Sanjay B. Dhok

Cluster size optimisation with Tunable Elfes sensing model for single and multi-hop wireless sensor networks

ABSTRACT Minimising energy dissipation and maximising network coverage are the crucial aspects of wireless sensor networks (WSNs). The nodes of a sensor network are grouped into several non-overlapping subset to facilitate the network scalability and design of energy efficient system. Selecting optimal clusters provide significant gain in terms of network lifetime, system scalability, collision avoidance and end-to-end delay. Network coverage is another critical issue which depends on sensing model like deterministic sensing model and probabilistic sensing model. In this paper, we have proposed Tunable Elfes Sensing Model. This model is preferable in case of remote area application in WSNs, where nodes in the core of network closer to base station (BS) are modelled deterministically, whereas peripheral nodes are modelled probabilistically. Thus, we can model energy efficient system with large coverage area. In this paper, we have provided expression for optimal cluster using Tunable Elfes sensing model of BS for square and circular sensing field using single-hop communication between cluster heads (CHs) and BS with consideration of boundary effect. We have also analysed the optimal clusters for square and circular type of sensing field using Tunable sensing model for BS multi-hop communication between CHs and BS.

Review of Text Extraction Algorithms for Scene-text and Document Images

ABSTRACT One of the major applications of text retrieval from images is to extract the text information and then recognize its characters. This is helpful for indexing the images within storage media. When we want to search a particular image or document, there is no need to go through a large bunch of images. We go only through the group of indexed images, so that the task of finding the particular image becomes easy. Extracting text lines from scanned document images present a major problem in optical character recognition process as skewed text lines raise the complexity. The problem gets even worse with the text lines of different orientations. Such lines are called as multi-skewed lines. These multi-skewed lines are easily observed in both printed and handwritten documents. It is a challenging task to design a real time system, which can maintain a high recognition rate with good accuracy and is independent of the type of documents and character fonts. In this paper, we attempt to analyze and classify the various text extraction schemes for the scene-text and document images. We also compare different approaches of these images based on common problems and discuss their merits and demerits.

Magnetic Induction-Based Non-Conventional Media Communications: A Review

The magnetic induction (MI)-based communications assume the applications, wherein standard electromagnetic (EM) wave and acoustic communications are not effective. The EM and acoustic-based communications do have high power loss, high propagation delays, very low data rates, and environment-dependent channel behavior. MI communications heavily depend upon the time varying magnetic field to convey information between transmitter and receiver. MI-based communications for non-conventional media (e.g., underwater or underground) exhibit several unique and promising qualities, such as constant channel behavior, negligible propagation delay, and large communications range. This paper surveys the current state-of-the-art magnetic induction-based communications for non-conventional media applications. The widely used communications techniques for non-conventional media are qualitatively compared. In particular, the advantages and the disadvantages of different communications techniques are analyzed in terms of different performance metrics. In addition, we highlight some important open issues related to the design of MI for non-conventional media. This survey aims to provide a useful guidance to the researchers in this area.

Script identification algorithms: a survey

Script identification is being widely accepted techniques for selection of the particular script OCR (Optical Character Recognition) in multilingual document images. Extensive research has been done in this field, but still it suffers from low identification accuracy. This is due to the presence of faded document images, illuminations and positions while scanning. Noise is also a major obstacle in the script identification process. However, it can only be minimized up to a level, but cannot be removed completely. In this paper, an attempt is made to analyze and classify various script identification schemes for document images. The comparison is also made between these schemes, and discussion is made based upon their merits and demerits on a common platform. This will help the researchers to understand the complexity of the issue and identify possible directions for research in this field.

Digital Forensic of JPEG Images

Since JPEG is the de facto image format adopted in most of the digital cameras and image editing software, tampered image will be often a recompressed JPEG image. As JPEG works on 8 by 8 block cosine transform most of the tampering correlation inherited by tampered image may get destroyed, making forgery detection difficult thus it is common practice followed by forger to hide traces of resampling & splicing. JPEG forgery detection techniques try to identify inconsistencies in the artifacts introduced in image due to 8 by 8 block DCT transform. The original image on which forgery is created may be compressed or uncompressed image, similarly area pasted may belong to compressed or uncompressed image. Since both will be having different compression history JPEG forgery detection techniques try to identify the difference in compression history which may be in the form of shifting of DCT block alignment, difference in primary quantization table or ghost detection.

