Search

The purpose of the research is to validate the potential of Yogic Hand Gestures in a well-formed human-computer interface with a real-time image sequence taken on a video recording device to trace the potential subject region(PSR) spontaneously, essentially, the hand region with the help of skin detection algorithm, and detect, and perceive hand gestures for human-computer interaction. To detect skin, we use skin colour detection and softening to remove extra background information from the image, and then use background subtraction to detect the PSR. Moreover, to avoid the background information, we use the kernelised correlation filters (KCF) algorithm to track the detected PSR. The image size of the PSR is then resized to 50px * 50px and then fed into the deep convolutional neural network (CNN) to identify eight yogic hand gestures. The deep CNN architecture developed in this study that is a modified VGGNet. The above process of tracking and recognition is repeated with a ranking algorithm to produce a real-time impression, and the system’s execution continues until the hand leaves the camera range. While recognising the gesture primarily, it adds the top-ranked image captures to add into the sample pool for future training, the training data set reaches a recognition rate of 99.00%, and the test data set has a recognition rate of 95.89%, which represents the feasibility of the practical application. The implemented proof of concept and the custom yogic gesture dataset, namely the YoGiR-1 dataset, are availed on request.

Over the last few decades, a number of researchers have proposed a variety of hand gesture recognition techniques. The paper presents a new approach for hand recognition. The preprocessing is done by applying Gaussian scale space and to enhance the feature average gray intensity has been found. The kirsch’s convolution mask is computed for edge map and has collaborated with result obtained by combining different Bit Planes. The aim of the proposed descriptor is to illuminate the noise and unwanted data and make it invariant to scale rotation and illumination changes. The local edge computation gives the result which is invariant to scale rotation but it does not tend to eliminate noise. Bit plane encoding used the binary form of image and reduce the data used to describe a series of sample values. The bit plane slicing is done through lossless binary compression technique and the bits are recombined to build the feature vector. The aim is to make the hand recognition result under rotation, illumination and roughness effective. In this paper, we summarized the proposed descriptor and compares it with other methods found in literature for recognition of the same data.

Hand gesture recognition system has a good attention now days because of easy interaction between human and machine. The focus of developing hand gesture is to create a better communication between human and computer for conveying information. This paper presents a survey on recent technology of hand gesture recognition both static and dynamic. It shows all method that was used for hand gesture recognition in different research paper.

Defect is an important issue in medical image; we have investigated the defects in medical images. The missing data in an image is computed through error detection mechanism. Defect is creating a major problem in the medical science. When a patient with disease has any internal infections like cancer, kidney stone and external infections like fungal infection, skin disease, etc., patient follows the doctor’s advice. Doctor checks his patient and his disease and he suggests many types of tests like X-ray. Theses tests are done by patients, but some defects are caused in the machine internal or external, which makes the result improper, hence the problem cannot be identified by the doctorclearly. In this paper calculate the percentage of defected image with healthy image and comparison of healthy image.

Data mining and machine learning concepts play a vital role in dealing with large number of datasets. Various algorithms embedded within these concepts provide a wide array of mechanisms to classify the data into its specific classes. Least square support vector machine (LS-SVM) is a machine learning approach used to classify the data. Although it works better in comparison to other algorithms, the various changes sustained on each run of the program execution in its parametric values makes it quite resilient enough towards its performance. Hence, this paper focuses on the enhancement of the performance level of traditional LS-SVM. In order to do so, traditional LS-SVM is integrated together with simplified particle swarm optimization technique (PSO). PSO, a swarm intelligence based, optimization approach is exploited to optimize the kernel parametric values of LS-SVM so that it not only improves its classification performance but significantly also improve the time execution of the program being run. The proposed method is exploited on the phishing dataset and experimental results are evaluated against the results of other algorithms.

Defect is an important issue in medical image the computational technique adapt everywhere in the real world. Most of their adoption is based on analysis and comparative study of novel adventures. The missing data in an image is computed through error detection mechanism a defect is creating a major problem in the medical science. The decision to classify the actual problem into a human are defected through the existence of minor defect in to their X-RAY, MRI and CT scan report. Due to this defect a patient didn't advised to take a genuine medicine to improve their disease. The experimental data obtain as a result of survey clarify the importance of image defect to their removal process. Therefore, we are focusing the impact of image defect into real world.

In Last one decade researchers are focus on cloud computing presenting many novel approach for improving storage spaces in digital world. In this paper, we introduce architecture and algorithms that can be implemented to facilitate well-equipped infrastructure within cloud environment for load balancing and resource allocation. This architecture is specially developed for virtual storage drive over cloud. This architecture supports a number of end users, which are authenticating to send requests to the server. This request may demand some resources for its processing, thus, here comes the concept of resource allocation where it is required to allocate and schedule the available resources to process the request of the client. A numerous algorithms have been introduced here for easy configuration for the proposed architecture. The conclusion of this research paper is to provide such a cloud framework which can be implemented for efficient resource allocation and load balancing for multiple clouds.