Adaptive Deep Supervised Autoencoder Based Image Reconstruction for Face Recognition

Based on a special type of denoising autoencoder (DAE) and image reconstruction, we present a novel supervised deep learning framework for face recognition (FR). Unlike existing deep autoencoder which is unsupervised face recognition method, the proposed method takes class label information from tra...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Mathematical problems in engineering Ročník 2016; číslo 2016; s. 1 - 14
Hlavní autoři: Zhou, Jiliu, Li, Guoqi, Liu, Chang, Huang, Rongbing
Médium: Journal Article
Jazyk:angličtina
Vydáno: Cairo, Egypt Hindawi Publishing Corporation 01.01.2016
John Wiley & Sons, Inc
Témata:
Adaptive sampling
Deep learning
Face
Face recognition
Facial
Image reconstruction
Learning
Machine learning
Mathematical analysis
Methods
Neural networks
Noise
Occlusion
Reconstruction
Vectors (mathematics)
ISSN:1024-123X, 1563-5147
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Based on a special type of denoising autoencoder (DAE) and image reconstruction, we present a novel supervised deep learning framework for face recognition (FR). Unlike existing deep autoencoder which is unsupervised face recognition method, the proposed method takes class label information from training samples into account in the deep learning procedure and can automatically discover the underlying nonlinear manifold structures. Specifically, we define an Adaptive Deep Supervised Network Template (ADSNT) with the supervised autoencoder which is trained to extract characteristic features from corrupted/clean facial images and reconstruct the corresponding similar facial images. The reconstruction is realized by a so-called “bottleneck” neural network that learns to map face images into a low-dimensional vector and reconstruct the respective corresponding face images from the mapping vectors. Having trained the ADSNT, a new face image can then be recognized by comparing its reconstruction image with individual gallery images, respectively. Extensive experiments on three databases including AR, PubFig, and Extended Yale B demonstrate that the proposed method can significantly improve the accuracy of face recognition under enormous illumination, pose change, and a fraction of occlusion.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1024-123X
1563-5147
DOI:10.1155/2016/6795352