1 Genetic Algorithm based Mosaic Image Steganography for Enhanced Security, Soumi C.G, Joona George, Janahanlal Stephen
The concept of mosaic steganography was proposed by Lai and Tsai [4] for information hiding and retrieval using techniques such as histogram value, greedy search algorithm, and random permutation techniques. In the present paper, a novel method is attempted in mosaic image steganography using techniques such as Genetic algorithm, Key based random permutation .The creation of a predefined database of target images has been avoided. Instead, the randomly selected image is used as the target image reduces the enforced memory load results reduction in the space complexity .GA is used to generate a mapping sequence for tile image hiding. This has resulted in better clarity in the retrieved secret image as well as reduction in computational complexity. The quality of original cover image remains preserved in spite of the embedded data image, thereby better security and robustness is assured. The mosaic image is yielded by dividing the secret image into fragments and embed these tile fragments into the target image based on the mapping sequence by GA and permuted the sequence again by KBRP with a key .The recovery of the secret image is by using the same key and the mapping sequence. This is found to be a lossless data hiding method.
2 Mental Stress Evaluation using an Adaptive Model, Khalid Masood
Chronic stress can have serious physiological and psychological impact on an individual’s health. Wearable sensor systems can enable physicians to monitor physiological variables and observe the impact of stress over long periods of time. To correlate an individual’s physiological measures with their perception of psychological stress, it is essential that the stress monitoring system accounts for individual differences in self-reporting. Self-reporting of stress is highly subjective as it is dependent on an individual’s perception of stress and thus prone to errors. In addition, subjects can tailor their answers to present their behavior more favorably. In this paper we present an adaptive model which allows recorded stress scores and physiological variables to be tuned to remove biases in self-reported scores. The model takes an individual’s physiological and psychological responses into account and adapts to the user’s variations. Using our adaptive model, physiological data is mapped efficiently to perceived stress levels with 90% accuracy.
3 High Density Salt and Pepper Impulse Noise Removal, Manohar Koli, and S.Balaji
In this paper, solution for very high density salt and pepper impulse noise is proposed. An algorithm is designed by considering the different parameters that influence the effect of noise reduction. The proposed algorithm contains two phases: Phase 1 detects the noisy pixels and Phase 2 replaces identified noisy pixels by non-noisy estimated values. Restored Mean Absolute Error (RMAE) is used to measure and compare the performance of the proposed algorithm. The algorithm is compared with several non-linear algorithms reported in the literature. Experimental results show that the proposed algorithm produces better results compared to the existing algorithms.
4 Optimized Neural Network for Classification of Multispectral Images, Rajesh K. Agrawal, Dr. Narendra G. Bawane
The proposed work involves the multiobjective PSO based optimization of artificial neural network structure for the classification of multispectral satellite images. The neural network is used to classify each image pixel in various land cove types like vegetations, waterways, man-made structures and road network. It is per pixel supervised classification using spectral bands (original feature space). Use of neural network for classification requires selection of most discriminative spectral bands and determination of optimal number of nodes in hidden layer. We propose new methodology based on multiobjective particle swarm optimization (MOPSO) to determine discriminative spectral bands and the number of hidden layer node simultaneously. The result obtained using such optimized neural network is compared with that of traditional classifiers like MLC and Euclidean classifier. The performance of all classifiers is evaluated quantitatively using Xie-Beni and â indexes. The result shows the superiority of the proposed method.
5 Comparative Study of Morphological, Correlation, Hybrid and DCSFPSS based Morphological & Tribrid Algorithms for GFDD, V. Jayashree, S. Subbaraman
This paper proposes comparative study of two basic approaches such as Morphological Approach (MA) and Correlation Approach (CA) and three modified algorithms over the basic approaches for detection of micronatured defects occurring in plain weave fabrics. A Hybrid of CA followed by MA was developed and has shown to overcome the drawbacks of the basic methods. As automation of MA using DC Suppressed Fourier Power Spectrum Sum (DCSFPSS), DCSFPSSMA could not yield improvement in Overall Detection Accuracy (ODA) for micronatured defects, automation of modified Hybrid Approach (HA) was proposed leading to the development of Tribrid Approach (TA). Modified Hybrid approach involves cascade operation of CA and MA both automated using DCSFPSS. Texture periodicity of defect free fabric was obtained using DCSFPSS which was extended for the design and extraction of defect independent template for CA and for the design of the size of structuring element for morphological filtering process. Overall Detection Accuracy was used by adopting simple binary based defect search algorithm as the last step in the experimentation to detect the defects. Overall Detection Accuracy was found to be ~100%/97.41%/ 98.7 % for 247 samples of warp break defect/ double pick/ normal samples and 96.1% /99% for 205 thick place defect samples/normal samples belonging to two different plain grey fabric classes. Robustness of the performance of TA scheme was tested by comparing TA with two traditional algorithms viz., CA and MA and our previously proposed hybrid algorithm and DCSFPSSMA. This TA algorithm outperformed when compared to CA-only, MA-only, HA and DCSFPSSMA by yielding an overall ODA of more than 98% for the defect and defect free samples of different fabric classes. Secondly, the recognition of defect area less than 1 mm2 which has not been reported in the literature yet, was possible using this algorithm. We propose to use this method as a means to grade the grey fabric similar to the standard fabric grading system.
