A deep learning framework for face verification without alignment

Fan, Zhongkui; Guan, Yuanyuan

doi:10.1007/s11554-020-01037-z

Cited by 6 publications

(2 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main goal of HHAC is to predict the human head attributes of a given image, including gender, age group, smiling, attraction, etc. During recent years, HHAC has attracted significant attention due to its widespread applications, including object recognition [1,2], face recognition [3,4], face verification [5,6], face retrieval [7], image retrieval [8], image search [9]and recommendation systems [10]. However, HHAC remains a challenging problem in practice because of the large variability of human head appearances in illumination, pose, expression, etc.…”

Section: Introductionmentioning

confidence: 99%

Multi-Output Convolutional Neural Network for Automatic Human Head Attributes Classification

2022

IJIES

View full text Add to dashboard Cite

Human head attribute classification (HHAC) is a fundamental and substantial research domain in pattern recognition and computer vision. However, recent HHAC networks do not consider the correlation of common characteristics among the attributes over different regions of the human head. To address the above problem, this study proposes a multi-output convolutional neural network to jointly learn the features of human head attributes with common characteristics. The proposed network contains two convolutional blocks and five output layers, where each output layer learns to predict a specific group of human head attributes. In order to properly learn the correlation among the human head attributes, this study divides these attributes into five groups: hair, face, style, accessories, and appearance. Extensive experiments showed that the proposed network obtained an average classification accuracy of 95.29% and 97.93% on the challenging CelebA and LFWA datasets, respectively. Thus, the proposed network is approximately 2% and 10% superior to the closest competitor (i.e., PS-MCNN) on both datasets. In addition, the proposed network achieved higher classification accuracy compared to the existing networks almost in all human head attributes. That findings demonstrate the effectiveness of the proposed network and the attributes grouping method in learning the correlations among human head attributes correctly.

show abstract

Section: Introductionmentioning

confidence: 99%

Multi-Output Convolutional Neural Network for Automatic Human Head Attributes Classification

2022

IJIES

View full text Add to dashboard Cite

show abstract

“…The first theme of this special issue focuses on "Theories, models, and algorithms". Fan and Guan [1] have developed a deep face verification framework based on SIFT (scale invariant feature transform) and CNN (convolutional neural network) methods. Their experimental results show how the proposed model outperformed some state-of-theart methods on the LFW (Labeled Faces in the Wild) and YTB (YouTube) datasets.…”

mentioning

confidence: 99%