The present paper focuses on the analysis of the possibilities of using integral transforms for measuring and evaluating the differences of compared images (car silhouettes) with the purpose of a correct car body categorization. Approaches such as the light intensities frequency change, the application of discrete integral transforms without the use of further supplementary information enabling automated data processing using the Fourier-Mellin transforms are used within this work. The calculation of the several metrics was verified through different combinations that implied using and not using the Hamming window and a low-pass filter. The paper introduced a method for measuring and evaluating the differences in the compared images (car silhouettes). The proposed method relies on the fact that the integral transforms have their own transformants in the case of translation, scaling and rotation, in the frequency area. Besides, the Fourier-Mellin transform was to offer image transformation that is resistant to the translation, rotation and scale.
Data matrix codes are two-dimensional (2D) matrix bar codes, which are the descendants of the well known 1D bar codes. However, compared to 1D bar codes, they allow to store much more information in the same area. Comparing data matrix codes with QR codes, for example, we find them much more effective in marking small objects or in the case that you have only a very small area for placing a code in. Their capacity and ability of decoding also a code that is partly damaged make them an appropriate solution for industrial applications. In the following paper we compare the impact of various cameras on the detection and decoding of data matrix codes in real scene images. The location of the code is based on the fact that typical bordering of a data matrix code forms a region of connected points which create “L”, the so-called finder pattern, and the parallel dotting, the so-called timing pattern. In the first step, we try to locate the finder pattern using adaptive thresholding and connecting neighbouring points to continuous regions. Then we search for the regions where 3 outer boundary points form a isosceles right triangle that could represent the finder pattern. In the second step, we have to verify the timing pattern. We look for an even number of crossings between the background and foreground. Experimental results show that the algorithm we have proposed provides better results than competitive solutions.