NDLI: Face recognition with compressed Fisher vector on multiscale convolutional features

Content Provider	IET Digital Library
Author	Deng, Weihong Wang, Hongjun
Abstract	Representations generated by Fisher vector (FV) have shown decent performances on many facial image datasets. However, discriminative information could be masked by noise if the authors directly sum all local responses with respect to the learned dictionary. Further, the high dimension of FV prohibits its practical use. To mitigate these problems, the authors propose a new framework called joint compressed Fisher vector (JCFV), which generate task-specific data representation by jointly encoding multiscale deep convolutional activations. Firstly, they feed into the deep network facial images cropped with cascaded sub-windows and resized into various scales. Next, they select discriminative convolutional features to form a dictionary. Then, they aggregate multiscale features with respect to the dictionary by calculating a re-weighted first-order statistics. JCFV halves the dimension of FV, and they could further compress the dimension with several combinations of subspace methods. They prove the effectiveness of their JCFV descriptor with comprehensive experiments on FERET, AR, LFW and FRGC 2.0 Experiment 4.
Starting Page	447
Ending Page	453
Page Count	7
ISSN	20474938
Volume Number	7
e-ISSN	20474946
Issue Number	Issue 5, Sep (2018)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-bmt/7/5
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-bmt.2017.0194
Journal	IET Biometrics
Publisher Date	2018-02-08
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Cascaded Sub-windows Computer Vision And Image Processing Technique Data Compression Deep Network Facial Image Discriminative Convolutional Feature Selection Discriminative Information Face Recognition Facial Image Datasets Feature Selection Image Recognition JCFV JCFV Descriptor Joint Compressed Fisher Vector Learned Dictionary Multiscale Convolutional Feature Multiscale Deep Convolutional Activation Encoding Multiscale Feature Aggregation Neural Computing Technique Neural Nets Re-weighted First-order Statistics Statistical Analysis Statistics SubSpace Method Task-specific Data Representation
Content Type	Text
Resource Type	Article
Subject	Signal Processing Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

Diversified Fisher kernel: encoding discrimination in Fisher features to compete deep neural models for visual classification task

Discriminative common feature subspace learning for age-invariant face recognition

Improved deep face identification with multi-class pairwise discriminant loss

Novel multi-scale deep residual attention network for facial expression recognition

Fusing HOG and convolutional neural network spatial–temporal features for video-based facial expression recognition

Learning content-adaptive feature pooling for facial depression recognition in videos

Improved softmax loss for deep learning-based face and expression recognition

Ear verification under uncontrolled conditions with convolutional neural networks

Recognition Oriented Facial Image Quality Assessment via Deep Convolutional Neural Network

Face recognition with compressed Fisher vector on multiscale convolutional features

Similar Documents

Diversified Fisher kernel: encoding discrimination in Fisher features to compete deep neural models for visual classification task

Discriminative common feature subspace learning for age-invariant face recognition

Improved deep face identification with multi-class pairwise discriminant loss

Novel multi-scale deep residual attention network for facial expression recognition

Fusing HOG and convolutional neural network spatial–temporal features for video-based facial expression recognition

Learning content-adaptive feature pooling for facial depression recognition in videos

Improved softmax loss for deep learning-based face and expression recognition

Ear verification under uncontrolled conditions with convolutional neural networks

Recognition Oriented Facial Image Quality Assessment via Deep Convolutional Neural Network

Face recognition with compressed Fisher vector on multiscale convolutional features