An approach to partial occlusion using deep metric learning

Chethana Hadya Thammaiah, Trisiladevi Chandrakant Nagavi


The human face can be used as an identification and authentication tool in biometric system. Face recognition in forensics is a challenging task due to the presence of partial occlusion features like wearing hat, sunglasses, scarf and beard. In forensics, criminal identification having partial occlusion features is a most difficult task to perform. In this paper, a combination of Histogram of Gradients with Euclidean distance is proposed. Deep Metric Learning is the process of measuring the similarity between the samples using optimal distance metric for learning tasks. In proposed system, Deep metric learning technique like Histogram of Gradients is used to generate a 128d real feature vector. Euclidean distance is then applied between the feature vectors and a tolerance threshold is set to decide whether it is a match or mismatch. Experiments are carried out on Disguised Faces In The Wild (DFW) dataset collected from IIIT Delhi which consists of 1000 subjects in which 600 subjects were used for testing and remaining 400 subjects were used for training purpose. The proposed system provides a recognition accuracy of 90% and it outperforms compared with other existing methods.


Deep metric learning; Disguised facesin the wild; Euclidean distance; Face recognition; Histogram of Gradients



  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

View IJICT Stats