A hybrid watermarking technique using Singular value Decomposition with orthogonal transforms like DCT, Haar, Walsh, Real Fourier Transform and Kekre transform is proposed in this paper. Later, SVD is combined with wavelet transforms generated from these orthogonal transforms. Singular values of watermark are embedded in middle frequency band of column/row transform of host image. Before embedding, Singular values are scaled with suitable scaling factor and are sorted. Column/row transform reduces the computational complexity to half and properties of singular value decomposition and transforms add to robustness. Behaviour of proposed method is evaluated against various attacks like compression, cropping, resizing, and noise addition. For majority of attacks wavelet transforms prove to be more robust than corresponding orthogonal transform from which it is generated.

This paper deals with interpretation of patterns via neural networks under organization and classification approaches. Fifty different groups of images including geometric shapes, mechanical instruments, machines, animals, fruits, and other classes of samples are classified here in two successive steps. Each primary category is divided into three different sub-groups. The purpose is identifying the class and sub-class of each input sample. Nowadays, industry and manufacturing are moving towards automation; hence accurate description of photos results in a myriad of industrial, security, and medical applications and takes a pressing part in artificial intelligence's progression. Intelligent interpretation of structure's design in CNC machine eventuates in autonomous selection of cutting tools by which any structure can easily be manufactured. Anyhow, this paper comes up with a pattern interpretation method to be applied in submarine detection purposes. Remotely operated vehicles (ROV) are used to detect and survey oil pipelines and underwater marine structures, so mentioned neural network classification is a practicable tool for detection mechanism and avoiding obstacles in ROVs.

Face recognition system is one of the robust means of authentication. It involves comparing the faces of an individual against a set of images in the training database. Thus the security issues pertaining to the training database is very critical. This paper aims at providing security to the images in the training database by empowering the encryption algorithms using a secure Random Number Generator (RNG). To facilitate this, the seismic waves are used as seeds to drive the Pseudo-Random Number Generators (PRNGs). The efficiency of seismic waves as a True Random Number Generator (TRNG) was evaluated using two statistical suites. Also, the proposed TRNG is compared against other existing RNGs. It was found that the degree of randomness rendered by the proposed system was in good agreement like the other existing generators. The proposed system was found to be cost-effective, portable and easy to maintain.

HyperSpectral Imagers (HySI) are used in the spacecraft or aircrafts to get minute characteristics of target element through capturing image in a large number of narrow and contiguous bands. HySI data represented as data cube with two dimensions representing spatial distribution and third dimension providing band information is huge in volume and challenging task to handle. Hence onboard compression becomes a necessary for optimal usage of onboard storage and downlink bandwidth. CCSDS recommended 123.0-B-1 standard[2] has been released with onboard compression scheme of hyperspectral data. The scheme is based on Fast Lossless algorithm and consists of two main functional blocks namely Predictor and Encoder. Predictor algorithm can be implemented in two modes 'Full Neighborhood Oriented' and 'Reduced Column Oriented'. Encoder algorithm also defines two options 'sample-adaptive' and 'block-adaptive'. We have developed a MATLAB based model implementing the compression scheme with all options defined by the standard. Decompression model is also developed for getting back actual data and end to end verification. Four sets of HySI data (AVIRIS, Hyperion, Chandrayan-1 and FTIS) have been applied as input to the developed model for evaluation of the model. Compression ratio achieved is between 2 to 3 and lossless compression is ensured for each set of data as Mean Square Error (MSE) is zero for all hyperspectral images. Also visual reconstruction of decompressed data matches with original ones. In this paper we have discussed algorithm implementation methodology and results.

Spike sorting involves clustering spikes according to the similarity of their shapes. Usually the sorting procedure is carried out by extracting appropriate features of neuronal spikes. In this study a new spike sorting procedure based on genetic algorithm is developed which contains two distinct phases. In the first phase a B-spline curve is fitted to each spike waveform and then the optimal features are selected from parameters of fitted B-spline curves. The genetic algorithm is used for searching the optimal parameters of B-spline curve in a way that the curve fitting error is minimized. In the second phase, clustering of spikes based on extracted features is performed by applying genetic algorithm. In this phase the fitness function is defined in a manner that both spatial distances between objects in the feature space and their similarity in the real world are considered. The proposed sorting method is tested on the real neural dataset which firstly are classified by an expert human. The results show that the proposed method based on genetic algorithm framework gives fewer errors of clustering in comparison with some other approaches currently used in the clustering purposes.

Biometric authentication has been emerged as a reliable means to control a person's access to physical and virtual places. Despite the various efforts made on biometrics, accuracy of the authentication/identification is the main concern and it has to be completely investigated. The paper presents critical analysis of the matching score values in such a manner that system accuracy is increased. Min Max Threshold Range (MMTR) technique is proposed that provides two levels of authentication and increase in accuracy is observed. The methodology of increase in accuracy is observed on various feature extraction methods.

The marine researchers analyze the behaviors of fish in the sea by manually viewing the full video for their research activity. Searching events of interest from a video database is a time consuming and tedious process. Video summary refers to representing the whole video using few frames. The objective of this work is to design and develop a statistical video summarization to perform the automatic detection of events of interest in underwater video. In this proposed work, a video is partitioned into adjacent and non-overlapping datacubes. Then, the video frames are transformed into wavelet sub-bands and the standard deviation between two consecutive frames is computed. Pixels of interest in frames are identified using threshold values. Key frames are identified using Local Maxima and Local Minima. The proposed work effectively detects even the movement of small water bodies such as crabs which is not detected using the existing methods. Finally, this paper presents the experimental results of proposed method and existing methods in terms of metrics that measure the valid of the work.

Pixel value differencing is a steganographic technique for gray scaled images. In this paper, we propose a modified pixel value differencing image steganographic scheme with least significant bit substitution method. Our method divides the cover image into the blocks of two consecutive pixels and calculates the absolute difference between the pixels of a block similar to [1, 2]. If the difference is less than a particular threshold, i.e. 15 (in this paper) than 4 bits of secret data are taken and these bits are embedded onto the LSBs of the block's pixels through least significant bit substitution method otherwise the number of bits to be hidden are selected based on some characteristics of the block and hidden. The experimental results show that our method significantly improves the quality of stego image as compared to the [1, 3] and have sufficient payload.