Some methods of constructing symmetry lines and shape grids for image interpretation, with applications in the fishing industry

AbstractThere is a need to ‘sort fish by species and to identify individual mackerel (Scomber scombrus). This is being met by developing an image processing system comprising a colour video camera, frame grabbing boards and a computer workstation.Using suitable software, grids are drawn on the fish images and used as reference for colour and pattern analysis, enabling the fish to be sorted by species. Methods of producing the grids by thinning algorithms (classical and simple) and the method of smoothed local symmetries are discussed.Individual mackerel can be distinguished by their striations, a distinctive pattern which runs along the top half of their bodies. By filtering and thinning, the striations are enhanced and transformed from 2D to ID. The transformed patterns can then be used to differentiate between the individual mackerel.

[1]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[2]  D. T. Lee,et al.  Medial Axis Transformation of a Planar Shape , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Andrew Zisserman,et al.  Using a mixed wave/ diffusion process to elicit the symmetry set , 1989, Image Vis. Comput..

[4]  G. Scott,et al.  Parallel algorithms for shape representation , 1988 .

[5]  HARRY BLUM,et al.  Shape description using weighted symmetric axis features , 1978, Pattern Recognit..

[6]  Michael Brady,et al.  Generating and Generalizing Models of Visual Objects , 1987, Artif. Intell..

[7]  Andrew P. Witkin,et al.  Analyzing Oriented Patterns , 1985, IJCAI.

[8]  T. Pavlidis Algorithms for Graphics and Image Processing , 1981, Springer Berlin Heidelberg.

[9]  Ugo Montanari,et al.  Continuous Skeletons from Digitized Images , 1969, JACM.

[10]  Alastair R. Allen,et al.  Fish species recognition by shape analysis of images , 1990, Pattern Recognit..

[11]  M. Brady,et al.  Smoothed Local Symmetries and Their Implementation , 1984 .

[12]  P. V. de Souza,et al.  Computer location of medial axes. , 1977, Computers and biomedical research, an international journal.

[13]  Lawrence O'Gorman,et al.  An approach to fingerprint filter design , 1989, Pattern Recognit..