Goutam Sanyal

Hand Gesture Recognition Systems: A Survey

Gesture was the first mode of communication for the primitive cave men. Later on human civilization has developed the verbal communication very well. But still nonverbal communication has not lost its weightage. Such non – verbal communication are being used not only for the physically challenged people, but also for different applications in diversified areas, such as aviation, surveying, music direction etc. It is the best method to interact with the computer without using other peripheral devices, such as keyboard, mouse. Researchers around the world are actively engaged in development of robust and efficient gesture recognition system, more specially, hand gesture recognition system for various applications. The major steps associated with the hand gesture recognition system are; data acquisition, gesture modeling, feature extraction and hand gesture recognition. There are several sub-steps and methodologies associated with the above steps. Different researchers have followed different algorithm or sometimes have devised their own algorithm. The current research work reviews the work carried out in last twenty years and a brief comparison has been performed to analyze the difficulties encountered by these systems, as well as the limitation. Finally the desired characteristics of a robust and efficient hand gesture recognition system have been described. General Terms Hand gesture recognition, comparison

A comparative survey of Symmetric and Asymmetric Key Cryptography

Network security is an important aspect of information sharing. Attempts have been made to remove various insecurities over internet. For this, many technological implementations and security policies have been developed. The amount of data, transferred, is not a factor. The basic factor is, how much security, the channel provides while transmitting data. Cryptography is one such technique, which allows secure data transmission without losing its confidentiality and integrity. Based on the key distribution, cryptography is further classified into two major types-Symmetric Key Cryptography and Asymmetric Key Cryptography. In this paper, we have surveyed the traditional algorithms, along with the proposed algorithms based on their pros and cons, related to Symmetric and Asymmetric Key Cryptography. We have also compared the importance of both these cryptographic techniques. The proposed algorithms proved to be highly efficient in their respective grounds but there are certain areas that remained open, related to these algorithms, and have not yet been thoroughly discussed. This paper also presents an appropriate future scope related to these open fields.

Survey and analysis of optimal scheduling strategies in cloud environment

Cloud technologies promise to change the way organizations tackle complex computational problems. Here millions of user share cloud resources by submitting their computing task to the cloud system. So Scheduling these millions of task is a challenge to cloud computing environment. In this paper we have proposed a methodology by using assignment to assign these jobs to the suitable resources so as to minimize the whole completion time. The cost matrix is generated by using credit of a task to be assigned to a particular resource. The task having more credit carries more chance to assign to the best fitted resource. The proposed method has been established in homogeneous cloud environment.

An efficient face recognition approach using PCA and minimum distance classifier

Facial expressions convey non-verbal cues, which play an important role in interpersonal relations. Automatic recognition of human face based on facial expression can be an important component of natural human-machine interface. It may also be used in behavioral science. Although human being can recognize the face practically without any effort, but reliable face recognition by machine is a challenge. This paper presents a new approach for recognizing the face of a person considering the expression of the same human face at different instances of time. This methodology is developed by combining principle component analysis (PCA) for feature extraction and minimum distance classifier (MDC) for classification. Experiment is done on AT&T dataset and the recognition rate achieves to 96.7% for different facial expressions.

An enhancement of security of image using permutation of RGB-components

Data bits from textual message are encrypted through key to some suitable nonlinear pixel and bit positions about the entire image. As a result, we get a watermarked image. After that we have formed three different image shares using any two components of R, G and B of entire watermarked image. The key is also divided into three different logical blocks by digits. By combining any two blocks of key we have formed key shares and have assigned to image shares. Out of those three shares, only addition of any two is able to make the full image or key. At the decryption end through appropriate arrangement of shares of key and image, make possible to retrieve hidden data bits from watermarked image and reform into its original content.

Development of Edge Detection Technique for Images Using Adaptive Thresholding

Edge detection is a terminology in image processing and computer vision, particularly in the areas of feature detection and feature extraction, to refer to algorithms which aim at identifying points in a digital image at which the image brightness changes sharply or more formally has discontinuities. In this paper a simple edge detection technique is performed by convoluting the image using a five order mask and then Selecting a threshold from taking the sum of mean value and the standard deviation of the gradient image within a 3 X 3 window. In Canny edge detection a gauss kernel is used for smoothing the image in order to eliminate the noise. But in our algorithm a single mask perform the noise smoothing as well as finding the edge strength.

