Localization of Endoscopic Capsule in the GI Tract Based on MPEG-7 Visual Descriptors

Author

Duda, K. ; Zielinski, T. ; Fraczek, R. ; Bulat, J. ; Duplaga, M.

Author_Institution

AGH Univ. of Sci. & Technol., Krakow

fYear

2007

fDate

5-5 May 2007

Firstpage

1

Lastpage

4

Abstract

The paper addresses the problem of localization of video endoscopic capsule in the gastrointestinal (GI) tract on the base of appropriate classification of images received from it. In this context usefulness of MPEG-7 image descriptors as classification features has been verified. For classification purpose various state of the art tools were used including Neural Networks and Vector Quantization. The dimension of the problem was also reduced by the Principal Component Analysis. Novelty of the presented approach consists in joint application of mentioned above techniques for recognition of the GI region inspected by the capsule by means of classification of MPEG-7 features to different parts of GI tract. In this research recognition of the upper part organs of the GI tract has been performed.

Keywords

endoscopes; feature extraction; image classification; medical image processing; neural nets; principal component analysis; vector quantisation; video coding; MPEG-7 visual descriptors; classification features; endoscopic capsule localization; gastrointestinal tract; images classification; neural networks; principal component analysis; vector quantization; video endoscopic capsule; Biomedical imaging; Endoscopes; Gastrointestinal tract; Image resolution; MPEG 7 Standard; Medical diagnostic imaging; Neural networks; Principal component analysis; Vector quantization; Video recording; MPEG-7 image descriptors; Principal Component Analysis; Vector Quantization; endoscopic capsule; gastrointestinal (GI) tract;

fLanguage

English

Publisher

ieee

Conference_Titel

Imaging Systems and Techniques, 2007. IST '07. IEEE International Workshop on

Conference_Location

Krakow

Print_ISBN

1-4244-0965-9

Electronic_ISBN

1-4244-0965-9

Type

conf

DOI

10.1109/IST.2007.379580

Filename

4258780