Employing fuzzy intervals and loop-based methodology for designing structural signature: an application to symbol recognition

TL;DR

This paper introduces a novel symbol recognition method combining fuzzy intervals, structural graph signatures, and Bayesian networks, demonstrating robustness to noise and deformations in graphic symbols.

Contribution

It presents a new structural signature for symbols using fuzzy intervals and Bayesian networks, enhancing robustness and feature selection in symbol recognition.

Findings

Robust recognition rates against noise and deformations.

Effective feature pruning with Bayesian network.

Successful application to symbol spotting in documents.

Abstract

Motivation of our work is to present a new methodology for symbol recognition. We support structural methods for representing visual associations in graphic documents. The proposed method employs a structural approach for symbol representation and a statistical classifier for recognition. We vectorize a graphic symbol, encode its topological and geometrical information by an ARG and compute a signature from this structural graph. To address the sensitivity of structural representations to deformations and degradations, we use data adapted fuzzy intervals while computing structural signature. The joint probability distribution of signatures is encoded by a Bayesian network. This network in fact serves as a mechanism for pruning irrelevant features and choosing a subset of interesting features from structural signatures, for underlying symbol set. Finally we deploy the Bayesian network in supervised learning scenario for recognizing query symbols. We have evaluated the robustness of our method against noise, on synthetically deformed and degraded images of pre-segmented 2D architectural and electronic symbols from GREC databases and have obtained encouraging recognition rates. A second set of experimentation was carried out for evaluating the performance of our method against context noise i.e. symbols cropped from complete documents. The results support the use of our signature by a symbol spotting system.