Method of rapid correlation using ternary templates for object recognition in images
N.I. Glumov, E.V. Myasnikov, V.N. Kopenkov, M.A. Chicheva

Image Processing Systems Institute of RAS,
Samara State Aerospace University

Full text of article: Russian language.

Abstract:
The task of recognition and position detection of fragments corresponding to one of templates of a set is considered in this work. The proposed method of fast correlation using a set of ternary templates solve the problems indicated above successfully. The method is applied to solve the two following tasks: the first task is detection of eye position on the face facsimile on the documents and the second one is recognition of machine readable text on the scanned documents.

Key words:
correlation, object recognition, document image, eye search, machine-readable data.

Citation: Glumov NI, Myasnikov EV, Kopenkov VN, Chicheva MA. Method of rapid correlation using ternary templates for object recognition in images. Computer Optics 2008; 32(3): 277-82.

References:

  1. Document ICAO 9303 “Machine Readable Travel Documents (MRTD)" //http://www.icao.int/mrtd/publicatio ns/doc.cfm
  2. Soifer VA, ed. Methods of computer image processing [In Russian]. Moscow: “Fizmatlit” Publisher 2001; 784 p.
  3. Chicheva MA, Glumov NI, Sergeev VV. Optimization of linear filtering procedure in image processing applications. Proceedings of the 6-th German-Russian workshop "Pattern recognition and image understanding" OGRW-6-2003; 2003: 149-154.
  4. Kawato S, Ohya J. Two-step approach for real-time eye tracking with a new filtering technique. Systems, Man and Cybernetics 2000; 2: 1366-1371.
  5. Lladoós J, Martí E, Villanueva J. Symbol recognition by error-tolerant subgraph matching between region adjacency graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence 2001; 23(10): 1137-1143.
  6. Ryu YS, Oh SY. Automatic extraction of eye and mouth fields from a face image using eigenfeatures and multilayer perceptrons. Pattern recognition 2001; 34(12): 2459-2466.
  7. Su Ya. Symbol recognition via statistical integration of pixellevel constraint histograms: a new descriptor. IEEE Transactions on Pattern Analysis and Machine Intelligence archive 2005; 27(2): 278 - 281.

© 2009, ИСОИ РАН
Россия, 443001, Самара, ул. Молодогвардейская, 151; электронная почта: ko@smr.ru ; тел: +7 (846) 332-56-22, факс: +7 (846 2) 332-56-20