DETERMINATION OF BIOMETRICAL TRAITS ANAMOLY AND PRODODIC FEATURES THROUGH HUMAN GAIT IMAGES WITH CALIBRATED FEATURES USING HIGH END COMPUTING TECHNIQUES
Loading...
Date
item.page.authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Human-Gait Analysis comes under a Biometrical study, which is a very important research problem with respect to security and recognition of medical problem for diagnosis. So far most of the Biometrical research work has been carried out using template-based approach for the recognition of medical problem. Determination of biometrical traits anomaly and prosodic features (DBTPF) is one of the biometrical research problem which can be applied for medical diagnosis and security. As per the literature, most of the work has been carried out for the detection of various problems like: short and long foot problems, ankle and knee angle variations, detection of walking speed after hitting an object, recognition of gender, recovery type of problems using human-gait analysis and so on. Most the work have been carried out by the different researchers in the field of human-gait analysis using model-based and template based approach. The methods that have been applied so far are not based on high-end computing techniques. Very little amount of work has been carried out with knowledge-based or model-based mechanism using soft-computing tools like Artificial Neural Network (ANN), Fuzzy Set Rules, Genetic Algorithms (GA), and utility computing with symbolic rules. The present research work has been carried out by using high-end computing techniques. High-end computing techniques involve combination of soft-computing, symbolic computing. Soft-computing techniques involve artificial neural networks, fuzzy set theory and genetic algorithms. Symbolic computing involves special data type called symbolic objects. Such computing allows researchers to perform mathematical operations without calculating numeric valves. Earlier little contributions have been made for the recognition of foot abnormality through human-gait images using soft-computing tools. In the present work two biometrical traits has been considered, they are human-gait and human-speech.