Using Grammars for Pattern Recognition in Images: A Systematic Review

Author(s)

Dias Pedro, Ricardo Wandre ^[1] ; Nunes, Fatima L. S. ^[1] ; Machado-Lima, Ariane ^[1]

Affiliation

^[1] Univ Sao Paulo, Sch Arts Sci & Humanities, BR-03828000 Sao Paulo - Brazil

• Document type: Review article
• Source: ACM COMPUTING SURVEYS; v. 46, n. 2 NOV 2013.
• Web of Science Citations: 4

Abstract

Grammars are widely used to describe string languages such as programming and natural languages and, more recently, biosequences. Moreover, since the 1980s grammars have been used in computer vision and related areas. Some factors accountable for this increasing use regard its relatively simple understanding and its ability to represent some semantic pattern models found in images, both spatially and temporally. The objective of this article is to present an overview regarding the use of syntactic pattern recognition methods in image representations in several applications. To achieve this purpose, we used a systematic review process to investigate the main digital libraries in the area and to document the phases of the study in order to allow the auditing and further investigation. The results indicated that in some of the studies retrieved, manually created grammars were used to comply with a particular purpose. Other studies performed a learning process of the grammatical rules. In addition, this article also points out still unexplored research opportunities in the literature. (AU)

• FAPESP's process: 11/50761-2 - Models and methods of e-Science for life and agricultural sciences
• Grantee: Roberto Marcondes Cesar Junior
• Support type: Research Projects - Thematic Grants
• FAPESP's process: 10/15691-0 - Proposition, implementation and validation of techniques for virtual interactive medical training
• Grantee: Fátima de Lourdes dos Santos Nunes Marques
• Support type: Regular Research Grants