期刊名称：International Journal of Advances in Engineering and Management
电子版ISSN：2395-5252
出版年度：2021
卷号：3
期号：7
页码：3092-3100
DOI：10.35629/5252-030729082912
语种：English
出版社：IJAEM JOURNAL
摘要：In India countless number of children are reported missing every year. Among the missing child cases a large percentage of children remain unreached. Deep learning technique is used foridentifying the reported missing child from the photos of multitude of children available, with the help of face recognition. The people can upload photographs of suspicious child into a common portal with landmarks and remarks. The photo will be automatically compared with the registered photos of the missing child from the repository. Classification of the input child image is done and photo with best match will be selected from the database of missing children. So, a deep learning model is trained to correctly identify the missing child from the database provided, using the facial image uploaded by the public. Convolutional Neural Network, 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-defined CNN model VGG-Face deep architecture. Compared with 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. Choosing best performing CNN model of the face recognition, VGG-Face and proper training of it results in a deep learning model invariant of noise, illumination, contrast, occlusion, image pose and age of child and it outperforms earlier methods in face recognition based on missing child identification technique. The classification performance achieved for achild identification system is 99.41%. It has been evaluated on 43 Child cases.
关键词：Missing child identification;face recognition;deep learning;CNN;VGG-Face;Multi class SVM. I
