1 Scalable Recognition with a Vocabulary Tree

Strengths System Overview Animated explanation of the vocabulary tree Explanation of the scoring scheme Testing Results Conclusion Scalable Recognition with a Vocabulary Tree The paper describes a system which can recognize objects from a very large database with great speed and recognition quality. The system uses local region descriptors which are hierarchically quantized in a vocabulary tree. Strengths! The vocabulary tree directly defines the quantization. Each high-dimension feature vector is quantized into an integer which corresponds to a path in the vocabulary tree. Results in speed Feature extraction on a 640x480 video frame in 0.2 sec. and database query in 25ms on a 50000 image database. Results in compactness