Recently, the biometric-based identifications are widely adopted for personnel identification. However, the unimodal recognition systems currently suffer from noisy data, biometric sensor data quality, spoofing attacks, unacceptable error rates and lack of distinctiveness of the biometric trait. These issues can be undertaken via multi-modal biometrics authentication system. This paper proposes a multi-modal framework to capture human skeletal features and facial features using imaging techniques. This modelling technique captures human joints with 3D depth data, to improve the system efficiency. This Biometric technique is used to recognize the known/unknown image from the trained images within short span of time. The proposed research has subdivided into three-folds. First, preprocessing the image, using the MinMax method which reduces the noise in data and enhance the image quality. Second, image features are extracted using Genetic method in combination with cuckoo search algorithm which is considered to be best optimization technique for image analysis. Third, the human recognition is attained via the Artificial Neural Network (ANN) which relies on back-propagation algorithm. The performance of the proposed method is evaluated based on the measure of different metric named as, true positive and negative rate, false positive and rejection rate, accuracy. The experimental results show that this new framework dramatically improves the system performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.