A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function
Superpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. The...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9051814/ |
| id |
doaj-2d60e16613e94d31aa87f3424b784832 |
|---|---|
| record_format |
Article |
| spelling |
doaj-2d60e16613e94d31aa87f3424b7848322021-03-30T01:33:24ZengIEEEIEEE Access2169-35362020-01-018647836479810.1109/ACCESS.2020.29847209051814A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure FunctionGuoqi Liu0https://orcid.org/0000-0002-4106-3222Xusheng Li1https://orcid.org/0000-0003-0492-7455Baofang Chang2https://orcid.org/0000-0002-5402-4345Yifei Dong3https://orcid.org/0000-0002-2428-6205College of Computer and Information Engineering, Henan Normal University, Xinxiang, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang, ChinaCollege of Computer and Information Engineering, Henan Normal University, Xinxiang, ChinaSuperpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. There are three steps in the framework. Firstly, based on the proposed information measure function, the under-segmented superpixels generated by classic superpixel algorithms are screened out. Secondly, with the two invariant centroids method, these under-segmented superpixels are re-segmented to improve the accuracy in boundary adherence. Finally, smaller superpixels are merged to maintain the same number with initial superpixels. Quantitative evaluations on the BSDS500 exhibit that the performance of the classic superpixel algorithms is improved by employing the framework, especially on the condition of fewer superpixels.https://ieeexplore.ieee.org/document/9051814/Superpixelboundary optimizationframeworkinformation measure functionweighted directed graph |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Guoqi Liu Xusheng Li Baofang Chang Yifei Dong |
| spellingShingle |
Guoqi Liu Xusheng Li Baofang Chang Yifei Dong A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function IEEE Access Superpixel boundary optimization framework information measure function weighted directed graph |
| author_facet |
Guoqi Liu Xusheng Li Baofang Chang Yifei Dong |
| author_sort |
Guoqi Liu |
| title |
A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function |
| title_short |
A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function |
| title_full |
A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function |
| title_fullStr |
A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function |
| title_full_unstemmed |
A Superpixel Boundary Optimization (SBO) Framework Based on Information Measure Function |
| title_sort |
superpixel boundary optimization (sbo) framework based on information measure function |
| publisher |
IEEE |
| series |
IEEE Access |
| issn |
2169-3536 |
| publishDate |
2020-01-01 |
| description |
Superpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. There are three steps in the framework. Firstly, based on the proposed information measure function, the under-segmented superpixels generated by classic superpixel algorithms are screened out. Secondly, with the two invariant centroids method, these under-segmented superpixels are re-segmented to improve the accuracy in boundary adherence. Finally, smaller superpixels are merged to maintain the same number with initial superpixels. Quantitative evaluations on the BSDS500 exhibit that the performance of the classic superpixel algorithms is improved by employing the framework, especially on the condition of fewer superpixels. |
| topic |
Superpixel boundary optimization framework information measure function weighted directed graph |
| url |
https://ieeexplore.ieee.org/document/9051814/ |
| work_keys_str_mv |
AT guoqiliu asuperpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT xushengli asuperpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT baofangchang asuperpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT yifeidong asuperpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT guoqiliu superpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT xushengli superpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT baofangchang superpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction AT yifeidong superpixelboundaryoptimizationsboframeworkbasedoninformationmeasurefunction |
| _version_ |
1724186761119137792 |