Fisher vector encoded deep convolutional features for unconstrained face verification
Authors:
- 19 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 2981-2985
Abstract
We present a method to combine the Fisher vector representation and the Deep Convolutional Neural Network (DCNN) features to generate a rerpesentation, called the Fisher vector encoded DCNN (FV-DCNN) features, for unconstrained face verification. One of the key features of our method is that spatial and appearance information are simultaneously processed when learning the Gaussian mixture model to encode the DCNN features. Evaluations on two challenging verification datasets show that the proposed FV-DCNN method is able to capture the salient local features and also performs well when compared to many state-of-the-art face verification methods.Keywords
This publication has 16 references indexed in Scilit:
- Frontal to profile face verification in the wild2016
- Unconstrained face verification using fisher vectors computed from frontalized faces2015
- A Compact and Discriminative Face Track Descriptor2014
- DeepFace: Closing the Gap to Human-Level Performance in Face Verification2014
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Similarity Metric Learning for Face Recognition2013
- Fisher Vector Faces in the Wild2013
- Aggregating local descriptors into a compact image representation2010
- Histogram of Gabor Phase Patterns (HGPP): A Novel Object Representation Approach for Face RecognitionIEEE Transactions on Image Processing, 2006
- Face Description with Local Binary Patterns: Application to Face RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006