Share Email Print

Proceedings Paper

Hybrid feature fusion for person recognition in photo albums
Author(s): Sheng Li; Likun Huang; Wei Zhang; Bing Tang
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

The current work on person recognition in photo albums mainly utilize pure deep convolutional features to describe a person’s image. However, we observe that the hand-crafted features are usually able to provide complementary information and are more stable for identity recognition under some challenging circumstances. In view of this, we propose a novel hybrid method for person recognition in photo albums. In the proposed method, both the hand-crafted features and deep convolutional features are extracted from every person’s image. These multi-modality features are then fused by a weighted average method and classified by a pre-trained SVM in the recognition procedure. The experimental results demonstrates the effectiveness of the proposed method.

Paper Details

Date Published: 14 February 2020
PDF: 6 pages
Proc. SPIE 11430, MIPPR 2019: Pattern Recognition and Computer Vision, 114300R (14 February 2020); doi: 10.1117/12.2538184
Show Author Affiliations
Sheng Li, Wuhan Institute of Technology (China)
Likun Huang, Wuhan Institute of Technology (China)
Wei Zhang, Wuhan Institute of Technology (China)
Bing Tang, Wuhan Institute of Technology (China)

Published in SPIE Proceedings Vol. 11430:
MIPPR 2019: Pattern Recognition and Computer Vision
Nong Sang; Jayaram K. Udupa; Yuehuan Wang; Zhenbing Liu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?