Robust Character Segmentation and Recognition Schemes for Multilingual Indian Document Images

ABSTRACT This paper presents robust methods for character segmentation and recognition for multilingual (Latin and Devanagari) Indian document images. The documents degraded over the years because of text diffusion, layout structures, and intermixed texts (printed and handwritten). In character segmentation algorithm, initially, pre-processing like noise and non-uniform illumination reduction is performed. Segmentation columns between characters are obtained using their structural properties. In addition, graph distance theory is used to separate touched and overlapped characters. Finally, support vector machine classifier is employed to validate the segmentation results. For character recognition, set of features based on geometrical properties of the characters are proposed. First feature is formed using center pixel of each non-overlapping block, whereas second feature is a vector of cut points calculated in the triangular areas of the character. Apart from these features, one more feature is used that contains neighborhood information of text pixels. Comprehensive experiments are performed on publicly available databases along with the database collected by us. Benchmarking analysis shows that highest segmentation and recognition accuracies are obtained 98.79% and 99.6%, respectively.

Word Level Multi-Script Identification Using Curvelet Transform in Log-Polar Domain

ABSTRACT Nowadays, a number of scripts are used for writing. Script identification finds many applications like sorting and preparing an online database of documents. Identifying these scripts, especially with different orientations and scales, is an important and challenging problem in document image analysis. This paper proposed a new scheme for script identification from word images using skew and scale robust log-polar curvelet features. These word images are first extracted in the form of text-patches from documents using Gaussian filtering. Thereafter, texture features are calculated using curvelet transform in log-polar domain. Log-polar domain is independent of rotation and scale variations, whereas curvelet transform exhibits directional and anisotropic properties. This helps in the extraction of significant features. For experiments, k-nearest neighbor classifier is employed to identify the scripts, as it has zero training time and is simple to implement. Further, statistical significance test is performed by using two more classifiers, namely random forest and support vector machine. Comprehensive experimentations are carried out on ALPH-REGIM, Pati and Ramakrishnan, PHDIndic_11, and proprietary databases containing printed as well as handwritten texts. Here, bi-script, tri-script, and multi-script identification results are reported. Benchmarking analysis illustrated the effectiveness of the proposed method, where a maximum recall rate of 98.76% has been achieved.

Localization of Tampering Created with Facebook Images by Analyzing Block Factor Histogram Voting

Facebook images get distributed within a fraction of a second, which hackers may tamper and redistribute on cyberspace. JPEG fingerprint based tampering detection techniques have major scope in tampering localization within standard JPEG images. The majority of these algorithms fails to detect tampering created using Facebook images. Facebook utilizes down-sampling followed by compression, which makes difficult to locate tampering created with these images. In this paper, the authors have proposed the tampering localization algorithm, which locates tampering created with the images downloaded from Facebook. The algorithm uses Factor Histogram of DCT coefficients at first 15 modes to find primary quantization steps. The image is divided into BXB overlapping blocks and each block is processed individually. Votes cast by these modes for conceivable tampering are collected at every pixel position and the ones above threshold are used to form different regions. High density voted region is proclaimed as tampered region.

Tampering Localization in Digital Image Using First Two Digit Probability Features

In this paper, we have used the first digit probability distribution to identify inconsistency present in the tampered JPEG image. Our empirical analysis shows that, first two digits probabilities get significantly affected by tampering operations. Thus, prima facie tampering can be efficiently localized using this smaller feature set, effectively reducing localization time. We trained SVM classifier using the first two digit probabilities of single and double compressed images, which can be used to locate tampering present in the double compressed image. Comparison of the proposed algorithm with other state of the art techniques shows very promising results.

Fractal Video Coding Using Fast Normalized Covariance Based Similarity Measure

Fast normalized covariance based similarity measure for fractal video compression with quadtree partitioning is proposed in this paper. To increase the speed of fractal encoding, a simplified expression of covariance between range and overlapped domain blocks within a search window is implemented in frequency domain. All the covariance coefficients are normalized by using standard deviation of overlapped domain blocks and these are efficiently calculated in one computation by using two different approaches, namely, FFT based and sum table based. Results of these two approaches are compared and they are almost equal to each other in all aspects, except the memory requirement. Based on proposed simplified similarity measure, gray level transformation parameters are computationally modified and isometry transformations are performed using rotation/reflection properties of IFFT. Quadtree decompositions are used for the partitions of larger size of range block, that is, 16 × 16, which is based on target level of motion compensated prediction error. Experimental result shows that proposed method can increase the encoding speed and compression ratio by 66.49% and 9.58%, respectively, as compared to NHEXS method with increase in PSNR by 0.41 dB. Compared to H.264, proposed method can save 20% of compression time with marginal variation in PSNR and compression ratio.