Enhanced Position Power First Mapping (PPFM) based image steganography

Abstract The booming technological trends of the global world bring along with it several disincentives, surmounting which has become a challenging task. The realm of modern communication, in order to shun the attention of any third-party demands certain measure that affirms immense security along with the confidentiality of information. Steganography ratifies the stated fact. With reference to this context, we propose a new image steganographic approach that competently masks the secret information bits without enticing the hackers and crackers. A two-level security mechanism in the form of two-way scrambling has been incorporated in this approach. Arnold transform is implemented on the cover in the very first step, which is succeeded by a new scrambling mechanism based on a unique technique of permutation. The aforesaid steps dexterously encrypt the cover image, thereby ensuing a two-level security in the steganographic method. The embedding mechanism of Position Power First Mapping (PPFM) is next effectuated. Incorporation of the inverse permutation-based scrambling method followed by the technique of inverse Arnold transform consummates the whole procedure and spawns an imperceptible stego. The resultant hefty embedding capacity is the prime advantage here, along with the clear resemblance of the cover and stego formed.

Selection of User-Dependent Cohorts Using Bezier Curve for Person Identification

The traditional biometric systems can be strengthened further with exploiting the concept of cohort selection to achieve the high demands of the organizations for a robust automated person identification system. To accomplish this task the researchers are being motivated towards developing robust biometric systems using cohort selection. This paper proposes a novel user-dependent cohort selection method using Bezier curve. It makes use of invariant SIFT descriptor to generate matching pair points between a pair of face images. Further for each subject, considering all the imposter scores as control points, a Bezier curve of degree n is plotted by applying De Casteljau algorithm. As long as the imposter scores represent the control points in the curve, a cohort subset is formed by considering the points determined to be far from the Bezier curve. In order to obtain the normalized cohort scores, T-norm cohort normalization technique is applied. The normalized scores are then used in recognition. The experiment is conducted on FEI face database. This novel cohort selection method achieves superior performance that validates its efficiency.

A DWT Based Steganographic Method Using Prime First Mapping (PFM)

Steganography takes up a distinctively extraordinary space in facilitating secret communication in this technology aided world. It differs from Cryptography in such a way that the outputs attained after various steganographic operations are apparently kept hidden. The output, in cryptography, appears to be visibly encrypted. In this context, a new concept in the steganographic horizon is proposed, where the confidential information is hidden in such a fashion, that it does not captivate any bit of suspicion of the hackers. And even if it does, it is almost impossible to crack the security. To begin with, we have applied 2D Haar Discrete Wavelet Transform on the chosen cover or carrier image. We are hence able to figure out all of its coefficient matrices. This step is followed by applying our proposed Prime First Mapping (PFM) approach for embedding purpose where unique concepts based on the prime and non-prime location values of the existing pixels have been used. The results obtained clearly prove the novelty of this approach, in terms of all the evaluated benchmark techniques. The embedding capacity is eminently high and the moderate PSNR value shows the imperceptibility of the stego-image. The similarity measure also substantiates its efficiency in preserving the image quality.

BCP-BCS: Best-Fit Cascaded Matching Paradigm with Cohort Selection Using Bezier Curve for Individual Recognition

The concept of cohort selection has been emerged as a very interesting and potential topic for ongoing research in biometrics. It has the capability to provide the traditional biometric systems to having a higher performance rate with lesser complexity and cost. This paper describes a novel matching technique incorporated with Bezier curve cohort selection. The Best-Fit matching with dynamic threshold has been proposed here to reduce the number of false match. This algorithm is applied for matching of Speeded Up Robust Feature (SURF) points detected on face images to find out the matching score between two faces. After that, Bezier curve is applied as a cohort selection technique. All the cohort scores are plotted in a 2D plane as if these are the control points of a Bezier curve and then a Bezier curve of degree n is plotted on the same plane using De Casteljau algorithm where number of control point is \(n+1\). A template contains more discriminative features more it is having distance from the curve. All the templates having score point far from the curve are included into the account of cohort subset. For each enrolled user a specific cohort subset is determined. As long as the subset is formed, T-norm cohort score normalization technique is applied to obtain the normalized scores which are further used for person identification and verification. Experiments are conducted on FEI face database and results are showing dominance over the non-cohort system.