In this paper, a handwritten digit classification system is proposed based on the Discrete Wavelet Transform and Spike Neural Network. The system consists of three stages. The first stage is for preprocessing the data and the second stage is for feature extraction, which is based on Discrete Wavelet Transform (DWT). The third stage is for classification and is based on a Spiking Neural Network (SNN). To evaluate the system, two standard databases are used: the MADBase database and the MNIST database. The proposed system achieved a high classification accuracy rate with 99.1% for the MADBase database and 99.9% for the MNIST database

A proposed feature extraction algorithm for handwriting Arabic words. The proposed method uses a 4 levels discrete wavelet transform (DWT) on binary image. sliding window on wavelet space and computes the stander derivation for each window. The extracted features were classified with multiple Support Vector Machine (SVM) classifiers. The proposed method simulated with a proposed data set from different writers. The experimental results of the simulation show 94.44% recognition rate.

      In the last decade, 3D models gained interest in many applications, such as games, the medical field, and manufacture. It is necessary to protect these models from unauthorized copying, distribution, and editing. Digital watermarking is the best way to solve this problem. This paper introduces a robust watermarking method by embedding the watermark in the low-frequency domain, then selecting the coarsest level for embedding the watermark based on the strength factor. The invisibility of the watermark for the proposed algorithm is tested by using different measurements, such as HD and PSNR. The robustness was tested by using different types of attacks; the correlation coefficient was applied for the evaluati

      Recently, digital communication has become a critical necessity and so the Internet has become the most used medium and most efficient for digital communication. At the same time, data transmitted through the Internet are becoming more vulnerable. Therefore, the issue of maintaining secrecy of data is very important, especially if the data is personal or confidential. Steganography has provided a reliable method for solving such problems. Steganography is an effective technique in secret communication in digital worlds where data sharing and transfer is increasing through the Internet, emails and other ways. The main challenges of steganography methods are the undetectability and the imperceptibility of con

In this paper, an adaptive medical image watermarking technique is proposed based on wavelet transform and properties of human visual system in order to maintain the authentication of medical images. Watermark embedding process is carried out by transforming the medical image into wavelet domain and then adaptive thresholding is computed to determine the suitable locations to hide the watermark in the image coefficients. The watermark data is embedded in the coefficients that are less sensitive into the human visual system in order to achieve the fidelity of medical image. Experimental results show that the degradation by embedding the watermark is too small to be visualized. Also, the proposed adaptive watermarking technique can preserv

    In this paper a method  to determine whether an image is forged (spliced) or not is presented. The proposed method is based on  a classification model to determine the authenticity of a tested image. Image splicing causes many sharp edges (high frequencies) and discontinuities to appear in the spliced image. Capturing these high frequencies in the wavelet domain rather than in the spatial domain is investigated in this paper. Correlation between high-frequency sub-bands coefficients of Discrete Wavelet Transform (DWT) is also described using co-occurrence matrix. This matrix was an input feature vector to a classifier. The best accuracy of 92.79% and 94.56% on Casia v1.0 and Casia v2.0 datasets respectively was achieved. This pe

In the current research work, a system of hiding a text in a digital grayscale image has been presented. The algorithm system that had been used was adopted two transforms Integer Wavelet transform and Discrete Cosine transformed. Huffman's code has been used to encoding the text before the embedding it in the cover image in the HL sub band. Peak Signal to Noise Ratio (PSNR) was used to measure the effect of embedding text in the watermarked image; also correlation coefficient has been used to measure the ratio of the recovered text after applying an attack on the watermarked image and we get a good result. The implementation of our proposed Algorithm is realized using MATLAB version 2010a.

This work implements an Electroencephalogram (EEG) signal classifier. The implemented method uses Orthogonal Polynomials (OP) to convert the EEG signal samples to moments. A Sparse Filter (SF) reduces the number of converted moments to increase the classification accuracy. A Support Vector Machine (SVM) is used to classify the reduced moments between two classes. The proposed method’s performance is tested and compared with two methods by using two datasets. The datasets are divided into 80% for training and 20% for testing, with 5 -fold used for cross-validation. The results show that this method overcomes the accuracy of other methods. The proposed method’s best accuracy is 95.6% and 99.5%, respectively. Finally, from the results, it

    Multiple applications use offline handwritten signatures for human verification. This fact increases the need for building a computerized system for signature recognition and verification schemes to ensure the highest possible level of security from counterfeit signatures. This research is devoted to developing a system for offline signature verification based on a combination of local ridge features and other features obtained from applying two-level Haar wavelet transform. The proposed system involves many preprocessing steps that include a group of image processing techniques (including: many enhancement techniques, region of interest allocation, converting to a binary image, and Thinning). In feature extraction and