Abstract: This disclosure relates to an image processing system which relies upon quantization and dithering techniques to enable an output device, which has a given number of output levels, to accurately reproduce a image which is generated by an input device, which has a greater or equal number of input levels. Generally, neither the number of input nor output levels need to be a power of two. The present invention is implemented in a number of different embodiments. These embodiments generally rely upon an image processor which, depending on the particular implementation, includes memory devices and an adder, a comparator, or a bit shifter. Additional embodiments use an image adjustment system or an image modification system to refine the raw input levels of the input device, in order to create an improved output image. Also, the particular embodiments of the image processors can be used in connection with imaging systems having bi-tonal, monochromatic, or color input and output devices.

Abstract: Compression of a plurality of signal samples y(t.sub.0),y(t.sub.1),y(t.sub.2) . . . y(t.sub.z) may be accomplished by performing a first linear regression to obtain a curve fitted thereto which is represented by a polynomial having a first set of coefficients (a.sub.0,a.sub.1,a.sub.2,a.sub.3 . . . a.sub.n) which is stored in memory (18) or transmitted by a transmitter (20). The error between each of the actual signal samples (y(t.sub.0),y(t.sub.1),y(t.sub.2) . . . y(t.sub.z) and the value approximated by the curve fitted to the values is computed and then thresholded. A second regression analysis is then performed to fit a curve, having a second set of coefficients (b.sub.0,b.sub.1,b.sub.2,b.sub.3 . . . b.sub.q) to the thresholded error values. The second set of coefficients is also stored or transmitted and used, in conjunction with the first set of coefficients, to closely approximate the original set of signal samples.

Abstract: Substantially circular objects such as the ends of the filters of filter tipped cigarettes are inspected for acceptable appearance utilizing a blob analysis which includes imaging a peripheral region so as to provide resolution along the edge of the circular object.

Abstract: A motion detecting apparatus in which when pixels within a search range formed of a predetermined number of pixels and pixels within a reference data block the number of which is smaller than the predetermined number of pixels in the search range, are compared on the basis of the arrangement state thereof, a processing circuit processes sums of difference absolute values of respective pixels within the reference data block and corresponding pixels within the search range formed at every search range, to thereby detect a motion state on the basis of the sums. Respective pixels within the search range are input to the processing circuit at a set time and pixels within the search range are input to the processing circuit at the set time, thereby being sequentially processed with corresponding pixels within the data block.

Abstract: A method of compressing inputting two-dimensional object, compressing the two-dimensional data in a short time to a small amount of data and reproducing in any size at any position. This invention reads two dimensional object, e.g. characters, figures, drawings or Illustrations optically, extracts peripheral points from a binary image, approximates the peripheral lines by Fluency functions, reckons curvatures at all points, and finds joints. The peripheral points series are divided by the joints. The lines between two neighboring joints are approximated by straight lines, arcs and free curves in this order. The free curves are approximated by linear combinations of Fluency functions. Adoption of joints greatly alleviates the quantity of data. Approximation by Fluency functions heightens the quality of the reproduced objects.

Abstract: A method and apparatus for differentiating and extracting handwritten annotations and machine printed text in an image. The method provides for the use of morphological operations, preferably at reduced scale, to eliminate for example, the handwritten annotations from an image. A separation mask is produced that, for example, converts all the image pixels corresponding to machine printed text, and none of the image pixels corresponding to handwritten or handprinted annotations. The separation mask is used in conjunction with the original image to produce separate handwritten annotations and machine printed text images. The invention also provides a method and apparatus for identifying the location of specialized type styles such as bold and italic is disclosed. The method erodes a binary image utilizing structuring elements which provide a relatively large number of hits in regions containing the specialized type styles.

Abstract: A decoding processing is executed in a multiple processing at high speed with a simple construction or control in a manner such that the image memory 11 stores an input compressed code, the multiplexer 14 selects the compressed code shift circuit 12 or 13 where the compressed code is shifted, and the decoder 15 decodes the shifted compressed-code.

Abstract: Disclosed is a technique for deriving a composite video image by merging foreground and background video image data supplied from a plurality of separate video signal sources employing pattern-key insertion, rather than prior-art color-key insertion, for this purpose. Pattern-key insertion involves replacing a first pattern in a video scene with a second pattern. This is accomplished by first detecting the first pattern in the video scene and estimating the pose of this detected first pattern with respect to a reference object in the video scene. The second pattern is then geometrically transformed using the pose estimate of the detected first pattern. Finally, the detected first pattern is replaced with the geometrically-transformed second pattern.

Abstract: A magnetic ink character recognition (MICR) system includes power management features so as to permit the unit to be powered by the auxilliary power provided by a generic host (e.g., an electronic cash register). The system also includes motorized conveyance features in combination with a track facilitating manual conveyance.

Abstract: A method and system for processing and storing data in which the average time needed for storing the processed data in a storage device is automatically measured, and a processing parameter is optimized in response to the measured average storage time. In some embodiments, the invention compresses and stores video data, automatically measures the average time needed for storing the compressed video in a storage device, and optimizes the compression rate in response to the measured average storage time. The invention provides adaptive control of the bandwidth of processed data output to a storage device, to maintain transfer of the processed data to any desired storage device with optimal (for example, maximum attainable) bandwidth. In some embodiments, average throughput time for data transfers to and from a desired storage device is automatically measured, and an optimal compression rate is set in response to the measured time.

