Alaa Hamdy

FPGA-based object-extraction based on multimodal Σ-Δ background estimation

In this paper, we propose a robust and accurate algorithm based on a multimodal Σ-Δ background estimation to extract the moving objects in image sequence of size 768 x 576 pixels taken from a static camera. Σ-Δ estimation is used to compute two orders of temporal statistics for each pixel of the sequence providing a pixel-level decision framework. A serious limitation of this approach lies in the adaptation capability to certain complex scenes. In this paper, we avoid this limitation by modeling each pixel as mixture of three distributions to deal with complex scenes. We show that the enhanced performance is achieved by using the proposed algorithm. This paper describes also an FPGA-based implementation of the proposed algorithm at a very high frame rate that reaches to 1198 frames per second in a single low cost FPGA chip, which is adequate for most real-time vision applications.

Utilizing Image Block Properties to Embed Data in the DCT Coefficients with Minimum MSE

Steganography aimed at hiding the presence of communication in a medium that is used to carry secret messages (image, audio, or video). Many steganographic systems can be attacked visually or statistically (steganalysis). In this paper, block based steganography algorithm with minimum MSE is presented, an algorithm that embed data in the least significant bit (LSB) of the discrete cosine transform (DCT) coefficients of JPEG image blocks. This technique exploits the ratio of even to odd coefficients in each image block and embeds data bits in a way that preserves the ratio between even and odd DCT coefficients of each image block. Block Based Steganography (BBS) algorithm offers high capacity with statistically minimal changes compared to current steganographic algorithms. The mean square error of BBS algorithm in the spatial domain is presented.

Disparity map using suboptimal cost with dynamic programming

1D optimization methods based on dynamic programming (DP) stereo are of practical interest because it can reconstruct an observed 3D optical surface very quickly and thus has potential for real-time applications. While being efficient, its performance is far from the state of the art because the vertical consistency between the scanlines is not enforced. 1D optimization based on dynamic programming for stereo correspondence is re-examined by applying it to the vertical consistency between the scanlines as opposed to the individual scanlines. To do this, a pixel is allowed to have a disparity with possibly sub-optimal cost for it in two directions. Thus, the proposed algorithm is a truly global optimization method because disparity estimate at one pixel depends on the disparity estimates at all the other pixels, unlike the scanline based methods. Proposed algorithm is evaluated on the benchmark Middlebury database. The algorithm is very simple, so the proposed algorithm should be a good candidate for real time implementation. The results are considerably better than that of the scanline based methods. While the results are not the state of the art, the proposed algorithm offers a good trade off in terms of accuracy and computational efficiency.

Arabic Alphabet and Numbers Sign Language Recognition

This paper introduces an Arabic Alphabet and Numbers Sign Language Recognition (ArANSLR). It facilitates the communication between the deaf and normal people by recognizing the alphabet and numbers signs of Arabic sign language to text or speech. To achieve this target, the system able to visually recognize gestures from hand image input. The proposed algorithm uses hand geometry and the different shape of a hand in each sign for classifying letters shape by using Hidden Markov Model (HMM). Experiments on real-world datasets showed that the proposed algorithm for Arabic alphabet and numbers sign language recognition is suitability and reliability compared with other competitive algorithms. The experiment results show that the increasing of the gesture recognition rate depends on the increasing of the number of zones by dividing the rectangle surrounding the hand.

Multi-objective symbolic regression using long-term artificial neural network memory (LTANN-MEM) and neural symbolization algorithm (NSA)

Symbolic regression is commonly performed using evolutionary algorithms like genetic programming (GP). The goal of this research work is to construct symbolic models from examples where a new symbolic regression approach based on artificial neural networks is proposed. This approach is composed of a long-term artificial neural network memory (LTANN-MEM), a working memory (WM) in addition to a proposed neural symbolization algorithm (NSA) which uses LTANN-MEM and WM for synthesizing symbolic models equivalent to learning examples. The proposed LTANN-MEM is composed of two separate multilayer perceptron (MLP) feed-forward neural networks as well as the working memory which is composed of a single MLP. The core idea of the proposed approach is based on memorizing the learning experience of individual perceptrons in long-term memory (LTM), so they become available to be reused in generating and developing hypotheses about the learning examples. Although this idea is generic and could be used for the purpose of symbolization in general, it is applied here in symbolic regression for Boolean domain only. The obtained results show the ability of the proposed approach to search the solutions space using learning experience stored previously in LTM to guide the search process. A comparison is done with GP and found that the proposed NSA algorithm outperforms GP in its performance when increasing the number of inputs and outputs in the same problem by comparing the number of emerged candidate solutions in both approaches.

