Abstract: An improved machine vision apparatus, of the type having a search element capable of estimating the location of a template image in a candidate image, includes an element that accepts signals representative of the template and of a candidate image. Those signals are applied to the search element to obtain its estimate of location. A correction element responds to the resulting approximation by the location-finder for generating a signal representative of more exacting location based on a known relationship between the location-finder output and more exacting locations of the template in a model of the candidate image.

Abstract: A method of making color and gradation correction performs color and gradation correction differently for a human subject image and a computer graphic image before or after composing these images. A gradation correction is carried out by the use of linear table data written in a look-up table for computer graphic images and non-linear table data for human subject images. A color correction circuit for transforming image data by the use of a matrix calculation comprises three look-up table memories and an adder for adding together outputs from the look-up table memories for each color to be color corrected. In these three look-up table memories, different table data are written in, according to the kinds of human subject image and computer graphic image. There are provided a plurality of different table data for human subject images and computer graphic images, respectively and suitable table data are selected according to a human subject image and a computer graphic image to be composed.

Abstract: A transform approach to image coding where pixels are coded in the order prescribed by a predetermined "List". The code for each pixel is developed by computing a prediction for the pixel based on the known pixel values in the neighborhood of the pixel and subtracting this prediction from the true value of the pixel. This results in a sequence of predominantly non-zero valued pixel prediction errors at the beginning of the encoding process (of each block), and predominantly zero valued pixel prediction errors towards the end of the encoding process. Enhancements to this approach include adaptive encoding, where pixel sequences having expected zero prediction errors are not encoded, and run length encoding of the signals to be transmitted or stored for augmenting the encoding process.

Abstract: This invention enables easy and fast selection of candidates for an inputted character image among the character categories by search of a tree-structured dictionary. Each ordinary node of the tree structure has three branches, that is two ordinary nodes and one reject node, and compares the multivalued feature extracted from the inputted character image for the node concerned, with a threshold, upper limit and lower limit values. If the feature value is out of the limited range, the search goes down to the reject node at the next level. If not, the search goes down to the right or left node at the next level based on the comparison of the feature value with the threshold value. Reject nodes have no branch. The tree structure has character category information as leaves connected to the bottom ordinary nodes and another character category information for all the reject nodes.

Abstract: A digital subsystem for improving the resolution of a TV digital signal by inserting additional digital samples into the digital TV signal in response to the correspondence of the digital signal and predefined patterns. The digital subsystem is a logic circuit which is responsive to received digital samples to group these digital samples into sets of samples. The digital circuit then calculates the slope between pairs of digital samples of each set and utilizes the calculated slopes to determine the correspondence to the predefined patterns. The determined predefined pattern designates the digital sample to be inserted into each set. The inserted digital sample is either equal to one of the digital samples or the average between two of the digital samples of each set. The calculation of the slopes results in a logical "0" for a constant slope and a logical "1" for a negative or a positive slope.

Abstract: A serial data image processing system is described whereby interconnect artwork for electronic component manufacturing is scanned by a 1.times.n CCD image pickup element and converted into serial digital data. The serial digital data representing the original image is processed by a programmable serial image processor to detect flaws in the original image artwork. The serial data digital image processor is comprised of a plurality of pipe elements, the configuration of which can be arranged for parallel or serial processing. Each pipe element contains a plurality of 4.times.5 pixel neighborhood array processing blocks, each of which can be programmed to perform one of a number of neighborhood image enhancement techniques. The 4.times.5 pixel neighborhood provides single-pass thinning and trimming algorithms which in turn allows for more efficient processing to be performed in the serial pipeline combination of a plurality of transformation neighborhoods.

Abstract: A character region extracting method adapted to character recognition comprises the following three steps. The first step is to segmentate a first region (BL1) from a document image by extracting projection of the document image in a first direction parallel to a character string and detecting a range in which the projection is continuous in a second direction perpendicular to the first direction. The range defines the first region. The second step is to segmentate a second region (sBL1) from the first region by extracting projection of the first region in the second direction and detecting a range in which the projection is continuous in the first direction. The range defines the second region. The third step is to segmentate a third region (BL2) from the second region by extracting projection of the second region in the first direction and detecting a range in which the projection is continuous in the second direction. The range defines the third region.

Abstract: The present invention relates to a system for the acquisition of data inscribed on a support. It more particularly applies to the acquisition of graphic data, such as characters, curves or all types of lines present on a reflecting or transparent support, whereby said data are monochromatic or polychromatic. The system according to the invention makes it possible to digitize graphic data on a support. It can also permit the acquisition of data in photometry, densitometry, and so forth.