This paper presents an efficient handwritten digit recognition system based on support vector machines (SVM). A novel feature set based on transition information in the vertical and horizontal directions of a digit image combined with the famous Freeman chain code is proposed. The main advantage of this feature extraction algorithm is that it does not require any normalization of digits. These features are very simple to implement compared to other methods. We evaluated our scheme on 80,000 handwritten samples of Persian numerals and we have achieved very promising results. Ó 2015 Production and hosting by Elsevier B.V. on behalf of King Saud University. This is an open access article under the CC BY-NC-ND license (http://creativecommons. org/licenses/by-nc-nd/4.0/).

The proposed technique is based on the detection of the lower baselines of the text lines of Arabic documents. As the lower baseline pixels belong to the lower edge of the word images, we first locate vertically the black-white transitions at the black pixels where the resulting image would emphasize the baselines of the text. Once the skew angle is determined using a randomized Hough transform, the baselines are extracted using y-intercept histogram. This algorithm can also contribute significantly for text line extraction from skewed document images for many languages. Ó 2016 King Saud University. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

This paper describes a new approach to combine a multilayer perceptron (MLP) and a hidden Markov model for recognizing handwritten Arabic words. As a first step, connected components (CCs) of black pixels are detected, then the system determines which CCs are subwords and which are diacritics. The diacritics are then isolated and identified separately, and the sub-words are segmented into graphemes. The MLP is used as labeller (classifier) and probability estimator. We also introduce the diacritics and their positions in our hybrid system; thus, only one model including both grapheme and diacritic states is built to represent the whole alphabet. Finally, we consider a maximum likelihood classifier to decide about the word class. The experiments that were performed show promising results on Arabic word segmentation and recognition.

No abstract

In this study, we present efficient detection and precoding algorithms for massive multi-user multiple-input multiple-output wireless system. To reduce the computational complexity due to large matrix inversion, the proposed algorithms are an enhanced version of zero forcing scheme based on QR matrix decomposition for both uplink and downlink systems. Through extensive numerical experiments, we demonstrate that the proposed algorithms outperform the recently published ones in terms of performance and complexity.