Symbol Recognition: Current Advances and Perspectives

Abstract

Abstract. The recognition of symbols in graphic documents is an intensive research activity in the community of pattern recognition and document analysis. A key issue in the interpretation of maps, engineering drawings, diagrams, etc. is the recognition of domain dependent symbols according to a symbol database. In this work we first review the most outstanding symbol recognition methods from two different points of view: application domains and pattern recognition methods. In the second part of the paper, open and unaddressed problems involved in symbol recognition are described, analyzing their current state of art and discussing future research challenges. Thus, issues such as symbol representation, matching, segmentation, learning, scalability of recognition methods and performance evaluation are addressed in this work. Finally, we discuss the perspectives of symbol recognition concerning to new paradigms such as user interfaces in handheld computers or document database and WWW indexing by graphical content.

Symbol recognition using spatial relations

“…[Cordella and Vento, 2000;Lladós et al, 2002] show that these methods are particularly suited for isolated line symbols, not for composed symbols connected to a complex environment. In order to exploit the information embedded in those documents, one needs to be able to extract visual parts and formalise the possible links that exist between them.…”

Local Structural Analysis: A Primer

“…The local analysis employs different approaches from character recognition (latin [55], oriental [18]), and graphics recognition (technical documents [51], maps [43], symbols [32], and so on.). It extracts different objects from documents according to the exploration granularity.…”

“…The problem of document image interpretation is a vast field gathering three main applications: handwriting [58], graphics documents (technical documents [51], maps [43], symbols [32], and so on. ), and structured documents [39].…”

Symbols Recognition System for Graphic Documents Combining Global Structural Approaches and Using a XML Representation of Data

“…Into graphic documents, many objects could be described by graphs, especially symbols [10]. Thus, in a structural recognition system of symbols, the images processing step extracts graphs from images corresponding to symbols, and the structural recognition step exploits these graphs.…”