Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features
Weakly supervised learning has outstanding ability to solve classification tasks, and multiformity middle-level visual features provide more abundant discriminant information for meaningful regions. In this paper, we study the integration of the middle-level visual features including homogeneity of...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9148596/ |
id |
doaj-30a6f03bb4a0423facc7acdf947bfab2 |
---|---|
record_format |
Article |
spelling |
doaj-30a6f03bb4a0423facc7acdf947bfab22021-03-30T04:18:57ZengIEEEIEEE Access2169-35362020-01-01813765813767110.1109/ACCESS.2020.30120399148596Image Segmentation Based on Weakly Supervised MKL on Mixed Visual FeaturesHaifeng Sima0https://orcid.org/0000-0002-2049-3637Junding Sun1https://orcid.org/0000-0001-7349-0248Minmin Du2https://orcid.org/0000-0002-8448-3737Jing Wang3https://orcid.org/0000-0002-3288-2111Chaosheng Tang4https://orcid.org/0000-0001-6923-855XDepartment of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaDepartment of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaDepartment of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaDepartment of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaDepartment of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, ChinaWeakly supervised learning has outstanding ability to solve classification tasks, and multiformity middle-level visual features provide more abundant discriminant information for meaningful regions. In this paper, we study the integration of the middle-level visual features including homogeneity of superpixels, region objectness and texture map for segmentation. Then, three kernels are exploited to map visual features to high-dimensional space. A few labeled pixels are chosen for training support vector machines(SVMs) in a single image with hybrid kernels. On this basis, the remaining pixels are labeled with classified results of SVMs and refined the segmentation results by merging pre-segments of mean-shift. We perform sufficient experiments on Berkeley datasets and compared them with several excellent segmentation algorithms. Extensive experimental results of the proposed method show superior segmentation performance and expanded tests on PASCAL VOC datasets further validate the effectiveness of the algorithm.https://ieeexplore.ieee.org/document/9148596/Image segmentationMKLmixed visual features |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Haifeng Sima Junding Sun Minmin Du Jing Wang Chaosheng Tang |
spellingShingle |
Haifeng Sima Junding Sun Minmin Du Jing Wang Chaosheng Tang Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features IEEE Access Image segmentation MKL mixed visual features |
author_facet |
Haifeng Sima Junding Sun Minmin Du Jing Wang Chaosheng Tang |
author_sort |
Haifeng Sima |
title |
Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features |
title_short |
Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features |
title_full |
Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features |
title_fullStr |
Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features |
title_full_unstemmed |
Image Segmentation Based on Weakly Supervised MKL on Mixed Visual Features |
title_sort |
image segmentation based on weakly supervised mkl on mixed visual features |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Weakly supervised learning has outstanding ability to solve classification tasks, and multiformity middle-level visual features provide more abundant discriminant information for meaningful regions. In this paper, we study the integration of the middle-level visual features including homogeneity of superpixels, region objectness and texture map for segmentation. Then, three kernels are exploited to map visual features to high-dimensional space. A few labeled pixels are chosen for training support vector machines(SVMs) in a single image with hybrid kernels. On this basis, the remaining pixels are labeled with classified results of SVMs and refined the segmentation results by merging pre-segments of mean-shift. We perform sufficient experiments on Berkeley datasets and compared them with several excellent segmentation algorithms. Extensive experimental results of the proposed method show superior segmentation performance and expanded tests on PASCAL VOC datasets further validate the effectiveness of the algorithm. |
topic |
Image segmentation MKL mixed visual features |
url |
https://ieeexplore.ieee.org/document/9148596/ |
work_keys_str_mv |
AT haifengsima imagesegmentationbasedonweaklysupervisedmklonmixedvisualfeatures AT jundingsun imagesegmentationbasedonweaklysupervisedmklonmixedvisualfeatures AT minmindu imagesegmentationbasedonweaklysupervisedmklonmixedvisualfeatures AT jingwang imagesegmentationbasedonweaklysupervisedmklonmixedvisualfeatures AT chaoshengtang imagesegmentationbasedonweaklysupervisedmklonmixedvisualfeatures |
_version_ |
1724181955258351616 |