Ajou University repository

Age Estimation Using Trainable Gabor Wavelet Layers in A Convolutional Neural Network
Citations

SCOPUS

0

Citation Export

Publication Year
2019-09-01
Journal
Proceedings - International Conference on Image Processing, ICIP
Publisher
IEEE Computer Society
Citation
Proceedings - International Conference on Image Processing, ICIP, Vol.2019-September, pp.3626-3630
Keyword
Age estimationArtificial neural networksFeature extractionGabor filters
All Science Classification Codes (ASJC)
SoftwareComputer Vision and Pattern RecognitionSignal Processing
Abstract
In this paper, we propose a trainable Gabor wavelet (TGW) layer and cascade it with a convolutional neural network (CNN) for the age estimation. Unlike an existing method that uses fixed (hand-tuned) Gabor filters at the head of a CNN, we use Gabor wavelets that can be adapted for the given input as well as for the targeting task. This is enabled by (a) estimating hyperparameters of Gabor wavelets from the input and (b) using a 1 × 1 convolution layer for the selection of orientation parameter. The proposed TGW layers are trained with the standard gradient-descent method and can be easily incorporated with conventional CNNs in an end-to-end training manner. We conduct experiments on the Adience dataset and show that the proposed network outperforms the baseline CNN without TGW layers and efficiently used trainable parameters than ordinary CNN based methods.
ISSN
1522-4880
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36440
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85076816566&origin=inward
DOI
https://doi.org/10.1109/icip.2019.8803442
Type
Conference
Funding
This work was supported in part by the SNU-Hojeon Garment Smart Factory Research Center funded by Hojeon Ltd., and in part by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No. 1711075689, Decentralised cloud technologies for edge/IoT integration in support of AI applications)
Show full item record

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

 KOO, HYUNG IL Image
KOO, HYUNG IL구형일
Department of Electrical and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.