Earticle

This paper presents for isolated handwritten Arabic characters recognition a comparison between the performances in terms of precision and speediness of six hybrid methods of features extraction based on a combination between profile technique and some efficient moments. More precisely these methods are profile with Racah moment, profile with Gegenbauer moment, profile with Hahn moment, profile with Tchybechev moment and profile with orthogonal Fourier-Mellin moment, finally profile combined in the same time with all these moments. For this purpose we have used for pre-processing the character images the median filter, the thresholding, the centering and the edge detection techniques, while in order to recognize each unknown character we have employed the support vectors machine. The simulation result demonstrates that the most precise method is the profile combined with all moments but in the same time it is the less fast.

In this paper we present a comparison between two methods of learning-classification, the first is the K-Nearest Neighbors (KNN) and the second is the Support Vectors Machines (SVM), these both methods are supervised and used for the recognition of handwritten Latin numerals that are extracted from the MNIST standard database. The recognition process organized as follows: in the pre-processing of numeral images, we exploited the thresholding, the centering and the normalization techniques, in the features extraction we have used the morphology mathematical, the zoning and the zig-zag methods. The classification methods include the K-Nearest Neighbors and the Support Vectors Machines. Our experiments results proved the highest test accuracies 93.13% and 86.50% respectively with SVM and KNN classifiers. The simulation results that we obtained demonstrate the SVM is more performing than the KNN in this recognition.

In this work we will create a system of recognition of Moroccan plate-style vehicle license plates using the invariant moments in features extraction and the support vectors machines such as Moroccan plate is slightly treated by researchers in pattern recognition field. In this context we propose a data set for Moroccan plates composed of 100 images capted with Samsung I9000 mobile camera with maximum resolution 2560 x 1920 dpi. For this purpose we have used in our system is composed by three main phases: the preprocessing of plates followed by the extraction of primitives with invariant moments method in order to convert each image into a vector number which is nothing other than an information extracted from this plate just to differentiate the others. Finally, our recognition system will end with a classification phase by the support vectors machines (SVM). Finally, the recognition system has been proved to be accurate and efficient by the experiment results.