Volume 2 Issue 1
Authors: Oleg Sytnik
Abstract: The problem of adaptive correction of the trajectory distortions on the images of the earth's surface, which are formed by synthetic-aperture radar (SAR), is discussed. The proposed method belongs to the class of adaptive self-focusing methods, in which the information on trajectory errors is retrieved from a reflected sounding signal. We have used the estimates of the Doppler spectrum displacement and its high derivatives averaged over the slant range as information parameters. It provided an opportunity to build an adaptive algorithm, which can automatically correct not only flight velocity errors, but acceleration and jump errors as well. The results of SAR signal processing are presented. The features of signal processing under different conditions and implementation of the proposed method are discussed.
Keywords: Coherent Radar; Doppler Spectrum; Distortions; Trajectory Errors; Radar’s Image of Surface; Synthetic Aperture Radar (SAR)
Authors: Abdelhay A. Sallam; Mohammed R. Elbasyouni; Cheng Y. Suen; Ahmed T. Sahlol
Abstract: Recognition of handwritten Arabic text awaits accurate recognition solutions. There are many difficulties facing a good handwritten Arabic recognition system such as unlimited variation in human handwriting, similarities of distinct character shapes, character overlaps, and interconnections of neighbouring characters and their position in the word. Arabic characters are drawn in four forms: Isolated, Initial, Medial, and Final. The typical Optical Character Recognition (OCR) systems are based mainly on three stages, pre-processing, features extraction and recognition. Each stage has its own problems and effects on the system efficiency which may be time consuming, resource using and may contribute to the possibility of recognition errors. There are many feature extraction methods for handwritten letters. In this paper, an efficient approach for the recognition of off-line Arabic handwritten characters is presented. The approach is based on novel preprocessing operations (including different kinds of noise removal and dilation), structural, statistical and topological features from the main body of the character and also from the secondary components. Evaluation of the importance and accuracy of the selected features is made. An off-line recognition system based on the selected features was built. The system was trained and tested with CENPRMI dataset. We used the popular Feed Forward Neural Network for classification to enhance recognition accuracy. The proposed algorithm obtained has promising results in terms of accuracy (success rate of 100% for some letters with an average rate of 88%). Compared to other related works, we find that our success outcomes are higher.
Keywords: Handwritten Arabic Characters; Noise Removal; Secondary Components