Debashis Ganguly

A Secure Scheme for Image Transformation

The dynamic growth in the field of Information communication has hiked the ease of Information transmission. But this type of real advancement in other sense has explored so many possibilities of information being snooped, at the time of communication in between the sender and the intended receiver. So, day by day Information Security is becoming an inseparable part of Computing and Communication. Various tools are available in order to address those issues and in them Steganography plays a significant role. In this paper, a heuristic approach for Information hiding in the form of multimedia objects or text using Steganography is proposed keeping in mind two considerations - Size and degree of security. Here, the Information is hidden behind an image in the form of an encoded matrix which is obtained from the bit matrix of the embedded object.

A Novel Approach for Determination of Optimal Number of Cluster

Image clustering and categorization is a means for high-level description of image content. In the field of content-based image retrieval (CBIR), the analysis of gray scale images has got very much importance because of its immense application starting from satellite images to medical images. But the analysis of an image with such number of gray shades becomes very complex, so, for simplicity we cluster the image into a lesser number of gray levels. Using K-Means clustering algorithm we can cluster an image to obtain segments. The main disadvantage of the k-means algorithm is that the number of clusters, K, must be supplied as a parameter. Again, this method does not specify the optimal cluster number. In this paper, we have provided a mathematical approach to determine the optimal cluster number of a clustered grayscale images. A simple index, based on the intra-cluster and inter-cluster distance measures has been proposed in this paper, which allows the number of clusters to be determined automatically.

A Novel Approach for Edge Detection of Images

Edge detection is a problem of fundamental importance in image analysis. Many approaches for edge detection have already revealed more are waiting to be. But edge detection using K-means algorithm is the most heuristic and unique approach. In this paper, we have proposed an algorithmic technique to detect the edge of any kind of true gray scale images considering the artificial features of the image as the feature set which is fed to K-Means algorithm for clustering the image and there to detect clearly the edges of the objects present in the considered image. The artificial features, which we have considered here, are mean, standard deviation, entropy and busyness of pixel intensity values.

A Secured Technique for Image Data Hiding

In this paper, a new technique for hiding the data of images has been proposed. This method is invented to hide an image file entirely with in another image file keeping two considerations in mind which are Size and Degree of Security. At the source, the image which is to be hidden (target image) is encoded at the end of another image (cover image). Double layer security of the hidden image can be achieved (over the untrusted network) by; firstly, the starting point of encoding the image data is depended on the size of the images and it is stored within the encoded image at the end of its header information as a cipher text.; secondly, the target image is hidden behind the cover image by following our encrypted image hiding technique.

Medical Imaging: A Review

The rapid progress of medical science and the invention of various medicines have benefited mankind and the whole civilization. Modern science also has been doing wonders in the surgical field. But, the proper and correct diagnosis of diseases is the primary necessity before the treatment. The more sophisticate the bio-instruments are, better diagnosis will be possible. The medical images plays an important role in clinical diagnosis and therapy of doctor and teaching and researching etc. Medical imaging is often thought of as a way to represent anatomical structures of the body with the help of X-ray computed tomography and magnetic resonance imaging. But often it is more useful for physiologic function rather than anatomy. With the growth of computer and image technology medical imaging has greatly influenced medical field. As the quality of medical imaging affects diagnosis the medical image processing has become a hotspot and the clinical applications wanting to store and retrieve images for future purpose needs some convenient process to store those images in details. This paper is a tutorial review of the medical image processing and repository techniques appeared in the literature.

Detecting Sexually Provocative Images

While the abundance of visual content available on the Internet, and the easy access to such content by all users allows us to find relevant content quickly, it also poses challenges. For example, if a parent wants to restrict the visual content which their child can see, this content needs to either be automatically tagged as offensive or not, or a computer vision algorithm needs to be trained to detect offensive content. One type of potentially offensive content is sexually explicit or provocative imagery. An image may be sexually provocative if it portrays nudity, but the sexual innuendo could also be contained in the body posture or facial expression of the human subject shown in the photo. Existing methods simply analyze skin exposure, but fail to capture the hidden intent behind images. Thus, they are unable to capture several important ways in which an image might be sexually provocative, hence offensive to children. We propose to address this problem by extracting a unified feature descriptor constituting the percentage of skin exposure, the body posture of the human in the image, and his/her gestures and facial expressions. We learn to predict these cues, then train a hierarchical model which combines them. We show in experiments that this model more accurately detects sexual innuendos behind images.