C30. An Interpolation Based Technique for Sign Language Recognition

The objective of the research presented in this paper is to facilitate the communication between people with hearing impairment (i.e. deaf people) and normal people. In addition, an efficient and fast algorithm for automatic translation system for gestures of manual numbers in the sign Language is proposed. The proposed algorithm does not rely on the use of any gloves or visual markings to accomplish the recognition job. The proposed system uses the concept of boundary tracing and finger tip detection. As an alternative, it deals with images of bare hands, which allows the user to interact with the system in a natural way. The technique is based on interpolation of signature of hand image. Experiments revealed that satisfactory results can be obtained via the proposed algorithm.

Multi target tracking using a compact Q-learning with a teacher

This paper focuses on developing a team of mobile robots capable of learning via human interaction. A modified Q-learning algorithm incorporating a teacher is proposed. The paper first concentrates on simplifying the Q-learning algorithm to be implemented on small and simple team of robots having limited capabilities of memory and computational power. Second it concentrates on the incorporation of a human teacher in the Q-learning algorithm. Experiments using the well-known robot simulator Webots on both single and multi-target tracking tasks have been conducted. The achieved results show the success of the proposed algorithm in the over all system performance.

Transfer learning with long term artificial neural network memory (LTANN-MEM) and neural symbolization algorithm (NSA) for solving high dimensional multi-objective symbolic regression problems

Long Term Artificial Neural Network Memory (LTANN-MEM) and Neural Symbolization Algorithm (NSA) are proposed for solving symbolic regression problems. Although this approach is capable of solving Boolean decoder problems of sizes 6, 11 and 20, it is not capable of solving decoder problems of higher dimensions like decoder-37; decoder-n is decoder with sum of inputs and outputs is n for example decoder-20 is decoder with 4 inputs and 16 outputs. It is shown here that LTANN-MEM and NSA approach is a kind of transfer learning however it lacks for sub tasking transfer and updatable LTANN-MEM. An approach for adding the sub tasking transfer and LTANN-MEM updates is discussed here and examined by solving decoder problems of sizes 37, 70 and 135 efficiently. Comparisons with two learning classifier systems are performed and it is found that the proposed approach in this work outperforms both of them. It is shown that the proposed approach is used also for solving decoder-264 efficiently. According to the best of our knowledge, there is no reported approach for solving this high dimensional problem.

Performance Evaluation of Virtual Identity Approaches for Anonymous Communication in Distributed Environments

Abstract: Todays enterprises core concept of security is the Identity (ID). When it comes to mapping identity in order to gain access to a specific service or digital account, cloud technology offers the most robust, cost-effective, easy-to-use solutions available. In this paper, the Virtual Identity (V ID ) concept is not only used to improve the user privacy and security on the network and service platforms but also, the V ID performance is evaluated by implementing a mathematical model based on Baskett Chandy Muntz-Palacios (BCMP) model. Moreover, a simulation-based evaluation using OPNET Modeler is conducted to compare the simulation results against the analytical model based BCMP queuing analysis. Finally, the comparative study of our proposed models and the related work proves that our proposed models are suitable for anonymous communication in distributed virtual environments.

Low Complexity for Scalable Video Coding Extension of H.264 based on the Complexity of Video

Scalable Video Coding (SVC) / H.264 is one type of video compression techniques. Which provided more reality in dealing with video compression to provide an efficient video coding based on H.264/AVC. This ensures higher performance through high compression ratio. SVC/H.264 is a complexity technique whereas the takes considerable time for computation the best mode of macroblock and motion estimation through using the exhaustive search techniques. This work reducing the processing time through matching between the complexity of the video and the method of selection macroblock and motion estimation. The goal of this approach is reducing the encoding time and improving the quality of video stream the efficiency of the proposed approach makes it suitable for are many applications as video conference application and security application.