. With the arrangement mentioned above, in order to accelerate pixel data propagation in the two-dimensional pixel image, a plurality of register units are respectively assigned to the plurality of processing elements.

Abstract: A method and system for enhancing a digital image stores the original image and a series of codes describing the manipulations performed on the image. Each time the image is retrieved from an original image archive (110) for viewing on a display (120), corresponding codes are retrieved from an original sequence archive (122). If the codes have previously been optimized, the image processing system (108) applies the optimized codes to the image in order to recreate the enhanced image. If the codes have not been optimized, an optimizer (126) combines and reorders the image enhancement codes in light of certain criteria, including minimizing information loss. A strategy used by the optimizer (126) to minimize information loss separates the codes into sequences and then commutes and combines the codes based on the code types. The optimized codes are applied to the image and produce the image that is displayed on the display (120) and saved in the enhanced image cache memory (114).

Abstract: According to the method of and apparatus for image processing, feature information of each picture element is extracted from image data received. An attribute of each picture element is determined on the basis of the aforesaid feature information. These attributes are corrected by detecting straight lines by applying a Hough transform to picture elements disposed along apparent border lines by which one attribute is divided from another, dividing the image data into a plurality of local regions by these straight lines, and determining an attribute with respect to each of the local regions. Each of the local regions is subjected to image processing in accordance with the corrected attribute.

Abstract: An operation of an iris filter is carried out on an original image signal representing an image, and the degree of centralization of gradients of the original image signal with respect to a picture element is thereby calculated, each of picture elements constituting the image being taken as the picture element. An image portion, which is associated with a high degree of centralization, in the image is detected in accordance with the calculated degree of centralization. Image emphasis processing is then selectively carried out on the detected image portion. Alternatively, a morphology operation is carried out on an original image signal Dorg by using a multiply structure element Bi and a scale factor .lambda., and a morphology signal Dmor is thereby obtained.

Abstract: A method of efficiently transferring data during image transformations performed by a multiprocessor (10). A bounding box (35) is defined for source data to be transferred to the multiprocessor (10) for processing. The dimensions of the bounding box (35) are derived from the dimensions of an associated block (30) in destination space and from the transform coefficients. The bounding box dimensions may be calculated so as to provide the most efficient transfers.

Abstract: An image processor which is connected to a system bus that connects a processor for forming graphic command related to image processing to a main memory that holds command and original image data, and draws image on the frame buffer based upon said graphic command from said processor, wherein said graphic processor has a data bus change-over unit which connects said system bus to a first data bus that is connected to a graphic data memory holding said graphic command and said original image data, or connects said first data bus to a frame buffer which holds the data to be displayed. The image processor realizes a high-speed processing at a reduced cost by using a graphic memory bus coupled to a graphic processor.

Abstract: A linear image filter and the corresponding filtering method is disclosed. In conventional linear image filters, only one pixel can be processed during a single cycle because it is applied to an odd-order filter matrix. Consequently, the present linear image filter and the corresponding method expand the original odd-order filter matrix into an even-order matrix by adding a row and a column of zeros at the topmost/bottommost and the rightmost/leftmost of the original filter matrix. This not only increases the filtering speed of the linear image filter because four pixels can be simultaneously reconstructed, but also fully utilizes current 32-bit processors because a pixel is currently represented only as an 8-bit value.

Abstract: A method and software system for processing images having reconfigurable communication pipelines. The system includes an image processor that instantiates a film module and dynamically creates an image module for each image to be processed. The image processor couples each image module to the film module by a unique communication pipeline according to imaging commands received from an input imaging device. The present invention is applicable to the general field of image processing and may be implemented in any general image output device. In one embodiment, the software system is embedded in a discrete continuous tone laser imager that is directly connected to one or more medical imaging modalities. In another embodiment, the laser imager is directly connected to a network of medical imaging modalities. In yet another embodiment, the software system is executed by an intermediate computer that interfaces an output imaging device to a plurality of networked medical imaging modalities.

