Abstract
Computer vision has been extensively adopted in many domains during the last three decades. One of the main goals of computer vision applications is to recognize objects. Generally, computers can successfully achieve object recognition by relying on a large quantity of data. In real world, some objects may own diverse configurations or/and be observed at various angles and positions, and the process of object recognition is denoted as recognizing objects in dynamic state. It is difficult to collect enough data to achieve the sorts of objects recognition. In order to resolve the problem, we propose a technique to achieve object recognition which is not only in static state where the objects do not own multiple configurations, but also in dynamic state. First, we apply an effective robust algorithm to obtain landmarks from objects in two dimensional images. With the algorithm, the number of landmarks from different objects can be appointed in advance. A set of landmarks as a point is projected into a pre-shape space and a shape space. Next, a method is proposed to create a surface among three basic data models in a pre-shape space. If basic data are too few to create a surface or a curve, a new basic data can be built from the basic data. Then, a series of new data models can be obtained from these basic data in a pre-shape space. Finally, object recognition can be achieved by using the new data models in shape space. We give some examples to show the algorithms are efficient not only for the objects with noises, but also for the ones with various configurations.
Similar content being viewed by others
References
Sarkodie-Gyan T, Lam CW, Hong D, Campbell AW (1997) An efficient object recognition scheme for a prototype component inspection. Mechatronics 7(2):185–197
Yuille A (1991) Deformable templates for face recognition. J Cogn Neurosci 3(1):59–71
Belongie S, Melik J, Puzicha J (2002) Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell 24(24):509–522
He L, Han CY, Everding B, Wee WG (2004) Graph matching for object recognition and recovery. Pattern Recogn 37(7):1557–1560
Li W, Lee T (2004) Projective invariant object recognition by a Hopfield network. Neurocomputing 62:1–18
Sun TH, Liu CS, Tien FC (2008) Invariant 2D object recognition using eigenvalues of covariance matrices, re-sampling and autocorrelation. Expert Syst Appl 35:1966–1977
Li J, Allinson NM (2009) Subspace learning-based dimensionality reduction in building recognition. Neurocomputing 73:324–330
Ommer B, Buhmann JM (2010) Learning the compositional nature of visual object categories for recognition. IEEE Trans Pattern Anal Mach Intell 32(3):501–516
Berg AC, Berg TL, Malik J (2005) Shape matching and object recognition using low distortion correspondences. In: IEEE Computer Society conference on computer vision and pattern recognition (CVPR’05), vol 1, Jun 20–25, pp 26–33
Han Y, Wang B, Idesawa M, Shimai H (2010) Recognition of multiple configurations of objects with limited data. Pattern Recognit 43:1467–1475
Kendall DG (1984) Shape manifolds, Procrustean metrics, and complex projective spaces. Bull Lond Math Soc 16:81–121
Kendall DG, Barden D, Carne TK, Le H (1999) Shape and shape theory. Wiley, New York
Kendall DG (1977) The diffusion of shape. Adv Appl Probab 9(3):428–430
Zhang J, Zhang X, Krim H (1998) Invariant object recognition by shape space analysis. Procceding of international conference on image processing, ICIP 98. Publication date: 4–7 October 1998, Meeting Date: 4–7 October, vol 3, pp 581-585
Zhang J, Zhang X, Krim H, Walter GG (2003) Object representation and recognition in shape spaces. Pattern Recogn 36:1143–1154
Glover J, Rus D, Roy N, Gordon G (2006) Robust models of object geometry. In: Proceedings of the IROS workshop on from sensors to human spatial concepts, Beijing, China
Han Y, Idesawa M, Shimai H (2008) The shortest path in shape space for shape matching. In: The 11th international conference on humans and computers (HC’2008), Japan
Rohlf F (1999) Shape statistics: procrustes superimpositions and tangent spaces. J Classif 16(2):197–223
