Abstract: An image processing apparatus having a character extraction unit for extracting an area whose density distribution characteristic meets a predetermined condition such as a binarization threshold and a size and a type of local filtering, from an input image of multiple gray levels, and extracts an object area as an output image from the input image by using the characteristic extraction unit. An area designation means designates an area having a uniform density distribution and containing the object area, to the input image. Condition determination means determines the condition for the characteristic extraction unit based on the density distribution characteristic of the input image in the designated area. In an image processing expert system, the image characteristics of the object image and the background in the area designated by the area designation means are evaluated and analyzed and the inquiry in the form of message is effected to quantize the evaluation of the image characteristic.

Abstract: In a method of recognizing a pattern of a gray level image the image to be processed is subjected to a normalization process, local gray level feature parameters are extracted from the normalized image at its sampling points, and the pattern is identified by using the extracted feature parameters in accordance with a predetermined recognition procedure. An apparatus for recognizing a pattern of a gray level includes a memory for storing a gray level image having several brightness tone levels, a normalization circuit for normalizing the brightness of the gray level image to be processed, an extraction circuit for extracting local gray level feature parameters from the obtained normality image at specific points, and a recognition circuit for identifying the pattern by using the feature parameters in accordance with a predetermined.

Abstract: An original picture taken by an ITV camera is subject to a local maximum filter processing and, if necessary, further to a local minimum filter processing, so that a background image is formed from the original picture itself. A target image included in the original picture is extracted separated from the background image by the subtraction between the thus obtained background image and the original picture. According to the present invention, since the background image is formed on the basis of the original picture, the unevenness or change of brightness, which equally influences on both of the target image and the background image, has no influence on the accurate extraction of the target image.

Abstract: For the preparation of a tree structure recognition dictionary, in order to obtain the best decision tree, the maximum depth or the sum of the depths should be taken into account. For this purpose, there is provided a system and method for preparing a recognition dictionary which makes it possible to shorten both the maximum recognition time and the total recognition time by successively allocating to nodes of the decision tree features, for which a feature evaluation measure called "maximum estimated depth" for reducing the maximum depth or "sum of estimated node numbers" for reducing the sum of the depths is the smallest.