Hitachi, Ltd.

Miyahiko Orita

Yoshiki Kobayashi

Tadaaki Mishima

Masato Suzuki

Masao Takatoo

Yuji Toda

Yutaka Kubo

Chieko Onuma

Morio Kanasaki

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. As a result, the area extraction procedure can be easily executed by the interaction with an operator.

Image processing apparatus

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.

System and method for preparing a recognition dictionary

For the preparation of a tree structure recognition dictionary, a feature set at each node of the tree should be the feature giving the largest discrete distribution number. When elements of an object are classified or divided into categories, if the number of combinations of subgroups, which are discrete, is the largest, the classification is the most effective. This classification is effected, when the distance between distributions for a certain feature is larger than a predetermined value.

Growing community of inventors

Hitachi, Japan

Miyahiko Orita