Virtual reality image local features are highly repetitive and are not easily affected by target occlusion, so research on virtual reality image local feature extraction techniques has received increasing attention. For the purpose of global scale selection, this article considers the virtual reality image in the global scope from the theoretical perspectives of the continuity of virtual reality images, the repeatability of virtual reality image features, the scale of scene virtual reality images in the global scope, and the visual saliency. This paper gives a general framework of multi-scale geometric analysis and particle swarm optimization virtual reality image matching algorithm. For the problem of virtual reality image matching, the original particle swarm optimization algorithm is improved. A more reasonable inertia weight change formula, a method for selecting the optimal solution when two objectives are optimized at the same time, and a method for selecting a reasonable input are designed. In this paper, performance evaluation experiments are performed on several feature description algorithms. The experimental results show that the descriptors constructed by these feature description algorithms are significantly more robust than SIFT (Scale Invariant Feature Transform) descriptors. The improved multi-scale geometric analysis and particle swarm optimization are robust due to the introduction of multiple support domains. It has the best discriminative ability, but at the same time, the introduction of multiple support domains leads to the worst real-time algorithm; DGOH (Dual Gradient Orientation Histogram) algorithm is more robust than FRDOH (Fast Representation Based on a Double Orientation Histogram) and SIFT algorithm, and DGOH algorithm has the best real-time performance. INDEX TERMS virtual reality images; particle swarm optimization; multi-scale geometric analysis; inertial weights; feature description.