Underwater Image Feature Matching Based on Inhomogeneous Illumination
In this paper, the problem of underwater image matching was concerned. The accuracy of underwater image feature matching is significant for underwater vision research. Due to the attributes including absorption and scattering of water, three problems should be accomplished: image acquisition, image processing, and image matching. In response to the first problem, an inhomogeneous illumination method is developed to acquire clear underwater-image. Then contrast limited adaptive histogram equalization was used to process the original image. Finally, an effective algorithm based on SIFT features is used to achieve precise image matching.
KeywordsInhomogeneous illumination CLAHE Feature extraction Image matching
- 1.Hongmei Xu, Zhang Zhigang, Zheng Bing (2010) Distribution characteristics in the underwater inhomogeneous illumination field. Acta Photonica Sinica 39(9):16061610Google Scholar
- 2.Schmid C, Mohr R (1997) Local grayvalue invariants for image retrieval[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(5):530–534Google Scholar
- 3.Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91–110Google Scholar
- 4.Mobley CD, Mobley CD (1994) Light and water: radiative transfer in natural waters. Academic press, San DiegoGoogle Scholar
- 5.Zhang Q, Wang Z (2009) Proficient in MATLAB image processing. Publishing House of Electronics Industry, beijing, pp 140–141Google Scholar