Abstract: Described is an image processing system which is operative to automatically determine a quadrilateral object such as a character frame, page mark, or position correction mark only with a mouse click. A field is automatically specified by displaying a scanned image of a form including a black frame on a display, clicking within a character frame at the left end for each recognition field, and clicking within a character frame at the right end of the same field. In this case, a field position/size determination program scans the image in the vertical and horizontal directions from the two clicked points to detect the inner wall of the black frame, and produces a histogram by establishing rectangles between two character frames to automatically detect the number of character frames in the field and the thickness of the black line between the character frames.

Abstract: The detection of a nearest neighbor is calculated at high speed and with high accuracy. Feature space grouping is performed, with one, or two or more features being assigned to each group. A check is performed to determine whether or not a calculated distance value that is acquired before the limits for a group is reached has exceeded the threshold value THR.sub.-- MIX for each group. The threshold value that is set for THR.sub.-- MIX is the average of the threshold value that is determined based on the cumulative quantity of the features that is acquired and the threshold value that is based on the number of dimensions. When the distance value for each group is greater than the threshold value THR.sub.-- MIX, first phase screening is performed to exclude, from the succeeding distance calculations, the prototype that provides that distance value. Then, for a group for which the first phase screening is performed, the threshold value THR.sub.

Abstract: OCR processing involves: acquisition of images from image capturing devices; determination of location/size/style for each character; normalization; smoothing for large corners; smoothing by the deletion of individual protruding and extraneous dots; extraction of features; pattern matching; automatic error correction using a word dictionary; and output of recognition results.In the present invention, high speed software processes accomplish smoothing large corners and deletion of individual protruding and extraneous dots. In this software processing, the smoothing process is performed by shifting bit rows and using only the logical operators NOT, AND, and OR; not used are the often employed conventional conditional branch commands, such as the "if then else" and "switch" statements. This smoothing method (using only NOT, AND, and OR) contributes to a substantial reduction in the processing speed.

Abstract: An apparatus for separating an image from a black frame quickly and precisely wherein corner coordinates for a character field are inferred by using a parameter relative to a character frame layout, and more precise corner coordinates are detected by pel distribution in a partial range. The positions of inner walls of a black frame are then inferred by using the detected corner coordinates and the parameter relative to the character frame, and a detection area is set. The positions of the inner walls are precisely detected by the pel distribution in the detection area, and smoothing process is performed on the detected values by employing the detected values of other adjacent black frames. Sequentially, white lines are drawn along the inner walls to separate the black frame from the character, and noise is removed. In consonance with a skew value, the detection area is divided to change the set range, and data separation is performed by using two white lines with a step difference between them.

Abstract: A computer-implemented method is provided for extracting bending points from character images for use in an optical character recognition procedure that recognizes the characters. In a preferred aspect a contour (boundary of strokes) of a character image is traced and strong curvatures are detected as bending points using heuristically determined parameters with some attributes such as position, angle of curvature, convex or concave, and acuteness being provided as a data set output.

Abstract: A color image region management system suitable for retrieving a region having a specified color. Color class is determined for each picture element of image data in which the color data of each picture element is expressed by a trichromatic system. In the trichromatic system, it is determined to which color class the color of the picture element belongs of a plurality of color classes divided on the basis of a perceptual color system. There is a color index memory for constructing tree structure data reaching a root node with blocks each including at least one picture element as a leaf node, and calculating, for each node in the tree structure data and for each color class in regards to the picture elements included in the node, the frequency of picture elements having a color belonging to the color class. The calculated frequency of the picture elements is stored as a color index for each color class.

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 catalyst in the form of a honeycomb structured cordierite carrier having platinum supported in a loading weight of at least 0.20 mg per square centimeter of the apparent outer surface area of the catalyst is effective in a process for oxidizing CO in exhaust gas from a sintering furance wherein it maintains high CO oxidiation efficiency for a longer period of time, requiring less frequently regeneration and less power consumption.

Abstract: Preselection of words for spelling error check utilizes unique attribute information of words. The attribute information is generated for each vocabulary word and each vocabulary word is classified based on the attribute information and then stored in the dictionary. The attribute information is generated by obtaining character categories for each vocabulary word, ordering the character categories with a predetermined criterion, taking a leading character categories, and then generating one or more combinations of m character categories from the n leading character categories, which combinations being the attribute information. For an inputted character string to be checked, the attribute information is also generated, and the vocabulary words included in one or more classes specified by the attribute are selected as the candidate words for the correct word.

Abstract: A system and method for electronically segmenting character components on character-containing documents involving first scanning a document and quantizing the image information obtained by the scanning into two levels, e.g., black and white, by 1 and 0 bits, and from the quantized information, m-bit OR groups are generated by sequentially ORing every m-th bit in a first direction of the quantized image, where m is an integer equal to or greater than two. The black (character) bits in each of the m-bit OR groups are counted and processed using the steps of: sequentially calculating sums of n consecutive count values by shifting one by one the count values obtained by the counting along a second direction perpendicular to the first direction; and then, segmenting character components by comparing the sums with a predetermined threshold value.