zbMATH — the first resource for mathematics

Detection and recognition of contour parts based on shape similarity. (English) Zbl 1138.68050
Summary: Due to distortion, noise, segmentation errors, overlap, and occlusion of objects in digital images, it is usually impossible to extract complete object contours or to segment the whole objects. However, in many cases parts of contours can be correctly reconstructed either by performing edge grouping or as parts of boundaries of segmented regions. Therefore, recognition of objects based on their contour parts seems to be a promising as well as a necessary research direction.
The main contribution of this paper is a system for detection and recognition of contour parts in digital images. Both detection and recognition are based on shape similarity of contour parts. For each contour part produced by contour grouping, we use shape similarity to retrieve the most similar contour parts in a database of known contour segments. A shape-based classification of the retrieved contour parts performs then a simultaneous detection and recognition.
An important step in our approach is the construction of the database of known contour segments. First complete contours of known objects are decomposed into parts using discrete curve evolution. Then, their representation is constructed that is invariant to scaling, rotation, and translation.

68T10 Pattern recognition, speech recognition
68U10 Computing methodologies for image processing
Full Text: DOI
[1] Pizlo, Z.; Li, Y.; Francis, G., A new look at binocular stereopsis, Vision res., 45, 17, 2244-2255, (2005)
[2] Latecki, L.J.; Lakaemper, R.; Eckhardt, U., Shape descriptors for non-rigid shapes with a single closed contour, ()
[3] Hoffman, D.D.; Richards, W.A., Parts of recognition, Cognition, 18, 65-96, (1984)
[4] Hoffman, D.D.; Singh, M., Salience of visual parts, Cognition, 63, 29-78, (1997)
[5] L.J. Latecki, A. Gross, R. Melter (Eds.), Shape representation and dissimilarity for image databases, Pattern Recognition 35 (1) (2002) (special issue). · Zbl 0988.00035
[6] Belongie, S.; Malik, J.; Puzicha, J., Shape matching and object recognition using shape contexts, IEEE trans. PAMI, 24, 509-522, (2002)
[7] Grigorescu, C.; Petkov, N., Distance sets for shape filters and shape recognition, IEEE trans. image process., 12, 9, 1274-1286, (2003) · Zbl 1279.94017
[8] Ankerst, M.; Kastenm├╝ller, G.; Kriegel, H.-P.; Seidl, T., 3D shape histograms for similarity search and classification in spatial databases, Adv. spat. databases int. symp., 207-228, (1999)
[9] Saber, E.; Xu, Y.; Tekalp, A.M., Partial shape representation by sub-matrix matching for partial matching guided image labeling, Pattern recognition, 38, 1560-1573, (2005)
[10] Veltkamp, R.; Tanase, M., Part-based shape retrieval, ACM multimedia, 12, 543-546, (2005)
[11] Pentland, A., Recognition by parts, (), 612-620
[12] Wertheimer, M., Untersuchungen zur lehre von der gestalt II, Psycologische forschung, 4, 301-350, (1923)
[13] Kellman, P.J.; Shipley, T.F., A theory of visual interpolation in object perception, Cognitive psychol., 23, 141-221, (1991)
[14] Tu, Z., Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering, ()
[15] Elder, J.H.; Krupnik, A.; Johnston, L.A., Contour grouping with prior models, IEEE trans. PAMI, 25, 6, 661-674, (2003)
[16] Stahl, J.S.; Wang, S., Convex grouping combining boundary and region information, (), 946-953
[17] Stahl, J.S.; Wang, S., Globally optimal grouping for symmetric boundaries, ()
[18] Tversky, T.; Geisler, W.S.; Perry, J.S., Contour grouping: closure effects are explained by good continuation and proximity, Vision research, 44, 2769-2777, (2004)
[19] Latecki, L.J.; Lakaemper, R., Convexity rule for shape decomposition based on discrete contour evolution, Comput. vision image understanding, 73, 441-454, (1999)
[20] Bruckstein, A.M.; Sapiro, G.; Shaked, D., Evolutions of planar polygons, Int. J. pattern recognition artif. intell., 9, 991-1014, (1995)
[21] Latecki, L.J.; Lakaemper, R., Shape similarity measure based on correspondence of visual parts, IEEE trans. pattern anal. Mach. intell., 22, 10, 1185-1190, (2000)
[22] Sun, K.B.; Super, B.J., Classification of contour shapes using class segment sets, ()
[23] Mori, G.; Belongie, S.; Malik, J., Efficient shape matching using shape contexts, IEEE trans. pattern anal. Mach. intell., 27, 11, 1832-1837, (2005)
[24] Latecki, L.J.; Lakaemper, R., Polygonal approximation of laser range data based on perceptual grouping and EM, ()
[25] Duda, R.O.; Hart, P.E., Pattern classification and scene analysis, (1973), Wiley New York · Zbl 0277.68056
[26] X. Xi, E. Keogh, C. Shelton, L. Wei, C.A. Ratanamahatana, Fast time series classification using numerosity reduction, ICML, 2006.
[27] Biederman, I., Human image understanding: recent research and a theory, Cvgip, 32, 29-73, (1985)
[28] Binford, T., Visual perception by computer, ()
[29] Brooks, R., Symbolic reasoning among 3D models and 2D images, Artif. intell., 17, 285-348, (1981)
[30] Latecki, L.J.; Megalooikonomou, V.; Wang, Q.; Lakaemper, R.; Ratanamahatana, C.A.; Keogh, E., Partial elastic matching of time series, (), 701-704
[31] Latecki, L.J.; Lakaemper, R.; Wolter, D., Optimal partial shape similarity, Image vision comput. (IVC), 23, 227-236, (2005)
[32] Latecki, L.J.; Sobel, M.; Lakaemper, R., New EM derived from kullback – leibler divergence, ()
[33] McNeill, G.; Vijayakumar, S., 2D shape classification and retrieval, ()
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.