MISSING CHILD RECOGNITION SYSTEM USING DEEP LEARNING AND MULTI-CLASS SUPPORT VECTOR MACHINE

  • Unique Paper ID: 155314
  • Volume: 9
  • Issue: 1
  • PageNo: 570-574
  • Abstract:
  • This paper tells a pair of novel use of deep learning methodology which is employed for identifying the reported missing children from the images of multiple youngsters available, with the assistance of face recognition. the ultimate public can upload their images of suspicious children into an everyday portal with landmarks and remarks. The photo are automatically compared with the registered photos of the missing child from the repository. Cataloging of the input child photo is performed and photo with best match are designated from the database of missing children. For this, a deep learning model is trained to properly identify the missing child from the missing child image database provided, using the facial image uploaded by the final word public. The Convolutional Neural Network (CNN), is incredibly effective deep learning technique for image based applications is adopted here for face recognition. Face descriptors are extracted from the images employing 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 thus the kid recognition is completed by the trained SVM classifier. Choosing the foremost effective performing CNN model for face recognition, VGG-Face and proper training of it finally ends up during a very deep learning model invariant to noise, contrast, image pose and also the age of the children and earlier methods in face recognition based missing child identification.

Cite This Article

  • ISSN: 2349-6002
  • Volume: 9
  • Issue: 1
  • PageNo: 570-574

MISSING CHILD RECOGNITION SYSTEM USING DEEP LEARNING AND MULTI-CLASS SUPPORT VECTOR MACHINE

Related Articles