Title :
Scanning industrial Data Matrix Codes
Author :
A Ion-Cosmin Diţă;B Marius Oteşteanu;C Franz Quint
Author_Institution :
Faculty of Electronics and Telecommunications, Politehnica University of Timisoara, Romania
Abstract :
In this paper we present a solution to locate the Data Matrix Codes dotted on different materials in different orientations. Starting from the parameters of the industrial camera of the recognition system and knowing the real world size of the Data Matrix pattern, the proposed method can find the exact position and the orientation of the Data Matrix pattern in an image. In order to be independent of illumination variations or nonuniform background, we use an adaptive threshold method for the image thresholding. It is very difficult to recognize the pattern because the Data Matrix pattern is composed only of dots and to overcome this, we are using morphological operators to transform the pattern in a solid square. The distance between modules as well as the size and the orientation of the Data Matrix pattern are estimated out of the image. We tested the proposed algorithm with very good results for Data Matrix Codes dotted on different materials and different angles.
Keywords :
"Cameras","Pattern recognition","Shape","Materials","Vectors","Search problems","Charge coupled devices"
Conference_Titel :
Telecommunications Forum (TELFOR), 2011 19th
Print_ISBN :
978-1-4577-1499-3
DOI :
10.1109/TELFOR.2011.6143768