<span>With the rapid development of technology in all life fields, and due to the huge daily needs for banking systems process, documents processing and other similar systems. The authentication became more required key for these systems. One of the successful system to verify the any person is the signature verification system. However, a reliable and accurate system is still needed. For this reason, the security challenge is take place via authentic signatures. However, a reliable and accurate system is still needed. For this reason, the security challenge is take place via authentic signatures. Therefore, this paper present a reliable signature verification system using proposed histogram of sparse codes (HSC) feature extraction approach and artificial neural networks (ANN) architecture for classification. The system achieved fast computing 0.09 ms and accurate verification results that is 99.7% using three different signature images datasets CEDAR, UTSig, and ICDAR.</span>

<span>Handwriting recognition is a growing field of study in computer vision, artificial intelligence and pattern recognition technology aimed to recognizing texts and handwritings of hefty amount of produced official documents and paper works by institutes or governments. Using computer to distinguish and make these documents accessible and approachable is the goal of these efforts. Moreover, recognition of text has accomplished practically a major progress in many domains such as security sector and e-government structure and more. A system for recognition text’s handwriting was presented here relied on edge histogram descriptor (EHD), histogram of orientated gradients (HOG) features extraction and support vector machine (SVM) as a classifier is proposed in this paper. HOG and EHD give an optimal features of the Arabic hand-written text by extracting the directional properties of the text. Besides that, SVM is a most common machine learning classifier that obtaining an essential classification results within various kernel functions. The experimental evaluation is carried out for Arabic handwritten images from IESK-ArDB database using HOG, EHD features and proposed work provides 85% recognition rate.</span>

No abstract

No abstract