|Title: Wu-Lee Steganographic Algorithm on Binary Images Processed in Parallel|
|Author(s): Silvana GRECA, Edlira MARTIRI|
|Pages: 01-04||Paper ID: 127703-6363-IJVIPNS-IJENS||Published: June, 2012|
Abstract: Data security is nowadays one of the most active fields of study in Informatics and Computer Science. Author right for intellectual property is a real challenge, especially when information is processed and transmitted. One of the electronic forms of digital data is images. They are widely used in organizations, research institutions, and in environments where high resolution is needed. Here we come across to another kind of processing: parallelism. Information hiding and watermarking techniques are essential in addressing the problem of author copyright. This is done by means of steganographic algorithms. The aim of this paper is to analyze and present those steganographic algorithms which can be parallelized to a coarse-grain size. We will consider one typical steganographic algorithms for binary images, Wu-Lee and will analyze the parallelization of this algorithm.
|Keywords: Steganography, Wu-Lee method, binary image, parallel processing|
|Full Text (.pdf) | 177 KB|
|Title: A Computer Vision Approach for Reducing Energy Losses|
|Author(s): Ahmad Khan, Muhammad Uzair|
|Pages: 05-07||Paper ID: 122003-7474-IJVIPNS-IJENS||Published: June, 2012|
Abstract: Saving electrical energy is one of the major requisites of the countries around the world, especially third world countries. In this paper we present a computer vision system for reducing electrical energy waste. The system senses the environment using computer vision and turns-off electrical appliances when they run needlessly. The absence of people is determined by detecting and tracking people in places like offices, classrooms or halls. To increase accuracy, the concept of data fusion is employed. Simple electronics sensors are used to cope with situations where only camera decision is not sufficient. We have tested our system in university campus and in the absence of people, it is capable of intelligently turning off electrical appliances to avoid waste of electrical energy: resulting in energy saving.
|Keywords: Electrical Energy, Energy Losses|
|Full Text (.pdf) | 70 KB|
|Title: Adaptation of Spiking Neural Networks for Image Clustering|
|Author(s): Chinki Chandhok, Soni Chaturvedi|
|Pages: 08-13||Paper ID: 122503-8484-IJVIPNS-IJENS||Published: June, 2012|
Abstract: A Biological Neural Network or simply BNN is an artificial abstract model of different parts of the brain or nervous system, featuring essential properties of these systems using biologically realistic models. The process of segmenting images is one of the most critical ones in automatic image analysis whose goal can be regarded as to find what objects are presented in images. This paper depicts the image processing algorithms that treat the problem of image segmentation. Spiking Neuron Networks (SNNs) are often referred to as the 3rd generation of neural networks which have potential to solve problems related to biological stimuli. Spiking neural networks (SNNs) exhibit interesting properties that make them particularly suitable for applications that require fast and efficient computation and where the timing of input-output signals carries important information. However, the use of such networks in practical, goal-oriented applications has long been limited by the lack of appropriate unsupervised learning methods. Image clustering in realistic human sense can very well be analyzed using SNN. Spiking neural networks usually results in improved quality of segmentation reflecting the mean square error to be minimum. Effective Matlab Programs yielded good results for real time, realistic human being brain behavior like output.
|Keywords: Spiking Neural Network (SNN), Spike; Integrate and fire neuron, Segmentation, backpropagation, gradient descent, wavelets|
|Full Text (.pdf) | 189 KB|