Image Matching Algorithm Based on Topology Consistency of Bidirectional Optimal Matching Point Pairs

Abstract

The random sample consensus (RANSAC) algorithm is commonly used to estimate the parameters of the image transformation model based on matching point pairs in the featurebased image matching field. If the dataset of matching point pairs contains outliers, the conventional RANSAC algorithm may take a large number of iterations to obtain the desired model. To reduce mismatching, we propose the bidirectional optimal matching method, aiming to find robust parameters within a short time. The topology-consistency-based sampling method is introduced to divide the dataset into certain consensus sets, and sampling from each of them can reduce randomness. Then, all point pairs from a consensus set are used to estimate a model, and a point pair unsuitable for the model is deleted in each iteration, which is demonstrated to be faster than the conventional RANSAC. The superiority of the proposed method in fingerprint matching based on the scale-invariant feature transform is shown in experiments.

Research on high precision image registration method based on line segment feature and ICP algorithm

“…Image registration refers to the process of processing two or more images so that their scale, rotation, and translation are transformed into the same coordinate system for more accurate comparative analysis or synthesis of new images. Image registration technology is widely used in computer vision, remote sensing image processing, medical image analysis and other fields, the research on image registration is of great significance [1][2]. Commonly used image registration methods include methods based on grayscale, methods based on transform domain, and methods based on image feature: 1.…”