The speech recognition system has been widely used by many researchers using different
methods to fulfill a fast and accurate system. Speech signal recognition is a typical
classification problem, which generally includes two main parts: feature extraction and
classification. In this paper, a new approach to achieve speech recognition task is proposed by
using transformation techniques for feature extraction methods; namely, slantlet transform
(SLT), discrete wavelet transforms (DWT) type Daubechies Db1 and Db4. Furthermore, a
modified artificial neural network (ANN) with dynamic time warping (DTW) algorithm is
developed to train a speech recognition system to be used for classification and recognition
purposes. T

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.

Image quality plays a vital role in improving and assessing image compression performance. Image compression represents big image data to a new image with a smaller size suitable for storage and transmission. This paper aims to evaluate the implementation of the hybrid techniques-based tensor product mixed transform. Compression and quality metrics such as compression-ratio (CR), rate-distortion (RD), peak signal-to-noise ratio (PSNR), and Structural Content (SC) are utilized for evaluating the hybrid techniques. Then, a comparison between techniques is achieved according to these metrics to estimate the best technique. The main contribution is to improve the hybrid techniques. The proposed hybrid techniques are consisting of discrete wavel

 

            This paper presents a study of wavelet self-organizing maps (WSOM) for face recognition. The WSOM is a feed forward network that estimates optimized wavelet based for the discrete wavelet transform (DWT) on the basis of the distribution of the input data, where wavelet basis transforms are used as activation function.

 

 

Boltzmann mach ine neural network bas been used to recognize the Arabic speech.  Fast Fourier transl(>lmation algorithm has been used t() extract speciral 'features from an a caustic signal .

The  spectral  feature size is reduced by series of operations in

order to make it salable as input for a neural network which is used as a recogni zer by Boltzmann Machine Neural  network which has been used as a recognizer for phonemes . A training set consist of a number of Arabic phoneme repesentations, is used to train lhe neuntl network.

The neural network recognized Arabic. After Boltzmann Machine Neura l    network   training  the  system   with 

The need for a flexible and cost effective biometric security system is the inspired of this paper. Face recognition is a good contactless biometric and it is suitable and applicable for Wireless Sensor Network (WSN). Image processing and image communication is a challenges task in WSN due to the heavy processing and communication that reduce the life time of the network. This paper proposed a face recognition algorithm on WSN depending on the principles of the unique algorithm that hold the capacity of the network to the sink node and compress the communication data to 89.5%. An efficient hybrid method is introduced based upon the advantage of Zak transform to offprint the farthest different features of the face and Eigen face method to

Steganography is the art of secret communication. Its purpose is to hide the presence of information, using, for example, images as covers. The frequency domain is well suited for embedding in image, since hiding in this frequency domain coefficients is robust to many attacks. This paper proposed hiding a secret image of size equal to quarter of the cover one. Set Partitioning in Hierarchal Trees (SPIHT) codec is used to code the secret image to achieve security. The proposed method applies Discrete Multiwavelet Transform (DMWT) for cover image. The coded bit stream of the secret image is embedded in the high frequency subbands of the transformed cover one. A scaling factors ? and ? in frequency domain control the quality of the stego

Social media is known as detectors platform that are used to measure the activities of the users in the real world. However, the huge and unfiltered feed of messages posted on social media trigger social warnings, particularly when these messages contain hate speech towards specific individual or community. The negative effect of these messages on individuals or the society at large is of great concern to governments and non-governmental organizations. Word clouds provide a simple and efficient means of visually transferring the most common words from text documents. This research aims to develop a word cloud model based on hateful words on online social media environment such as Google News. Several steps are involved including data acq

The use of Cosine transform to analyze the model-noise pattern alteration with different vibration model applied on multimode fiber optics are studied. It's results compared with the Fourier transform to perform the same analysis using total frequency difference and the computation time, which almost coincide for the both transforms. A discussion for the results and recommendation are introduced.