Research and improvement of feature detection algorithm based on FAST

Abstract

At present, in the application of feature-based medical 3D reconstruction technology, there are still problems such as low matching accuracy of feature points in endoscope images and slow processing speed of image data. Therefore, the feature-based 3D reconstruction theory is of great research value and has great application value. This paper proposed a new feature detection method to improve the problems. This paper divides feature detection into two parts for further improvements: feature extraction and feature description. For feature extraction, the FAST algorithm shows a poor classification effect, so this paper adds the decision tree based on the C4.5 algorithm into the traditional FAST. The original data are divided into two decision trees to make the feature extraction performance more stable and feature point extraction more efficient. For the feature description part, the FREAK descriptor is used, combined with this paper's improved feature extraction algorithm. The feature points are extracted in scale space. The second-order function fitting is carried out according to the feature points' response scores in different scales. The scale-invariant descriptor of sub-pixel precision is obtained. The experimental results on the endoscope image show that the feature extraction method has a higher extraction accuracy and faster extraction speed. In addition, the feature description algorithm has higher calculation efficiency.