Deep-feature encoding-based discriminative model for age-invariant face recognition
作者：
Highlights：
• A robust deep-feature encoding-based discriminative model for age-invariant face recognition is proposed.
• Our method learns high-level deep features using a pre-trained deep-CNN model (AlexNet), which are then encoded by learning a codebook, which converts each of the features into a discriminant S-dimensional codeword for image representation.
• A new feature-encoding framework based on locality constraint is proposed, which provides closed-form solutions in both encoding and codebook-updating process.
• Experimental results on three challenging face-aging datasets demonstrates the superiority of our proposed method.
摘要
•A robust deep-feature encoding-based discriminative model for age-invariant face recognition is proposed.•Our method learns high-level deep features using a pre-trained deep-CNN model (AlexNet), which are then encoded by learning a codebook, which converts each of the features into a discriminant S-dimensional codeword for image representation.•A new feature-encoding framework based on locality constraint is proposed, which provides closed-form solutions in both encoding and codebook-updating process.•Experimental results on three challenging face-aging datasets demonstrates the superiority of our proposed method.
论文关键词：Age-invariant face recognition,Canonical correlation analysis,Deep learning,Discriminative model,Feature encoding,Linear regression
论文评审过程：Received 6 October 2018, Revised 3 March 2019, Accepted 24 April 2019, Available online 25 April 2019, Version of Record 10 May 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.04.028
