In this paper we provide a method to localize the modules of the industrial Data Matrix Code (DMC) marked on curved surfaces. An imaginary grid of points is constructed which has the same orientation as the surface. The imaginary grid is projected on to the image and according to this grid the modules of the code are scanned. If the surface considered is not a perfect sphere then the results are not accurate. To overcome this using an error correction based on the assumed centers and the computed centers a better approximation is obtained. Using this method we can localize the modules irrespective of the camera view or orientation of the DMC.

In this paper we present a method for scanning the Data Matrix Code (DMC) used in industrial environment dotted on cylindrical components. Since the code is used in cruel environment conditions, a standard code reader can not scan the code and extract reliably the information. Assuming that the radius of the curvature and the length of the code are estimated known, using an transformation matrix, an imaginary grid of points is constructed and projected on to the image. Using this method we can localize the modules irrespective of the camera view or orientation of the Data Matrix Code. If the surface considered is not a perfect cylinder, the projections in the image will serve as estimates for the true module positions. For that the modules position are relocated using an error correction based on the estimated centers and the computed centroids of the modules.

In many cases, because of the lenses system of the video camera and because of the difficult areas to take a perfect straight picture with the Data Matrix Code, we face with the bad situation not to recognize the code and to extract the desired encoded information. For the Industrial Data Matrix Codes marked on planar surfaces with no perspective errors, the scanning process is performed based on the orientation angle of the pattern and the distance between modules. This method is simple and efficient for planar surfaces but for the cases when the Data Matrix Code image has hard perspective errors is useless. To achieve this, we describe an efficient method for scanning the Industrial Data Matrix Codes for the special situations like the perspective errors. An imaginary grid of points is constructed which has the same orientation as the surface. The imaginary grid is projected on to the image and following it, the Data Matrix Code Image is scanned extracting the binary information.

Data Matrix Codes (DMC) are established by these days in many areas of industrial manufacturing thanks to their concentration of information on small spaces. In today's usually order-related industry, where increased tracing requirements prevail, they offer further advantages over other identification systems. This underlines in an impressive way the necessity of a robust code reading system for detecting DMC on the components in factories. This paper provides a solution for the Data Matrix Codes recognition. Using the Mean Shift Algorithm, the main information of the DMC pattern are computed and based on these, a virtual identification pattern is constructed. Seeking and matching over the image, the Data Matrix Code is located. We concentrate on Data Matrix Codes in industrial environment, punched, milled, lasered or etched on different materials in arbitrary orientation.

!" #$%&'()&* + + , + + + + + + , + + + . / 0 , , + 1 + + + . -2 3 + + 4 5 5 5 6+ . 5 3 + , + + + + . + 3 7 , , .8 + + 5 + + , . 9:;<='>%* ? ? . @ A B @ C / 0 3 , + + / 0 4 . , + + , 3 DEF. + + + + , + 7 5 -+ , . + , , / 3 + 0 + GHG IJJHIJJ. 1 + ,+ 4 1 + + DEF. .E 5 5 5 3 6+ + + + 6 . +4 + 3 + ! . /A 0 , 3 + + . , + 5 4 + .B + . 3 5 3 7 , , . + 3 . . . . + + + + + K + B 5 A 7 + . L +. . 5 . L +. . . L +. . ." + + + + B 5 + + M 7 !.4 L 1 . NOPQRS PTUVWXWYWZ[S \] _̂ Z̀TPaWbPYWZ[S cdefghijklmlinkf okpqjfcjljrlinkf \] _̂ sZtVaRXSuTP[[W[QS .E. 6+ + 3 1 . -1 3 + + + ,+ + . . v v w @ , +1 A xyz{| 3 . 3 ! + 2 + + , -1 3 . 5 5 D}FD~F. , + + 5 5 . 3 1 + + DF . 6 + 6 + , 3 3 + ! . ,€ + .-+ + 3 , + + , 4 . B ,€ + ! . + , ,€ + . 3 4 + . + ,€ + ,1 + 6 + + .B 5 + / .}0 5 ,-7 World Academy of Science, Engineering and Technology International Journal of Industrial and Manufacturing Engineering Vol:6, No:4, 2012