Published Paper Details:

It is estimated that a child goes missing in India every eight minutes. This paper presents a novel by using a deep learning methodology for identifying the missing person. The public can upload photographs of a suspicious child in our portal by their landmarks and remarks. The photo will be automatically compared with registered photos of missing child. Classification of input child image and photo with the best match will be selected from the database which contains missing children photos. The Convolutional Neural Network (CNN), a highly effective deep learning technique for image-based applications is adopted here for face recognition. Face descriptors are extracted from the images using a pre-trained CNN model VGG-Face deep architecture. 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 SVM classifier.