Kent J, Mardia K (2001) Shape, Procrustes tangent projections and bilateral symmetry. Biometrika 88(2):469–485
Klassen E, Srivastava A, Mio W, Joshi S (2004) Analysis of planar shapes using geodesic paths on shape spaces. Trans Pattern Anal Mach Intell 26(3):223–232
Roy-Chowdhury AK (2005) A measure of deformability of shapes, with applications to human motion analysis. IEEE Comput Soc Conf Comput Vis Pattern Recogn 05(1):398–404
Evans K (2005) Curve-fitting in shape space. In: Quantitative biology, shape analysis, and wavelets. Leeds University Press, Leeds
Evans K, Dryden IL, Le H (2010) Shape curves and geodesic modelling. http://www.maths.nott.ac.uk/personal/ild/papers/curves2.pdf
Kume A, Dryden I, Le H (2007) Shape-space smoothing splines for planar landmark data. Biometrika 94(3):513–528
Kilian M, Mitra N, Pottmann H (2007) Geometric modeling in shape space. ACM Siggraph 26(3)
Small CG (1996) The statistical theory of shape. Springer series in statistics. Springer, New York
Bookstein L (1997) Morphometric tools for landmark data: geometry and biology. Cambridge University Press, Cambridge
Bookstein L (1996) Landmark methods for forms without landmarks: Morphometrics of group differences in outline shape. Med Imag Anal 1(3):225–243
Förstner W, Gülch E A fast operator for detection and precise location of distinict points, corners and centers of circular features. In: Proceedings of intercommission conference on photogrammetric data. Interlaken, Switzerland, pp 281–305
Fatemizadeh E, Lucas C, Soltanian-Zadeh H (2003) Automatic landmark extraction from image data using modified growing neural gas network. IEEE Trans Inf Technol Biomed 7:77–85
Hoffman DD, Richards WA (1984) Parts of recognition. Cognition 18:65–96
Saengdeejing A, Qu ZH, Chaeroenlap N, Jin YF (2003) 2-D Shape recognition using recursive landmark determination and fuzzy ART network learning. Neural Process Lett 18:81–95
Sobel I, Feldman G (1968) A 3x3 isotropic gradient operator for image processing. Presented at a talk at the Stanford Artificial Project in 1968, unpublished but often cited, orig. in Pattern Classification and Scene Analysis, Duda,R. and Hart,P., John Wiley and Sons,’73, pp. 271–272
Canny J (1986) A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell 8(6):679–698
Marr D, Hildreth E (1980) Theory of edge detection. Proc R Soc Lond B Biol Sci 207(1167):187–217
Imai H, Iri M (1988) Polygonal approximation of a curve—formulations and algorithms. In: Computational Morphology Conference, pp 71–86
Chan WS, Chin F (1992) Approximation of polygonal curves with minimum number of line segments. Lect Notes Comput Sci 650:378–387
Chan WS, Chin F (1996) Approximation of polygonal curves with minimum number of line segments or minimum error. Int J Comput Geom Appl 6:59–77
Kolesnikov A, Franti P (2007) Polygonal approximation of closed discrete curves. Pattern Recogn 40:1282–1293
Mokhtarian F, Mackworth A (1986) Scale-based description and recognition of planar curves and two-dimensional shapes. IEEE Trans Pattern Anal Mach Intell 8(1):34–43
Li W, Bebis G, Bourbakis NG (2008) 3-D object recognition using 2-D views. IEEE Trans Image Process 17(11):2236–2255
Wang P (2001) 3D articulated object understanding, learning, and recognition from 2D images. Multispectr Image Proces Pattern Recogn 44:5–15
Huang C, Her I (2006) Homomorphic graph matching of articulated objects by an integrated recognition scheme. Expert Syst Appl 31:116–129
Beinglass A, Wolfson HJ (1991) Articulated object recognition, or, how to generalize the generalized hough transform. Pattern Recogn Lett (table of contents archive) 12(9)
Ruberto CD, Cinque L (2009) Decomposition of two-dimensional shapes for efficient retrieval. Image Vis Comput 27:1097–1107
Lowe D (1999) Object recognition from local scale-invariant features. Computer Vision, 1999. The proceedings of the seventh IEEE international conference, pp 1150–1157
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Han, Y., Koike, H. & Idesawa, M. Recognizing objects with multiple configurations. Pattern Anal Applic 17, 195–209 (2014). https://doi.org/10.1007/s10044-012-0277-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-012-0277-7