Face segmentation in thumbnail images by data-adaptive convolutional segmentation networks
Author | Kiranyaz, Mustafa Serkan |
Author | Waris M.-A. |
Author | Ahmad I. |
Author | Hamila R. |
Author | Gabbouj M. |
Available date | 2022-04-26T12:31:23Z |
Publication Date | 2016 |
Publication Name | Proceedings - International Conference on Image Processing, ICIP |
Resource | Scopus |
Identifier | http://dx.doi.org/10.1109/ICIP.2016.7532770 |
Abstract | In this study we address the problem of face segmentation in thumbnail images. While there have been several approaches for face detection, none performs detection in such low resolution and segmentation with pixel accuracy. In this paper, we propose convolutional segmentation networks (CSNs) that can be trained to learn segmentation of human faces. Unlike the deep classifiers such as Convolutional Neural Network (CNNs), CSNs have the unique design solely for segmentation with minimal complexity. Furthermore, we propose a self-data organization (SDO) in order to create 'expert' CSNs each of which is specialized over a set of images with certain face characteristics. SDO is integrated with CSN training in an interleaved manner and it is the key for the learning with simple and compact networks rather than the deep ones. This is especially a desired property for the limited face datasets with challenging face variations and complexities. Evaluations on the benchmark dataset show that CSNs can achieve an elegant segmentation accuracy despite the limited training data size, thumbnail resolution and highly complex face modalities. |
Language | en |
Publisher | IEEE Computer Society |
Subject | Complex networks Convolution Face recognition Image processing Neural networks Benchmark datasets Convolutional neural network Data organization Face segmentation Face variations Limited training data Low resolution Segmentation accuracy Image segmentation |
Type | Conference Paper |
Pagination | 2306-2310 |
Volume Number | 2016-August |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Electrical Engineering [2611 items ]