A Random-Fern based Feature Approach for Image Matching
This addresses the need for efficient image processing in applications like mobile photo uploads, but it appears incremental as it builds on existing probabilistic models.
The paper tackles the problem of fast and accurate image matching for recognition and retrieval by proposing a method derived from Naive Bayesian classification, achieving satisfactory performance in experiments compared to state-of-the-art methods like Ferns and SIFT.
Image or object recognition is an important task in computer vision. With the hight-speed processing power on modern platforms and the availability of mobile phones everywhere, millions of photos are uploaded to the internet per minute, it is critical to establish a generic framework for fast and accurate image processing for automatic recognition and information retrieval. In this paper, we proposed an efficient image recognition and matching method that is originally derived from Naive Bayesian classification method to construct a probabilistic model. Our method support real-time performance and have very high ability to distinguish similar images with high details. Experiments are conducted together with intensive comparison with state-of-the-arts on image matching, such as Ferns recognition and SIFT recognition. The results demonstrate satisfactory performance.