Fast Keypoint Recognition Using Random Ferns

摘要: While feature point recognition is a key component of modern approaches to object detection, existing require computationally expensive patch preprocessing handle perspective distortion. In this paper, we show that formulating the problem in naive Bayesian classification framework makes such unnecessary and produces an algorithm simple, efficient, robust. Furthermore, it scales well as number classes grows. To recognize patches surrounding keypoints, our classifier uses hundreds simple binary features models class posterior probabilities. We make tractable by assuming independence between arbitrary sets features. Even though not strictly true, demonstrate nevertheless performs remarkably on image data containing very significant changes.