Abstract
This paper describes a novel shape classification technique in computer vision called PDL-HM, which combines the selection of morphological structuring elements from contour description languages, the extraction of shape characteristics by the hit- and-miss transform, and shape classification by a neural network. This real-time method is orientation independent and tolerates limited object overlap. It is illustrated by an application to fish species classification in an industrial enviromnent and performs excellently
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Amarson H (1989) Fish sorting by computer vision, PhD Thesis (unpublished). Technical University of Denmark, Lyngby
Cosgriff RL (1960) Identification of shape, Report 820-11. Ohio State University, Research Foundation, Columbus, Ohio, ASTIA AD254 792
Cybenko G (1989) Approximation of sigmoidal function. J Math Control System Sig 5:303–314
Duda RO, Hart, PE (1972) Use of the Hough transformation to detect lines and curves in pictures. Commun ACM 15:11–15
Eberhart RC, Dobbins RW (1990) Neural network PC tools: a practical guide. Academic Press, New York
Fu KS (1982) Syntactic pattern recognition and applications. Prentice Hall, Englewood Cliffs
Fukunaga K (1974) Statistical pattern recognition. Academic Press, New York
Funahasi K (1989) On the approximate realization of continuous mappings by neural networks. J Neural Networks 2:183–192
Giardina C, Dougherty E (1989) Morphological methods in image and signal processing. Prentice Hall, Englewood Cliffs
Gillies AM (1990) Automatic generation of morphological template features. SPIE 1350:252–261
Haralick RM, Sternberg SR, Zuang X (1987) Image analysis using mathematical morphology. IEEE Trans PAM-I-9 PAMI9:532–550
Hornik K (1991) Approximation capabilities of multilayer feedforward neural networks. J Neural Networks 2:251–257
Hu M (1962) Visual pattern recognition by moment invariants. IRE Trans Inform Theory 8:179–187
Jianning X (1991) Deomposition of convex polygonal structuring elements into neighborhood subsets. IEEE Trans PAMI-13:153–161
Kanunge T, Haralik RM, Zhuang X (1990) B-code dilation and structuring element decomposition for restricted convex shapes. SPIE 1350:419–430
Khotanzad A, Lu J-H (1990) Classification of invariant image representations using neural networks. IEEE Trans ASSP-38:1028–1038
Levine MD (1985) Vision in man and machine. McGraw-Hill, New York
Leymarie F, Levine MD (1988) Curvature morphology. IntReptCIM-88-26, McGill University, Montreal
Leymarie E, Levine MD (1989) Snakes and skeletons. Int Rept CIM-89-3. McGill University, Montreal
Liu HC, Srinath MD (1990) Partial shape classification using contour matching in distance transformation. IEEE Trans PAMI-12:1072–1079
Maragos PA, Schafer RW (1986) Morphological skeleton representation and coding of binary images. IEEE Trans ASSP-34:1228–1244
Mathéron G (1965) Elements pour une Theorie des Milieux Poreux. Masson, Paris
Morris JT, Rubin LD, Tirri H (1990) Neural network techniques for object orientation detection: solution by optimal feedforward network and learning vector quantization approaches. IEEE Trans PAMI-12:1107–1114
Otsu N (1979) Threshold selection for gray-level histograms. IEEE Trans System Man Cybernet SMC-9:62–66
Pao YH (1988) Adaptive pattern rcognition and neural networks. Addison Wesley, Reading
Pau LF, Ben B (1990) Contour tracking and corner detection in a logic programming environment. IEEE Trans PAMI-9:913–917
Pau LF, Gøtsche T (1992) An explanation facility for neural networks, J Intell Robot 5:193–206
Pau Lf, Olafson R (eds) (1991) Fish quality and control by computer vision. Dekker, New York
Pavlidis T, (1977) Structural pattern rcognition. Springer, New York
Sahasrabudhe SC, Banerjee S (1990) morphological shape descriptor: image algebra and morphological image processing. SPIE 1350:56–67
Serra J (1982) Image analysis and mathematical morphology. Academic Press, New Nork
Serra J (ed) (1988) Image analysis and mathematical morphology, vol 2. Theoretical advances. Academic Press, London
Sterling L, Shapiro E (1986) The art of prolog. MIT Press, Cambridge, Mass
Strachan NJC, Murray CK (1991) Image analysis in the fish and food industries. In Fish quality control by computer vision, Dekker, New York, pp 47–58
Tayama I, Shimdate M, Kubuta N, Nomura Y (1982) Application of optical sensors to fish sorting. Reito (Tokyo) Refrigeration 57:1146–1150
Vincent L (1991) Morphological transformations of binary images with arbitrary structuring elements. Sig Process J 22:34–47
Vogt RC (1989) Automatic generation of morphological set recognition algorithms. Springer, Berlin, Heidelberg, New York
Wagner H, Schmidt U, Rudek JH (1987) Distinction between species of sea fish. Lebensm Indust 34:20–23
Zernique F ((1934) Physica Acta, vol 1, pp 678–689
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Arnarson, H., Pau, L.F. PDL-HM: morphological and syntactic shape classification algorithm. Machine Vis. Apps. 7, 59–68 (1994). https://doi.org/10.1007/BF01215802
Issue Date:
DOI: https://doi.org/10.1007/BF01215802