A Comparative Study of SIFT and its Variants
SIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2013-06-01
|
| Series: | Measurement Science Review |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/msr-2013-0021 |
| _version_ | 1818585570580889600 |
|---|---|
| author | Wu Jian Cui Zhiming Sheng Victor S. Zhao Pengpeng Su Dongliang Gong Shengrong |
| author_facet | Wu Jian Cui Zhiming Sheng Victor S. Zhao Pengpeng Su Dongliang Gong Shengrong |
| author_sort | Wu Jian |
| collection | DOAJ |
| description | SIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved algorithms that have drawn a lot of attention are PCA-SIFT, GSIFT, CSIFT, SURF and ASIFT. In this paper, we first systematically analyze SIFT and its variants. Then, we evaluate their performance in different situations: scale change, rotation change, blur change, illumination change, and affine change. The experimental results show that each has its own advantages. SIFT and CSIFT perform the best under scale and rotation change. CSIFT improves SIFT under blur change and affine change, but not illumination change. GSIFT performs the best under blur change and illumination change. ASIFT performs the best under affine change. PCA-SIFT is always the second in different situations. SURF performs the worst in different situations, but runs the fastest. |
| first_indexed | 2024-12-16T08:39:10Z |
| format | Article |
| id | doaj.art-a8308960c4ab49e29d63ece8e2852bbd |
| institution | Directory Open Access Journal |
| issn | 1335-8871 |
| language | English |
| last_indexed | 2024-12-16T08:39:10Z |
| publishDate | 2013-06-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Measurement Science Review |
| spelling | doaj.art-a8308960c4ab49e29d63ece8e2852bbd2022-12-21T22:37:43ZengSciendoMeasurement Science Review1335-88712013-06-0113312213110.2478/msr-2013-0021A Comparative Study of SIFT and its VariantsWu Jian0Cui Zhiming1Sheng Victor S.2Zhao Pengpeng3Su Dongliang4Gong Shengrong5The Institute of Intelligent Information Processing and Application, Soochow University, Suzhou 215006, ChinaDepartment of Computer Science, University of Central Arkansas, Conway 72035, USADepartment of Computer Science, University of Central Arkansas, Conway 72035, USAThe Institute of Intelligent Information Processing and Application, Soochow University, Suzhou 215006, ChinaThe Institute of Intelligent Information Processing and Application, Soochow University, Suzhou 215006, ChinaThe Institute of Intelligent Information Processing and Application, Soochow University, Suzhou 215006, ChinaSIFT is an image local feature description algorithm based on scale-space. Due to its strong matching ability, SIFT has many applications in different fields, such as image retrieval, image stitching, and machine vision. After SIFT was proposed, researchers have never stopped tuning it. The improved algorithms that have drawn a lot of attention are PCA-SIFT, GSIFT, CSIFT, SURF and ASIFT. In this paper, we first systematically analyze SIFT and its variants. Then, we evaluate their performance in different situations: scale change, rotation change, blur change, illumination change, and affine change. The experimental results show that each has its own advantages. SIFT and CSIFT perform the best under scale and rotation change. CSIFT improves SIFT under blur change and affine change, but not illumination change. GSIFT performs the best under blur change and illumination change. ASIFT performs the best under affine change. PCA-SIFT is always the second in different situations. SURF performs the worst in different situations, but runs the fastest.https://doi.org/10.2478/msr-2013-0021image matchinglocal featuresiftpca-siftgsiftcsiftsurfasift |
| spellingShingle | Wu Jian Cui Zhiming Sheng Victor S. Zhao Pengpeng Su Dongliang Gong Shengrong A Comparative Study of SIFT and its Variants Measurement Science Review image matching local feature sift pca-sift gsift csift surf asift |
| title | A Comparative Study of SIFT and its Variants |
| title_full | A Comparative Study of SIFT and its Variants |
| title_fullStr | A Comparative Study of SIFT and its Variants |
| title_full_unstemmed | A Comparative Study of SIFT and its Variants |
| title_short | A Comparative Study of SIFT and its Variants |
| title_sort | comparative study of sift and its variants |
| topic | image matching local feature sift pca-sift gsift csift surf asift |
| url | https://doi.org/10.2478/msr-2013-0021 |
| work_keys_str_mv | AT wujian acomparativestudyofsiftanditsvariants AT cuizhiming acomparativestudyofsiftanditsvariants AT shengvictors acomparativestudyofsiftanditsvariants AT zhaopengpeng acomparativestudyofsiftanditsvariants AT sudongliang acomparativestudyofsiftanditsvariants AT gongshengrong acomparativestudyofsiftanditsvariants AT wujian comparativestudyofsiftanditsvariants AT cuizhiming comparativestudyofsiftanditsvariants AT shengvictors comparativestudyofsiftanditsvariants AT zhaopengpeng comparativestudyofsiftanditsvariants AT sudongliang comparativestudyofsiftanditsvariants AT gongshengrong comparativestudyofsiftanditsvariants |