Abstract
The problem of logo recognition is of great interest in the document domain, especially for document databases. By recognizing the logo we obtain semantic information about the document which may be useful in deciding whether or not to analyze the textual components. Given a logo block candidate from a document image and alogo database, we would like to determine whether the region corresponds to a logo in the database. Similarly, if we are given a logo block candidate and adocumentdatabase, we wish to determine whether there are any documents in the database of similar origin. Both problems require indexing into a possibly large model space.
In this contribution, we present a novel application of algebraic and differential invariants to the problem of logo recognition. By using invariants we have shape descriptors for matching that are unique and independent of the point of view. The algebraic invariants handle cases in which the whole shape of the logo is given and it is easy to describe. The differential invariants cover complex arbitrary logo shape and handle situations in which only part of the logo is recovered.
We outline a hierarchical approach to logo recognition and define methods for page segmentation, feature extraction, and indexing. We demonstrate our approach and present results on a database of approximately 100 logos.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ballard D, Brown CM (1982) Computer vision. Prentice Hall, Englewood Cliffs
Barrett E, Payton P, Haag N, Brill M (1991) General methods for determining projective invariants in imagery. CVGIP:IU 53:45–65
Brossman C, Cross, G (1990) Model-based recognition of characters in trademark artwork. Pattern Recognition Letters 11:363–370
Bruckstein AM, Katzir A, Lindenbaum M, Porat M (1990) Similarity invariant recognition of partially occluded planar curves and shapes. Technion CIS report
Bruckstein A, Holt J, Netravali AN, Richardson TJ (1993) Invariant signatures for planar shape recognition under partial occlusion. CVGIP:IU 58:49–65
Bruckstein AM, Rivlin E, Weiss I (1995) Scale space local invariants. Technion CIS report
Bruckstein AM, Netravali AN (1990) On differential invariants of planar curves and the recognition of partially occluded planar shapes. AT&T technical memo
Cartan E (1955) La théorie des groupes continus et la géometrie. Oeuvres complètes, III/2, 1727–1861, Gauthier-Villars, Paris
Doermann D, Rosenfeld A (1993) The interpretation and recognition of interfering strokes. In: Proceedings of the international workshop on frontiers in handwriting recognition, pp 41–50
Duda RO, Hart PE (1973) Pattern classification and scene analysis. Wiley, New York
Etemad K, Doermann D, Chellappa R (1995) Multiscale document page segmentation using soft decision integration. IEEE Transactions on Pattern Analysis and Machine Intelligence (submitted)
Fan T, Tsai W (1984) Automatic Chinese seal identification. Computer Vision, Graphics and Image Processing 25:311–330
Fletcher L, Kasturi R (1988) A robust algorithm for text string separation from mixed text/graphics images. IEEE Transactions on Pattern Analysis and Machine Intelligence 10:910–918
Forsyth D, Mundy JL, Zisserman A, Brown CM (1990) Projectively invariant representations using implicit algebraic curves. Image and Vision Computing 8:130–136
Grace JH, Young A (1903) The algebra of invariants. Chelsea, New York
Grimson W, Lozano-Pérez T (1987) Localizing overlapping parts by searching the interpretation tree. IEEE Transactions on Pattern Analysis and Machine Intelligence 9:469–482
Guggenheimer H (1963) Differential geometry. Dover, New York
Halphen M (1880) Sur les invariants différentiels des courbes gauches. J. Ecole Polytechnique 28:1
Knuth D (1973) The art of computer programming: sorting and searching, vol 3. Addison-Wesley, Reading
Lane EP (1942) A treatise on projective differential geometry. University of Chicago Press
Lee S, Kim J (1989) Attributed stroke graph matching for seal imprint verification. Pattern Recognition Letters 9:137–145
Pavlidis T (1982) Algorithms for graphics and image processing. Computer Science Press, Rockville
Rivlin E, Weiss I (1995) Local invariants for recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 17:226–238
Rosenfeld A, Kak AC (1982) Digital picture processing, 2nd edn. Academic, New York
Springer CE (1964) Geometry and analysis of projective spaces. Freeman, San Francisco
Taubin G, Cooper DB (1992) Object recognition based on moment (or algebraic) invariants. In: Mundy JL, Zisserman A (eds) Geometric invariance in machine vision. MIT Press, Cambridge, pp 375–397
Ueda K, Nakamura Y (1984) Automatic verification of seal-impression pattern. In: Proceedings of the international conference on pattern recognition, pp 1019–1021
Van Gool L, Kempenaers P, Oosterlinck A (1991) Recognition and semi-differential invariants. Proc CVPR 454–460
Weiss I (1996) Geometric invariants and object recognition. Int J Computer Vision (accepted)
Weiss I (1992) Local projective and affine invariants, TR 612. Center for Automation Research, University of Maryland
Weiss I (1988) Projective invariants of shapes. In: Proceedings of the DARPA image understanding workshop. Cambridge, pp 1125–1134
Wilczynski EJ (1906) Projective differential geometry of curves and ruled surfaces. Teubner, Leipzig
Wolfson HJ (1990) On curve matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, pp 483–489
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Doermann, D., Rivlin, E. & Weiss, I. Applying algebraic and differential invariants for logo recognition. Machine Vis. Apps. 9, 73–86 (1996). https://doi.org/10.1007/BF01214362
Issue Date:
DOI: https://doi.org/10.1007/BF01214362