Graphic Symbol Recognition using Graph Based Signature and Bayesian Network Classifier

TL;DR

This paper introduces a novel structural and statistical approach for recognizing complex graphic symbols in technical documents, utilizing graph-based signatures and Bayesian networks to improve recognition accuracy.

Contribution

The paper proposes a new method combining graph-based signatures with Bayesian network classifiers for graphic symbol recognition, enhancing robustness and accuracy.

Findings

Achieved encouraging recognition rates on synthetic and degraded images.

Demonstrated effectiveness on architectural and electronic symbols from GREC databases.

Validated the approach's robustness to image deformation and degradation.

Abstract

We present a new approach for recognition of complex graphic symbols in technical documents. Graphic symbol recognition is a well known challenge in the field of document image analysis and is at heart of most graphic recognition systems. Our method uses structural approach for symbol representation and statistical classifier for symbol recognition. In our system we represent symbols by their graph based signatures: a graphic symbol is vectorized and is converted to an attributed relational graph, which is used for computing a feature vector for the symbol. This signature corresponds to geometry and topology of the symbol. We learn a Bayesian network to encode joint probability distribution of symbol signatures and use it in a supervised learning scenario for graphic symbol recognition. We have evaluated our method on synthetically deformed and degraded images of pre-segmented 2D architectural and electronic symbols from GREC databases and have obtained encouraging recognition rates.