Visual Feature Array based Cognitive polygon recognition using the UFEX text categorizer

Author

Reskó, Bama ; Tikk, Domonkos ; Hashimoto, Hideki ; Baranyi, Péter

Author_Institution

Inst. of Ind. Sci., Tokyo Univ.

fYear

2006

fDate

3-5 July 2006

Firstpage

539

Lastpage

544

Abstract

This paper presents a cognitive vision based approach to recognize polygons on a natural image. The approach is based on the visual feature array (VFA), which is a cognitive computational model of the mammalian primary visual processing. VFA, as a multidimensional orthogonal data structure, contains data about the line segment and vertex features in the edge detected input image. Based on the features available in VFA, using the universal feature extractor classifier (UFEX), the problem of polygon categorization and recognition is addressed. The results are compared to solutions by conventional neural networks, such as the learning vector quantization network

Keywords

cognitive systems; computer vision; edge detection; feature extraction; image segmentation; medical computing; natural scenes; neural nets; object recognition; UFEX text categorizer; cognitive computational model; cognitive polygon recognition; cognitive vision; edge detection; learning vector quantization network; mammalian primary visual processing; multidimensional orthogonal data structure; neural networks; polygon categorization; universal feature extractor classifier; visual feature array; Computational modeling; Data mining; Data structures; Feature extraction; Image edge detection; Image recognition; Image segmentation; Multidimensional systems; Text categorization; Text recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Mechatronics, 2006 IEEE International Conference on

Conference_Location

Budapest

Print_ISBN

0-7803-9712-6

Electronic_ISBN

0-7803-9713-4

Type

conf

DOI

10.1109/ICMECH.2006.252584

Filename

4018419