Abstract: In a position recognizing method and an apparatus, an edge is detected by scanning a one-dimensional model including an edge to be recognized and one-dimensional edge detecting data of an image obtained via a camera so as to determine the difference between the density of the pixel of the one-dimensional model and the density of the corresponding pixel of the one-dimensional edge detecting data and the geometric balance therebetween. Then, the amount of data for detecting the edge becomes smaller and the pattern or parts can be recognized without controlling the binary level and at a high speed.

Abstract: A pattern recognition apparatus detects a coincidence between an input image pattern and a target pattern. Input image data f.sub.ij are received, where f.sub.ij denotes a concentration of the input image pattern at a picture element i,j on a two-dimensional plane of the input image pattern. Mask data g.sub.uv is stored, where g.sub.uv denotes a concentration of the target pattern at a point u,v on a two-dimensional plane of the target pattern. The mask data g.sub.uv is scanned with respect to the input image data f.sub.ij and a proportional coefficient is computed corresponding to each picture element i,j of the two two-dimensional plane of the input image pattern. The proportional coefficient denotes a ratio between the concentration of the input image data f.sub.ij and the concentration of the mask data g.sub.uv. The input image data f.sub.ij is divided into a plurality of partial templates denoting a two-dimensional subsection of the input image pattern.