Abstract
The paper proposes a new approach to find semantic meanings in visual object class structure, in line with the Gestalt laws of proximity. Micro level semantic structures are formed by line segments (arcs also approximated into line segments based on pixel deviation threshold) which are in close proximity. These structures are hierarchically combined till a semantic label can be assigned. The algorithm extracts semantic groups, their inter-relations and represents these using a graph. Invariant geometrical properties of the groups and relations are used as vertex and edge labels. A graph model captures the inter class variability by analyzing the repetitiveness of structures and relations and uses it as a weighting factor for classification. The algorithm has been tested on a standard benchmark database and compared with existing approaches.
Similar content being viewed by others
References
Ballard DH, Brown CM (1982) Computer vision. Prentice-Hall, Englewood Cliffs
Berg C (2005) Shape matching and object recognition. PhD thesis. Computer Science Division, University of California, Berkeley
Berg C, Berg TL, Malik J (2005) Shape matching and object recognition using low distortion correspondence. Proc. Int. Conference on Computer Vision and Pattern Recognition (CVPR)
Dattorro J (2004) Convex optimization & euclidean distance geometry. Meboo Publishing USA http://meboo.convexoptimization.com/
Eakins JP (2002) Towards intelligent image retrieval. Pattern Recognit 35(1):3–14
Fei-Fei L, Fergus R, Perona P (2004) Learning generative visual models from few training examples: an incremental Bayesian approach tested on 101 object categories. IEEE. CVPR, Workshop on Generative-Model Based Vision
Grauman K, Darrell T (2006) Pyramid match kernels: discriminative classification with sets of image features. Technical Report MIT-CSAIL-TR-2006-020
Holub AD, Welling M, Perona P (2005) Exploiting unlabelled data for hybrid object classification. Proc. NIPS Workshop on Inter-Class Transfer
Kovesi PD (2002) Edges are not just steps. Proc. Fifth Asian Conference on Computer Vision (ACCV), Pub. Australian Pattern Recognition Society, pp 822–827
Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Proc. Int. Conference on Computer Vision and Pattern Recognition (CVPR)
Lew MS, Sebe N, Djeraba C, Jain R (2006) Content-Based Multimedia Information Retrieval: State of the Art and Challenges. ACM Transactions on Multimedia Computing, Communications and Applications (TOMCCAP) 2(1):1–19
Lowe DG (1985) Perceptual organization and visual recognition. Springer Int. Series in Engineering and Computer Science, Vol. 5
Mojsilovic A, Rogowitz B (2001) Capturing image semantics with low-level descriptors. Proc IEEE Int Conf Image Processing (ICIP) 1:18–21
Mutch J, Lowe DG (2008) Object class recognition and localization using sparse features with limited receptive fields. Int J Comput Vision 80(1):45–57
Ponce J, Hebert M, Schmid C, Zisserman A (Eds.) (2006) Toward Category-Level Object Recognition. LNCS Volume 4170 Springer-Verlag
Pope R, Lowe DG (1994) Vista: a software environment for computer vision research. Proc. Int. Conference on Computer Vision and Pattern Recognition (CVPR) pp 768–772
Rosch E, Mervis CB, Gray WD, Johnson DM, Boyes-Braem P (1976) Basic objects in natural categories. Cogn Psychol 8(3):291–440
Sarkar S, Boyer KL (1993) Perceptual organization in computer vision: a review and a proposal for a classificatory structure. IEEE Trans Syst Man Cybern 23(2):382–399
Serre T, Wolf L, Poggio T (2005) Object recognition with features inspired by visual cortex. Proc IEEE Int Conf Comput Vis Pattern Recognit (CVPR) 2:994–1000
Wang G, Zhang Y, Fei-Fei L (2006) Using dependent regions for object categorization in a generative framework. Proc. Int. Conference on Computer Vision and Pattern Recognition (CVPR)
Wertheimer M, King D (2004) Max Wertheimer and Gestalt Theory. Transaction, New Brunswick
Witkin AP, Tenenbaum JM (1983) What is perceptual organization for? Bundy A (ed.) Proc. 8th Int. Joint Conference on Artificial Intelligence (IJCAI) Volume 2, p 1023–1026
Acknowledgement
This study was supported by research fund from Chosun University, 2011.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ahmad, N., An, Y. & Park, J. An intrinsic semantic framework for recognizing image objects. Multimed Tools Appl 57, 423–438 (2012). https://doi.org/10.1007/s11042-011-0739-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-011-0739-8