A genetic matching algorithm is extended to take into account primitive arcs in a pattern recognition process. Usually approaches based on segments are sensitive to over segmentation effects. Handling with more accurate description allows to improve the recognition by limiting the number of vertices to be matched and so to decrease processing time. Experimental studies using real data attest the robustness of the proposed method.
Jean-Pierre Salmon, Laurent Wendling. ARG based on arc and line segments to improve the symbol recognition by genetic algorithm. Liu Wenyin, Josep Llados, Jean-Marc Ogier Editors. Graphics recognition-Recent advances and New Opportunities - selected papers from GREC'07, Springer, pp.80-90,2008, Lecture Notes in Computer Science 5046, ⟨10.1007/978-3-540-88188-9_9⟩. ⟨hal-00340452⟩
Citations
APA
ARG based on arc and line segments to improve the symbol recognition by genetic algorithm. (2008). https://api.istex.fr/ark:/67375/HCB-TM2WS6V6-Q/fulltext.pdf?sid=hal
MLA
ARG Based on Arc and Line Segments to Improve the Symbol Recognition by Genetic Algorithm. Jan. 2008, https://api.istex.fr/ark:/67375/HCB-TM2WS6V6-Q/fulltext.pdf?sid=hal.
Chicago
“ARG Based on Arc and Line Segments to Improve the Symbol Recognition by Genetic Algorithm.” 2008. https://api.istex.fr/ark:/67375/HCB-TM2WS6V6-Q/fulltext.pdf?sid=hal.
Harvard
“ARG based on arc and line segments to improve the symbol recognition by genetic algorithm” (2008). Available at : https://api.istex.fr/ark:/67375/HCB-TM2WS6V6-Q/fulltext.pdf?sid=hal.
ISO 690
ARG based on arc and line segments to improve the symbol recognition by genetic algorithm, 2008. [en ligne]. Disponible à l'adresse : https://api.istex.fr/ark:/67375/HCB-TM2WS6V6-Q/fulltext.pdf?sid=hal