Details
| Original language | English |
|---|---|
| Pages (from-to) | 975-990 |
| Number of pages | 16 |
| Journal | Machine Vision and Applications |
| Volume | 26 |
| Issue number | 7-8 |
| Publication status | Published - 15 Sept 2015 |
Abstract
In this paper, we present feature descriptor evaluation and feature regression for multimodal image analysis. First, we compare the performances of several popular interest point detectors and feature descriptors from multimodal images with focus on visual and infrared images. The performances of detectors are evaluated mainly by the score of repeatability and accuracy and the descriptors are assessed by using the rate of precision and recall. Secondly, we analyze the relationship between the corresponding descriptors computed from multimodal images. The descriptors are regressed by means of linear regression as well as Gaussian process. Then the features on infrared images are predicted by mapping the descriptors from visual images to the infrared modality through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. We believe that this evaluating information will be useful when selecting an appropriate detector and descriptor for multimodal image analysis. Also the experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
Keywords
- Feature performance, Feature regression, Multimodal images
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Hardware and Architecture
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Computer Science(all)
- Computer Science Applications
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Machine Vision and Applications, Vol. 26, No. 7-8, 15.09.2015, p. 975-990.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Descriptor evaluation and feature regression for multimodal image analysis
AU - Yong, Xuanzi
AU - Yang, Michael Ying
AU - Cao, Yanpeng
AU - Rosenhahn, Bodo
N1 - Funding information: The work is partially funded by DFG (German Research Foundation) YA 351/2-1. The authors gratefully acknowledge the support.
PY - 2015/9/15
Y1 - 2015/9/15
N2 - In this paper, we present feature descriptor evaluation and feature regression for multimodal image analysis. First, we compare the performances of several popular interest point detectors and feature descriptors from multimodal images with focus on visual and infrared images. The performances of detectors are evaluated mainly by the score of repeatability and accuracy and the descriptors are assessed by using the rate of precision and recall. Secondly, we analyze the relationship between the corresponding descriptors computed from multimodal images. The descriptors are regressed by means of linear regression as well as Gaussian process. Then the features on infrared images are predicted by mapping the descriptors from visual images to the infrared modality through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. We believe that this evaluating information will be useful when selecting an appropriate detector and descriptor for multimodal image analysis. Also the experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
AB - In this paper, we present feature descriptor evaluation and feature regression for multimodal image analysis. First, we compare the performances of several popular interest point detectors and feature descriptors from multimodal images with focus on visual and infrared images. The performances of detectors are evaluated mainly by the score of repeatability and accuracy and the descriptors are assessed by using the rate of precision and recall. Secondly, we analyze the relationship between the corresponding descriptors computed from multimodal images. The descriptors are regressed by means of linear regression as well as Gaussian process. Then the features on infrared images are predicted by mapping the descriptors from visual images to the infrared modality through the regression results. Predictions are assessed in two ways: the statistics of absolute error between true values and actual values, and the precision score of matching the predicted descriptors to the original infrared descriptors. We believe that this evaluating information will be useful when selecting an appropriate detector and descriptor for multimodal image analysis. Also the experimental results show that regression methods achieve a well-assessed relationship between corresponding descriptors from multiple modalities.
KW - Feature performance
KW - Feature regression
KW - Multimodal images
UR - http://www.scopus.com/inward/record.url?scp=84943364018&partnerID=8YFLogxK
U2 - 10.1007/s00138-015-0714-x
DO - 10.1007/s00138-015-0714-x
M3 - Article
AN - SCOPUS:84943364018
VL - 26
SP - 975
EP - 990
JO - Machine Vision and Applications
JF - Machine Vision and Applications
SN - 0932-8092
IS - 7-8
ER -