Matsushita Electric Industrial Co., Ltd.

Omur Bozma

Junichi Hada

Masamichi Morimoto

When an image of an object is recognized, a template having a size smaller than the object is used. First, operation reference points C.sub.s (X.sub.m, Y.sub.n) are set at steps smaller than lengths along the X and Y directions of an image of an object to be recognized, and a template T(x.sub.i, y.sub.i) is set at the operation reference points C.sub.s (X.sub.m, Y.sub.n). Then, an equation, ##EQU1## is operated based on the template T(x.sub.i, y.sub.i) and the image data P(X, Y). Next, candidate points are determined as points having M(X.sub.m, Y.sub.n) larger than a reference value. Then, a position of the image of the object is determined according to the candidate points. Even if an image to be recognized is inclined, the position and the slope of the image can be detected at a fast speed even for image data with noise.

Pattern detection method

In a component detecting method and apparatus, intensity data stored in an intensity data storing device are rearranged in order of increasing intensity data. An intensity data quadratic differential table is formed by quadratically differentiating the intensity data of an intensity profile with respect to a data number of the intensity data. The data number at a zero-crossing point at which a quadratic differential data obtained by quadratically differentiating the intensity data is changed between positive and negative through zero from the intensity data quadratic differential table is detected. A threshold value is determined according to the intensity data of the intensity profile corresponding to the data number at the zero-crossing point. So, the component detect method and apparatus can detecting an image of the component from a background with the appropriate threshold value even when the component to be recognized is dirty or the intensity of the background fluctuates

Growing community of inventors

Istanbul, Turkey

Omur Bozma