Contour matching for a fish recognition and migration-monitoring system

Fish migration is being monitored year round to provide valuable information for the study of behavioral responses of fish to environmental variations. However, currently all monitoring is done by human observers. An automatic fish recognition and migration monitoring system is more efficient and can provide more accurate data. Such a system includes automatic fish image acquisition, contour extraction, fish categorization, and data storage. Shape is a very important characteristic and shape analysis and shape matching are studied for fish recognition. Previous work focused on finding critical landmark points on fish shape using curvature function analysis. Fish recognition based on landmark points has shown satisfying results. However, the main difficulty of this approach is that landmark points sometimes cannot be located very accurately. Whole shape matching is used for fish recognition in this paper. Several shape descriptors, such as Fourier descriptors, polygon approximation and line segments, are tested. A power cepstrum technique has been developed in order to improve the categorization speed using contours represented in tangent space with normalized length. Design and integration including image acquisition, contour extraction and fish categorization are discussed in this paper. Fish categorization results based on shape analysis and shape matching are also included.

[1]  D. Dudgeon,et al.  The computation of two-dimensional cepstra , 1977 .

[2]  Dah-Jye Lee,et al.  An automated fish species classification and migration monitoring system , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[3]  Louis A. Helfrich,et al.  Anadromous salmonid passage and video image quality under infrared and visible light at Prosser Dam, Yakima River, Washington , 2000 .

[4]  Donald G. Childers,et al.  Signal detection and extraction by cepstrum techniques , 1972, IEEE Trans. Inf. Theory.

[5]  C.W. de Silva,et al.  Use of image processing for the measurement of orientation with application to automated fish processing , 1990, [Proceedings] IECON '90: 16th Annual Conference of IEEE Industrial Electronics Society.

[6]  Sameer K. Antani,et al.  An imaging system correlating lip shapes with tongue contact patterns for speech pathology research , 2003, 16th IEEE Symposium Computer-Based Medical Systems, 2003. Proceedings..

[7]  D.P. Skinner,et al.  The cepstrum: A guide to processing , 1977, Proceedings of the IEEE.

[8]  Emanuele Trucco,et al.  Introductory techniques for 3-D computer vision , 1998 .

[9]  Dah-Jye Lee,et al.  Analysis of sequential complex images, using feature extraction and two-dimensional cepstrum techniques , 1989 .

[10]  Dennis D. Dauble,et al.  Difficulties in estimating survival for adult chinook salmon in the Columbia and Snake rivers , 2000 .

[11]  Dah-Jye Lee,et al.  A vision system performing lip shape analysis for speech pathology research , 2003, IECON'03. 29th Annual Conference of the IEEE Industrial Electronics Society (IEEE Cat. No.03CH37468).

[12]  M. Menard,et al.  A priori minimization in pattern recognition. Application to industrial fish sorting and face recognition by computer vision , 1997, Proceedings of 6th International Fuzzy Systems Conference.

[13]  James J. Little,et al.  A unified recognition and stereo vision system for size assessment of fish , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[14]  Gordon Mueller,et al.  Experiments in in situ fish recognition systems using fish spectral and spatial signatures , 1999 .

[15]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[16]  Longin Jan Latecki,et al.  Application of planar shape comparison to object retrieval in image databases , 2002, Pattern Recognit..

[17]  Chan,et al.  A trainable n-tuple pattern classifier and its application for monitoring fish underwater , 1999 .

[18]  Shunji Mori,et al.  Acute toxicant warning system based on a fish movement analysis by use of AI concept , 1988, Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications.

[19]  T F Krile,et al.  Power cepstrum and spectrum techniques applied to image registration. , 1988, Applied optics.

[20]  Dah-Jye Lee,et al.  Accuracy of Depth Information from Cepstrum-Disparities of a Sequence of 2-D Projections , 1990, Other Conferences.

[21]  Ralph Roskies,et al.  Fourier Descriptors for Plane Closed Curves , 1972, IEEE Transactions on Computers.

[22]  Dah-Jye Lee,et al.  3-D representation from time-sequenced biomedical images using 2-D cepstrum , 1990, [1990] Proceedings of the First Conference on Visualization in Biomedical Computing.