Analysis of the Repeatability of SIFT and SURF Descriptors Techniques for Underwater Image Preprocessing

Abstract

To improve the repeatability of SIFT and SURF descriptors, we conducted research to find two methods: first, a method for pre-processing underwater images that does not require prior knowledge of the scene, and second, a method for computing distances that is less expensive in terms of execution time for finding corresponding points. SIFTs (Scale and Rotation Invariant Features) are new features that have been developed. SIFTs (Scale and Rotation Invariant Features) are newly developed features that are based on geometrical constraints between pairs of nearby points around a key point. SIFT is contrasted with cutting-edge local features. SIFT outperforms the state-of-the-art in terms of retrieval time and retrieval accuracy. We have discussed the time required to extract key point features of SIFT and SURF Descriptor.

Side-Scan Sonar Image Matching Method Based on Topology Representation

“…They facilitate the identification of similar feature points across disparate images, thereby enabling precise image registration and object recognition. Ghate and Nikose (2021) [12] analyzed the repeatability of SIFT and SURF descriptors with the aim of optimizing preprocessing methods for underwater images by refining the extraction process of key feature points. Additionally, Pourfard et al (2021) [13] proposed a method that amalgamates the KAZE algorithm with a modified SURF descriptor for the registration of Synthetic Aperture Radar (SAR) images, specifically targeting the issue of speckle noise.…”

Optimizing Underwater Vision: A Rigorous Investigation into CNN's Deep Image Enhancement for Subaquatic Scenes

“…When it comes to underwater robot inspection and marine environmental monitoring, problems with absorption and dispersion make it difficult to understand and recognize images. When applied to underwater photos, standard image enhancement techniques [1][2] [15][16] [8] have drawbacks as well. Due to insufficient training data, it is difficult to effectively improve underwater images and videos using deep learning.…”