One Dimensional Object Segmentation and Statistical Features of an Image for Texture Image Recognition System

Authors: Nang Thwe Thwe Oo

Abstract:

Traditional object segmentation methods are time consuming and computationally difficult. In this paper, onedimensional object detection along the secant lines is applied. Statistical features of texture images are computed for the recognition process. Example matrices of these features and formulae for calculation of similarities between two feature patterns are expressed. And experiments are also carried out using these features.

Keywords: 1-D object segmentation, secant lines, objectoccurrence(frequency) matrix, contiguity matrix, statistical features.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1055313

References:

[1] Rafael C. Gonzalez, Richard E. Woods.,Digital Image Processing 1993, Wesley Publishing Company, Inc. U.S.A.
[2] J. K. Hawkins, Textural Properties for Pattern Recognition. Academic Press, New York, 1970, Ðü. 347 - 370.
[3] William K. Pratt, Digital Image Processing: PIKS Inside, Third Edition. Los Altos, California, c. 519 - 548, 2001.
[4] C. H. Chen, L. F. Pau. The Handbook of Pattern Recognition and Computer Vision (2nd Edition). P. S. P. Wang (eds.), World Scientific Publishing Co., c. 207 - 248, 1998.
[5] Li Yi Wei. Texture synthesis by fixed neighborhood searching. PhD. Stanford university, 2001.
[6] Mishulina O.A., Labinskaya ðÉ. ðÉ., Sharbinina ð£.ðÆ. Practical for the course "Introduction to theory of neural network". ð£.: MEPhI, 2000.
[7] Win Htay, Histological image recognition method in the medical diagnostic problem, Science conference, MEPhI-2006, T3.
[8] Mishulina ð×.ðÉ., Win Htay, Texture image classification using vector neural network. XV International technological science seminar, Alushta,18-25 September 2006.
[9] Mishulina ð×.ðÉ., Win Htay, Feature image recognition system. Science conference MEPhI- 2007, Russia, ð£.:ð£ðÿðñðÿ, 2007
[10] Mishulina ð×.ðÉ., Win Htay, Texture image recognition in the vector neural network, IX All Russian techno-science conference «Neuro- 2007». ð£.:ð£EPhI, 2007. p. 146-157.
[11] Win Htay, Secant line technology for the texture image processing and recognition. MEPhI-2007, Russia, ð£.:ð£ðÿðñðÿ, 2007