AADHAR ENABLED BIOMETRIC PORTAL FOR MISSING IDENTITIES
Snehal Patil1, Arpita Ghogare2, Khushbu Bendale3 , Bhavesh Gosavi4
Department Of Computer Engineering, Shramsadhana Bombay Trust, College of Engineering & Technology, Jalgaon.
-------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - In India a countless number of children are reported missing every year. Among the missing child cases a large percentage of children remain untraced. Face recognition is a biometric-based technology that maps an individual’s facial features mathematically and stores the data as a face print. It employs Machine Learning on the image and generates a feature vector that maps an object with an array of numbers. The main idea of this work is to identify the reported missing child from the Aadhar database, extract his/her details and notify the respective authorities. The police authorities can upload photographs of a suspicious child who does not know proper/adequate information about their address/parents. The photo will be automatically compared with the Aadhar dataset repository. Classification of the input child image is performed and photo with best match will be selected. The Aadhar enabled data of missing person like photo, age, address, finger prints may be circulated to all state and district level police authorities through the dedicated portal with limited access to the authorized authorities only. This would help the Police authorities to find the missing children in their localities with authenticated and integrated information system.
Compared with normal deep learning applications, our algorithm uses convolution network only as a high-level feature extractor and the child recognition is done by the trained KNN classifier. This system will reduce human trafficking issues and ensure the security in our society. It will link the authorities making their process simpler and fast. The analysis and implementation result shows that the project is feasible and implementation is highly recommended by the researchers.s.
Key words: MTCNN, Keras, Matplotlib, face recognition, Aadhar Biometrics.