Abstract: In certain image analysis applications, it is desirable to compress the image while emphasizing a selected region of the image. The invention is a means for to allocating more bits, and thus better quality in the decoded image, to the selected region at the expense of other regions of the image. This allows efficient compression of the image for storage or transmission with those regions deemed to be important preserved at high quality and other regions stored with minimal quality to preserve the context of the image.

Abstract: A pattern recognition system capable of handling the non-Gaussian feature vector distribution in the feature vector space such that the recognition rate can be improved while using the pattern matching based on the assumption of the Gaussian feature vector distribution. In the system, a nonlinear transformation for each recognizable category is applied to the feature vector extracted from the input pattern to be recognized, to obtain a transformed feature data for the input pattern, where the nonlinear transformation maps linearly inseparable distributions in a vector space containing the feature vector onto linearly separable distributions. Then, the transformed feature data for the input pattern is compared with reference feature model for each recognizable category indicating a feature vector distribution for each category, to find a category of the input pattern as that of the reference feature model closest to the transformed feature data for the input pattern.

Abstract: An image processing apparatus 30, which can solve the problems of delay in dot generation in beginning portions of areas of low or high density and tailing after finishing areas of low or high density and carry out speedy binary coding image processing without accompanying side effects of quality depletion and without the need to utilize a complicated processing circuit: includes error correction unit 34 which corrects multigradation image data 200 and outputs it, threshold error setting unit which sets a binary coding threshold value based on the gradation value of said target pixel multigradation image data 200 and binary coding unit 36 which, based on the set threshold value, converts the previously mentioned corrected pixel data into the previously mentioned bigradation image data and outputs it; the gradation value of the previously mentioned target pixel multigradation image data being data, the median value of the previously mentioned first gradation value and second gradation value being m and the pre

Abstract: The noise is eliminated from the images by carrying out a first Fourier transform of the images of an original batch of images. Each of these transformed images is then broken down into Fourier series to reveal the main harmonics of a periodic evolution of the original images and of the transformed images. This harmonic breakdown is used to recompose transformed images that are thus filtered by the abandoning of the non-useful harmonics. The filtered transformed images are used to carry out a reverse Fourier transform to obtain, ultimately, filtered original images. It is shown that the filtering in this case removes the noise without lowering the quality of the structures of the image, without distributing the noise among all these structures.

Abstract: A method of determining unintended inclination in an image of characters that is to be processed by a device such as a copy machine, a facsimile machine, or an optical character recognition system. An image of characters is generated, and expansion is performed on this image the optimal number of times. The number of expansions is based on the differences in the area of the non-background portion of the image at various stages of expansion. Next, the major direction of inclination is determined for the image. The inclination angle of the image is then determined based on the inclination factors of the character lines for various zones in the image.

Abstract: A method and apparatus for obtaining an image from an object by acquiring training signal measurements which represent images of a plurality of training objects having at least one predetermined feature in common with the object and derive, from the training signal measurements, a set of basis functions that provide a convergent series expansion of the images. The method and apparatus determine a signal measurement prescription for the object based on the basis functions. A signal measurement acquiring device is controlled to acquire signal measurements of the object as determined by the signal measurement prescription. A truncated basis function expansion of the image is generated from the acquired signal measurements. Estimates of additional signal measurements are carried out based on the truncated basis function expansion. The image is reconstructed using the obtained signal measurements and the estimated additional signal measurements.

Abstract: A method of dividing a block pattern for use in a block exposure, to be implemented on a computer, divides an arbitrary block which is to be formed in a block mask that is used for the block exposure when the arbitrary block is judged as including a prohibiting pattern which is undesirable from a point of view of the block exposure.

Abstract: In an image compressing apparatus of this invention, a table of extended MH codes is prepared with respect to combinations of consecutive black/white pixels. When a portion where frequent changes between black and white occur is to be coded, consecutive black/white pixels are coded at once without measuring the run lengths of pixels. These extended MH codes are obtained by combining MH codes corresponding to black and white runs whose run lengths are determined in one byte of an original image.

Abstract: A method for restructuring information stored in physical design image form, such as an image of a layer in a semiconductor package, into a hierarchical area specification model useful in automated design applications. The restructuring results in recognizing identical patterns in the image and storing common information about the patterns in a single location to decrease storage space required and improve access efficiency by design application programs needing the information. Parameters controlling the method can be adjusted to produce a hierarchical model that is particularly suited to the needs of a particular application program.

Abstract: An image processing apparatus in a reproduction system includes an image input terminal having a device resolution of K pixels per unit length by L pixels per unit length (K x L). Each pixel is defined at a depth b representing one of b optical densities. The image input terminal emits an input image at the device resolution and depth (KxLxb). A memory is provided for receiving and storing as electrical signals the input image emitted from the image input terminal. A first processing means converts the resolution of the input image to a plurality of output images at a second resolution of M pixels per unit length by N pixels per unit length (M x N). Each pixel is defined at depth d representing one of d optical densities. The first processing means converts the input image to the plurality of output images by spatially offsetting a periodically repeating mapping defining the conversion between the input image and the output image.