ECIR-an electronic circuit diagram image recognizer

This paper describes a technique developed to analyze and recognize paper based electronic circuit diagram images. One of the key aspects of this recognition system relies on the identification of feature points used to guide a new line vectorization method developed for circuit diagram images. The feature paints are also used as a discriminate element in the symbol classification process. Once the lines are vectorized, the open symbols are first identified by a syntax-based classifier, followed by the identification of the loop-based symbols using a supervised parametric statistical classifier. We have demonstrated the proposed system by implementing and testing it on various real images of circuit diagrams.