Keypoints class distribution based entropy for weighting scheme on image classification
In bag-of-visual words (BoVW), a weighting scheme is applied to improve the discriminative power of visual words, which affect the performance of image classification. However, the weighting schemes in the BoVW model did not utilize the information class of keypoints. In this paper, we propose an al...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2022-11-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157822003019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In bag-of-visual words (BoVW), a weighting scheme is applied to improve the discriminative power of visual words, which affect the performance of image classification. However, the weighting schemes in the BoVW model did not utilize the information class of keypoints. In this paper, we propose an algorithm to measure the certainty of visual words which employ the information class of keypoints, called keypoints class distribution based entropy (KCDE). The algorithm is then combined with the existing weighting scheme namely term frequency-term distribution (TF-TD). The results show that the proposed weighting schemes give better classification results than the baseline weighting schemes. |
|---|---|
| ISSN: | 1319-1578 |