Refine Crude Corpus for Opinion Mining

This paper is meant for a heuristic approach for the refinements of corpus based on regular expressions and its possible applications in the field of Opinion Mining. Corpus which is the plural form of ‘corpora’ is nothing but the collection of linguistic data. And here the proposed work is based on a corpus of reviews; more specifically product reviews. The reviews are in the html files which are easily available in popular review sites like Cnet.com. The revolution in information and technologies has given a new era in the development of language industries. The versatility in technological development, along with the translations available in different languages has lead to use of this corpus for specific machine learning mechanism as well as various automatic translation applications. But the prime objective of researchers as well as the naive users is to give a fast developing technique of machine learning systems that should be both exact and effective. Most of the time it becomes a very tedious job to create exact dataset for the work due to the crisis of accurate corpus regarding respective research work. And that is why; we have proposed an algorithm for creating a corpus for opinion mining research field.

The Effect of Asymmetric Performance on Asynchronous Task Based Runtimes

It is generally accepted that future supercomputing workloads will consist of application compositions made up of coupled simulations as well as in-situ analytics. While these components have commonly been deployed using a space-shared configuration to minimize cross-workload interference, it is likely that not all the workload components will require the full processing capacity of the CPU cores they are running on. For instance, an analytics workload often does not need to run continuously and is not generally considered to have the same priority as simulation codes. In a space-shared configuration, this arrangement would lead to wasted resources due to periodically idle CPUs, which are generally unusable by traditional bulk synchronous parallel (BSP) applications. As a result, many have started to reconsider task based runtimes owing to their ability to dynamically utilize available CPU resources. While the dynamic behavior of task-based runtimes had historically been targeted at application induced load imbalances, the same basic situation arises due to the asymmetric performance resulting from time sharing a CPU with other workloads. Many have assumed that task based runtimes would be able to adapt easily to these new environments without significant modifications. In this paper, we present a preliminary set of experiments that measured how well asynchronous task-based runtimes are able to respond to load imbalances caused by the asymmetric performance of time shared CPUs. Our work focuses on a set of experiments using benchmarks running on both Charm++ and HPX-5 in the presence of a competing workload. The results show that while these runtimes are better suited at handling the scenarios than traditional runtimes, they are not yet capable of effectively addressing anything other than a fairly minimal level of CPU contention.

Network and Application Security: Fundamentals and Practices

To deal with security issues effectively, it is usually not sufficient to have knowledge of theories. Practical experience in dealing with these issues is essential. This book discusses the basic theories, and also helps develop a practical outlook on the matter in a short and intriguing, manner. The book is not intended as a textbook, therefore does not include minute and complex description of every theoretical aspect. It provides readers with basic concepts and an awareness of industry standards and best practices. Thus the book will be helpful for both the beginners and industry practitioners. If you are confused and have queries involving How do I...? like, How do I know which cryptographic approach to be followed?, How do I set a firewall?, How do I secure specific network layers or application?, How do I fight against application level attacks?, How should I code securely? and more; then this book will act as your pathfinder.

A Novel Approach for Refinement of Corpus in the Field of Opinion Mining

In this paper, we have provided a heuristic approach for the refinements of corpus based on regular expressions and its possible applications in the field of Opinion Mining. The proposed work is based on a corpus of reviews. The crude corpus is the raw html files containing reviews. This html file is refined further for the ease of our work so that we can get only the required part from that page. The ultimate output yields the xml files which will precisely store the important parts of the review pages from that refined html page. And that is going to be fed to the further process of language processing for machine learning process in the field of Opinion Mining.