6 Texture Unit based Monocular Real-world Scene Classification using SOM and KNN Classifier, N.P. Rath and Bandana Mishra
In this paper a method is proposed to discriminate real world scenes in to natural and manmade scenes of similar depth. Global-roughness of a scene image varies as a function of image-depth. Increase in image depth leads to increase in roughness in manmade scenes; on the contrary natural scenes exhibit smooth behavior at higher image depth. This particular arrangement of pixels in scene structure can be well explained by local texture information in a pixel and its neighborhood. Our proposed method analyses local texture information of a scene image using texture unit matrix. For final classification we have used both supervised and unsupervised learning using K-Nearest Neighbor classifier (KNN) and Self Organizing Map (SOM) respectively. This technique is useful for online classification due to very less computational complexity.
7 Rotman Lens Performance Analysis, Shruti Vashist, Dr. M.K Soni ,Dr.P.K.Singhal
This paper presents a trifocal Rotman Lens Design approach. The effects of focal ratio and element spacing on the performance of Rotman Lens are described. A three beam prototype feeding 4 element antenna array working in L-band has been simulated using RLD v1.7 software. Simulated results show that the simulated lens has a return loss of – 12.4dB at 1.8GHz. Beam to array port phase error variation with change in the focal ratio and element spacing has also been investigated.
8 Microelectronic Circuit Analogous to Hydrogen Bonding Network in Active Site of -lactamase, Rostislav P. Rusev, Elitsa E. Gieva, George V. Angelov, Rossen I. Radonov, and Marin H. Hristov
A microelectronic circuit of block-elements functionally analogous to two hydrogen bonding networks is investigated. The hydrogen bonding networks are extracted from â-lactamase protein and are formed in its active site. Each hydrogen bond of the network is described in equivalent electrical circuit by three or four-terminal block-element. Each block-element is coded in Matlab. Static and dynamic analyses are performed. The resultant microelectronic circuit analogous to the hydrogen bonding network operates as current mirror, sine pulse source, triangular pulse source as well as signal modulator.
9 3-D FFT Moving Object Signatures for Velocity Filtering, G. Koukiou and V. Anastassopoulos
In this paper a bank of velocity filters is devised to be used for isolating a moving object with specific velocity (amplitude and direction) in a sequence of frames. The approach used is a 3-D FFT based experimental procedure without applying any theoretical concept from velocity filters. Accordingly, each velocity filter is built using the spectral signature of an object moving with specific velocity. Experimentation reveals the capabilities of the constructed filter bank to separate moving objects as far as the amplitude as well as the direction of the velocity are concerned. Accordingly, weak objects can be detected when moving with different velocity close to strong vehicles. Accelerating objects can be detected only on the part of their trajectory they have the specific velocity. Problems which arise due to the discontinuities at the edges of the frame sequences are discussed.
10 Band Clustering for the Lossless Compression of AVIRIS Hyperspectral Images, Raffaele Pizzolante and Bruno Carpentieri
Hyperspectral images can be efficiently compressed through a linear predictive model, as for example the one used in the SLSQ algorithm. In this paper we exploit this predictive model on the AVIRIS images by individuating, through an off-line approach, a common subset of bands, which are not spectrally related with any other bands. These bands are not useful as prediction reference for the SLSQ 3-D predictive model and we need to encode them via other prediction strategies which consider only spatial correlation. We have obtained this subset by clustering the AVIRIS bands via the clustering by compression approach. The main result of this paper is the list of the bands, not related with the others, for AVIRIS images. The clustering trees obtained for AVIRIS and the relationship among bands they depict is also an interesting starting point for future research.
11 Blind Source Separation of Super and Sub-Gaussian Signals with ABC Algorithm, Sanjeev N. Jain, Dr.Chandra Shekhar Rai
Recently, several techniques have been presented for blind source separation using linear or non-linear mixture models. The problem is to recover the original source signals without knowing apriori information about the mixture model. Accordingly, several statistic and information theory-based objective functions are used in literature to estimate the original signals without providing mixture model. Here, swarm intelligence played a major role to estimate the separating matrix. In our work, we have considered the recent optimization algorithm, called Artificial Bee Colony (ABC) algorithm which is used to generate the separating matrix in an optimal way. Here, Employee and onlooker bee and scout bee phases are used to generate the optimal separating matrix with lesser iterations. Here, new solutions are generated according to the three major considerations such as, 1) all elements of the separating matrix should be changed according to best solution, 2) individual element of the separating matrix should be changed to converge to the best optimal solution, 3) Random solution should be added. These three considerations are implemented in ABC algorithm to improve the performance in Blind Source Separation (BSS). The experimentation has been carried out using the speech signals and the super and sub-Gaussian signal to validate the performance. The proposed technique was compared with Genetic algorithm in signal separation. From the result, it was observed that ABC technique has outperformed existing GA technique by achieving better fitness values and lesser Euclidean distance.
12 Efficient Architecture for Variable Block Size Motion Estimation in H.264/AVC, P.Muralidhar, C.B.Rama Rao, and CYN Dwith
This paper proposes an efficient VLSI architecture for the implementation of variable block size motion estimation (VBSME). To improve the performance video compression the Variable Block Size Motion Estimation (VBSME) is the critical path. Variable Block Size Motion Estimation feature has been introduced in to the H.264/AVC. This feature induces significant complexities into the design of the H.264/AVC video codec. This paper we compare the existing architectures for VBSME. An efficient architecture to improve the performance of Spiral Search for Variable Size Motion Estimation in H.264/AVC is proposed. Among various architectures available for VBSME spiral search provides hardware friendly data flow with efficient utilization of resources. The proposed implementation is verified using the MATLAB on foreman, coastguard and train sequences. The proposed Adaptive thresholding technique reduces the average number of computations significantly with negligible effect on the video quality. The results are verified using hardware implementation on Xilinx Virtex 4 it was able to achieve real time video coding of 60 fps at 95.56 MHz CLK frequency.