Abstract: An image generation apparatus of the present invention reduces the write access frequency to a plurality of memories and increases the image generation speed. The image generation apparatus divides an image zone into a plurality of blocks and assigns an address for each pixel within a block. In order to store the pixels within a shortened time, a parallel storing of the pixel shall be performed evenly at the grouping stage for storing them into respective FIFOs in accordance with the difference of the least significant bit of the address data of the pixel. In this case, the present invention bisects the binary address signal into high order address bits and low order address bits, takes an exclusive OR among the least significant bits of high and low order address bits and replace the least significant bit of the low order address bits with the result of the exclusive OR for the grouping discrimination sign.

Abstract: An operation of an iris filter is carried out on an original image signal representing an image, and the degree of centralization of gradients of the original image signal with respect to a picture element is thereby calculated, each of picture elements constituting the image being taken as the picture element. An image portion, which is associated with a high degree of centralization, in the image is detected in accordance with the calculated degree of centralization. Image emphasis processing is then selectively carried out on the detected image portion. Alternatively, a morphology operation is carried out on an original image signal Dorg by using a multiply structure element Bi and a scale factor .lambda., and a morphology signal Dmor is thereby obtained.

Abstract: The present invention has as an object thereof to provide a semiconductor operational circuit which is capable of instantaneously processing in parallel a large quantity of information. The semiconductor operational circuit of the present invention which executes a predetermined operation with respect to a first signal train of signals A.sub.1, A.sub.2, . . . , A.sub.N-1, A.sub.N (where N is a positive integer) of N signals numbered from 1 to N, and a second signal train of signals B.sub.1, B.sub.2, . . . , B.sub.M-1, B.sub.M (where M is a positive integer) of M signals numbered from 1 to M, comprising a plurality of first operational circuits for executing a predetermined operation with respect to A.sub.i, and B.sub.i+n (where i is a positive integer and n is a positive or negative integer and 1.ltoreq.i.ltoreq.n and 1.ltoreq.i+n.ltoreq.M) and generating an output signal C.sub.i,n, at least one second operational circuit for generating the sum S.sub.

Abstract: A convolver includes a plurality of multipliers for multiplying pixel values of a convolution window by corresponding coefficients of a convolution mask to provide products, a summer for summing the products to provide a result and a memory for storing intermediate results. The convolver may be used to perform an N.times.N convolution in two or more passes. A first subset of pixel values of an N.times.N convolution window and a first subset of corresponding coefficients of an N.times.N convolution mask are supplied to the multipliers during a first pass of the N.times.N convolution. The summer provides an intermediate result for the first pass and stores the intermediate result in the memory. A second subset of pixel values of the N.times.N convolution window and a second subset of corresponding coefficients of the N.times.N convolution mask are supplied to the multipliers during a second pass of the N.times.N convolution.

Abstract: A coprocessor in an image processing system is coupled to the bus to which a CPU and RAM holding image data are also coupled. The coprocessor extracts an input pixel stream corresponding to input images from selected bus transactions, performs computations on the input stream to produce output pixel streams corresponding to output images, and inserts the output pixel streams into selected CPU-to-memory bus transactions so that the memory stores the data. The CPU generates the selected bus transactions with specially marked address and/or control signals. The coprocessor includes a lookup table, and a first row delay. The row delay accumulates the three most recent rows of input pixels, which are sent to Sobel and rank processing sections for neighborhood processing. The results are thresholded and formatted, and are either output directly or passed through an additional pair of row delays to accumulate three rows of result data for neighborhood peak detection.

Abstract: The present invention provides an image compression/decompression coprocessor which is integrated on a single chip. The control bus has a control unit which is connected by an internal, global bus to a number of different, special purpose processing units. Each of the processing units is specifically designed to handle only certain steps in compression and decompression processes.