Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors
The utilization of gradient information is a key issue in building Scale Invariant Feature Transform (SIFT)-like descriptors. In the literature, two types of gradient information, i.e., Gradient Magnitude (GM) and Gradient Occurrence (GO), are used for building descriptors. However, both of these tw...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/11/8/998 |
| _version_ | 1798035403238801408 |
|---|---|
| author | Guangyao Dong Han Yan Guohua Lv Xiangjun Dong |
| author_facet | Guangyao Dong Han Yan Guohua Lv Xiangjun Dong |
| author_sort | Guangyao Dong |
| collection | DOAJ |
| description | The utilization of gradient information is a key issue in building Scale Invariant Feature Transform (SIFT)-like descriptors. In the literature, two types of gradient information, i.e., Gradient Magnitude (GM) and Gradient Occurrence (GO), are used for building descriptors. However, both of these two types of gradient information have limitations in building and matching local image descriptors. In our prior work, a strategy of combining these two types of gradient information was proposed to intersect the keypoint matches which are obtained by using gradient magnitude and gradient occurrence individually. Different from this combination strategy, this paper explores novel strategies of weighting these two types of gradient information to build new descriptors with high discriminative power. These proposed weighting strategies are extensively evaluated against gradient magnitude and gradient occurrence as well as the combination strategy on a few image registration datasets. From the perspective of building new descriptors, experimental results will show that each of the proposed strategies achieve higher matching accuracy as compared to both GM-based and GO-based descriptors. In terms of recall results, one of the proposed strategies outperforms both GM-based and GO-based descriptors. |
| first_indexed | 2024-04-11T20:57:42Z |
| format | Article |
| id | doaj.art-cc0dba177dd64ed9b2b1f63a48ab49e6 |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-04-11T20:57:42Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-cc0dba177dd64ed9b2b1f63a48ab49e62022-12-22T04:03:38ZengMDPI AGSymmetry2073-89942019-08-0111899810.3390/sym11080998sym11080998Exploring the Utilization of Gradient Information in SIFT Based Local Image DescriptorsGuangyao Dong0Han Yan1Guohua Lv2Xiangjun Dong3School of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaSchool of Computer Science and Technology, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250353, ChinaThe utilization of gradient information is a key issue in building Scale Invariant Feature Transform (SIFT)-like descriptors. In the literature, two types of gradient information, i.e., Gradient Magnitude (GM) and Gradient Occurrence (GO), are used for building descriptors. However, both of these two types of gradient information have limitations in building and matching local image descriptors. In our prior work, a strategy of combining these two types of gradient information was proposed to intersect the keypoint matches which are obtained by using gradient magnitude and gradient occurrence individually. Different from this combination strategy, this paper explores novel strategies of weighting these two types of gradient information to build new descriptors with high discriminative power. These proposed weighting strategies are extensively evaluated against gradient magnitude and gradient occurrence as well as the combination strategy on a few image registration datasets. From the perspective of building new descriptors, experimental results will show that each of the proposed strategies achieve higher matching accuracy as compared to both GM-based and GO-based descriptors. In terms of recall results, one of the proposed strategies outperforms both GM-based and GO-based descriptors.https://www.mdpi.com/2073-8994/11/8/998SIFTlocal descriptorgradient informationgradient occurrence |
| spellingShingle | Guangyao Dong Han Yan Guohua Lv Xiangjun Dong Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors Symmetry SIFT local descriptor gradient information gradient occurrence |
| title | Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors |
| title_full | Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors |
| title_fullStr | Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors |
| title_full_unstemmed | Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors |
| title_short | Exploring the Utilization of Gradient Information in SIFT Based Local Image Descriptors |
| title_sort | exploring the utilization of gradient information in sift based local image descriptors |
| topic | SIFT local descriptor gradient information gradient occurrence |
| url | https://www.mdpi.com/2073-8994/11/8/998 |
| work_keys_str_mv | AT guangyaodong exploringtheutilizationofgradientinformationinsiftbasedlocalimagedescriptors AT hanyan exploringtheutilizationofgradientinformationinsiftbasedlocalimagedescriptors AT guohualv exploringtheutilizationofgradientinformationinsiftbasedlocalimagedescriptors AT xiangjundong exploringtheutilizationofgradientinformationinsiftbasedlocalimagedescriptors |