Method of estimation of text labels recognition systems efficiency parameters with use of likelihood characteristics tree
E.M. Voskresensky, V.A. Tsarev

Institute of Management and Information Technologies (branch) of the St.-Petersburg State Polytechnical University

Full text of article: Russian language.

Abstract:
In article the method of estimation of text label recognition systems efficiency is offered. Processing of input images is presented as sequence of events of a kind «algorithm has returned the correct (wrong) answer». On this basis the diagram of all possible sequences of these events is generated. It is tree of likelihood characteristics. With use of the tree functional dependence of recognition system characteristics from characteristics of separate algorithms is determinated.

Key words:
optical character recognition, an estimation of efficiency of recognition.

Citation: Voskresensky EM, Tsarev VA. Method of estimation of text labels recognition systems efficiency parameters with use of likelihood characteristics tree. Computer Optics 2008; 32(3): 283-89.

References:

  1. Balykov EA, Tsarev VA. Software development and quality control of image processing and analysis [In Russian]. Moscow: Company Sputnik+ 2006; 178 p.
  2. Tsarev VA. Basic principles of vehicles optoelectronic identification system development. Pattern Recognition and Image Analysis 2005; 15(2): 454-457.
  3. Voskresensky EM, Tsarev VA. Text label recognition systems efficiency management using localization and segmentation algorithms output likelihood. 8th International Conference «Pattern Recognition and Image Analysis: New Information Technologies» (PRIA-8-2007): Conference Proceedings 2007; 8(3): 57-61.
  4. Tsarev VA, Balykov EA, Mikhailov AE. Optoelectronic systems of identification of transport facilities moving: functionality, composition, peculiar qualities of designing and software implementation  [In Russian]. The Journal “Nauchno-tekhnicheskie vedomosti SPbGPU” (St. Petersburg State Polytechnical University Journal) 2005; 3: 40-48.

© 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