Learning‐based natural geometric matching with homography prior
| Autor: | Jing Chen, Tianli Liao, Yifang Xu |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
business.industry
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Image registration 02 engineering and technology Image (mathematics) Transformation (function) Compositing 0202 electrical engineering electronic engineering information engineering Homography Key (cryptography) 020201 artificial intelligence & image processing Computer vision Affine transformation Artificial intelligence Electrical and Electronic Engineering business Homography (computer vision) |
| Zdroj: | Electronics Letters. 54:1328-1330 |
| ISSN: | 1350-911X 0013-5194 |
| Popis: | Geometric matching is a key step in computer vision tasks. Previous learning-based methods for geometric matching concentrate more on improving alignment quality, while the importance of naturalness issue is argued simultaneously. To this end, a novel homography geometric matching architecture with homography prior is proposed. Specifically, two choices for different purposes in geometric matching are provided. When compositing homography prior with affine transformation, the alignment accuracy improves and all lines are preserved, which results in a more natural transformed image. When compositing homography prior with thin-plate-spline transformation, the alignment accuracy further improves. Experimental results on Proposal Flow dataset show that the proposed method outperforms state-of-the-art methods, both in terms of alignment accuracy and naturalness. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Plný text