Ezel Inc.

Yozan Corporation

Sharp Corporation

Ryohei Kumagai

Makoto Yamamoto

Sunao Takatori

Koji Matsumoto

Zi Quan Hong

Weikang Yang

Tooru Takahashi

Kaoru Hiiro

Harumi Shimizu

Manabu Oosaka

Kazuo Maruta

Sunao Takstori

Tetsuo Ohsiro

Koji Matsumato

A method of condensing color image data in an image processing system so as to simplify operations while reducing errors in the condensation. The method includes, by computer, generating electrical signals corresponding to color image data representative of a physical image; associating an electrical signal corresponding to a representative code with portions of the signals representative of data in the color image data corresponding to each of the pixels; grouping together electrical signals representative of pixels having identical representative codes to form at least one group; assigning to the representative code for each of the at least one group a condensed pixel representable by the representative code for that group; and setting an electrical signal portion corresponding to each pixel in that group equal to an electrical signal representative of a pixel corresponding to the condensed pixel.

Method for quantizing color image data by minimizing least squares error

A data processing system including a plurality of neural layers characterized in that each neural layer is divided into a plurality of groups and that neurons in one of the group in one layer are connected only with neurons in corresponding group of adjacent layers, whereby independent neural cells are constructed each of which comprises corresponding groups of neurons. The minimum number of neural layers is equal to the difference between the degree of abstraction of an output data and the degree of abstraction of an input data.

Data processing system

An adaptation method for a data processing system comprising a plurality of neurons each of which outputs an output according to a comparison between a sum of multiplied inputs by weights and a threshold, characterized in the threshold of the neuron which has generated significant output at certain point of time is compulsorily increased to a maximal value and the weight of the neuron is adapted for a constant value of the inputs wherein the threshold is decreased to a value at the point.

Adaptation method for data processing system

An image processing method for thinning lines converts pixels having a density of a configuration to a background density. Pixels are converted according to conditions which include densities of pixels in a neighborhood around a pixel to be processed. Pixels to be converted to the background density are first converted to an index value. Subsequent pixels are evaluated using the index values of adjacent, previously evaluated pixels. Index values are then converted to the background density.

Image processing method for thinning lines using index values

A method of recognizing a character including the steps of reading sample characters and generating an image corresponding to the sample characters. Then calculating density projections of each sample characters. A primitive characteristic vector is then extracted from each density projection. Compression then occurs so that an optimal distinction vector and a corresponding characteristic space can be determined. A character to be recognized is then read and an image corresponding to said character to be recognized is generated. A density projection is then made from the image of the character to be recognized. A primitive characteristic vector is then made from the density projection of the character to be recognized. A secondary characteristic vector is then produced by projecting the primitive characteristic vector of the character to be recognized into the compressed characteristic space. Finally one of the sample characters is outputted, based upon the secondary characteristic vector, as the recognized character.

Apparatus and method for recognizing a character

A method for detecting the location of a human being in three dimensions from a spatial image of an area that is generated using a lens. Portions of the image having density values within a predetermined range are labeled, those density values corresponding to brightness levels of the pixels in the image. A labeled portion corresponding to a part of the head is selected when the top region of that portion forms the shape of an arch. The width of the selected portion is then determined. Assuming that the part of the head having hair on all persons has a constant horizontal width, the distance from a lens to a human being is calculated based on the determined width of the selected portion. The coordinates of the person are determined based on that distance.

Method of detecting the location of a human being in three dimensions

An image processing system has an input portion to which pixel data is inputted, a convolution processing portion processing each set of pixels in a predetermined convolution area so as to output a processed data for every predetermined convolution area. A computational portion calculates a parameter necessary for image processing according to the processed data from the convolution processing portion. A converting portion includes a selecting means, to which the output of the computational portion is inputted, a high speed memory to which the output of the selecting means is inputted and a light computational portion for performing light computation to which the output of the high speed memory is inputted and the output of which is inputted to the selecting means.

High speed image processing system having a preparation portion and a

There is provided a layer construction of neural layers according to the abstraction degree of data to be processed, and data is inputted to a neural layer corresponding to its abstraction degree.

Method for processing data using a neural network having a number of

An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an object sensing unit. The system also includes a memory for storing a matrix. A matrix calculation unit is included for performing matrix calculations and producing weighted data. A quantizer unit for quantizing the weighted data is included within the system. An adder unit and a maximum limiting unit are also included within the system. The adder unit adds matrices and the limiting unit limits values of an output matrix. Finally, the system includes a recognition unit for recognizing the sensed object based upon the output matrix.

Associative pattern conversion system and adaptation method thereof

A method and system for comparing an input image with a stored image. An input image is obtained and processed. By the processing of the input image, a rough judgment of whether the input image corresponds to the stored image is obtained. If the input image does correspond to the stored image, then further processing is preformed on the input image. Characteristics of the processed input image are determined. The system then determines whether the characteristics correspond to characteristics of the stored image.

Method and system for comparing two images by making an initial rough

A data processing system based on the concept of a neural network includes a normalizing circuit and driving elements. Each driving element has an output inductor magnetically coupled to an input inductor of the normalizing circuit. In the normalizing circuit, the input inductor is coupled to receive an input signal. The circuit also has a switching circuit responsive to the input signal and a switched inductor energized in response to the switched signal. The switched inductor comprising either a hooked or a spiral inductor.

Inductively coupled neural network

A lighting system for camera comprising light irradiation means which possesses plural luminous objects arranged circularly concentric to a camera lens, and cylindrical shield parts to restrain light from outside arranged between the camera and an object to be photographed.

Lighting system for camera

A system for performing parallel processing of digital data in order to compute numerical functions and extract characteristic information based on the digital data. After the digital data is processed by the parallel processing portion, a sequential processing portion rewrites the processing data according to a sequential processing operation so that operations such as thinning and labelling may be performed.

Data processing system for rewriting parallel processor output data

A dither processing method generates a binary-value image from an original image. The original image is converted to a binary-value image by a dither process. For each area in the dither image that corresponds to a dither cell, a representative density is calculated from the number of black (or white) pixels produced by the dither process. A median value of representative densities is then used as a threshold, and the original image is converted to a binary-value image using the threshold. By using the median of representative values, lighting of the original image is corrected.

Dither processing method

An associative pattern conversion system is disclosed which may be used for image recognition. The system includes an image input portion, an image processing portion and a recognition portion. The image processing portion includes a process unit for extracting characteristics and a frame memory for holding image data. The recognition portion, which includes a component for the learning of data to be associated, obtains the extracted characteristics from the image processing portion and performs associative pattern conversion from the image input portion. The system of the present invention may be applied to any neural network, preferably a matrix calculation type neural network.

Growing community of inventors

Tokyo, Japan

Ryohei Kumagai