Resolving Implementation Ambiguity and Improving SURF

Details Resolving Implementation Ambiguity and Improving SURF Resolving Implementation Ambiguity and Improving SURF

2012-02-02

arxiv.org/abs/1202.0492v3

Computer Science

Computer Vision and Pattern Recognition

Fixed incorrect contact information contained in previous version and clarified publication information. Additional small chan

Scientific paper

Speeded Up Robust Features (SURF) has emerged as one of the more popular feature descriptors and detectors in recent years. Performance and algorithmic details vary widely between implementations due to SURF's complexity and ambiguities found in its description. To resolve these ambiguities, a set of general techniques for feature stability is defined based on the smoothness rule. Additional improvements to SURF are proposed for speed and stability. To illustrate the importance of these implementation details, a performance study of popular SURF implementations is done. By utilizing all the suggested improvements, it is possible to create a SURF implementation that is several times faster and more stable.

Affiliated with

Also associated with

No associations

Rating

Resolving Implementation Ambiguity and Improving SURF does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Resolving Implementation Ambiguity and Improving SURF, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Resolving Implementation Ambiguity and Improving SURF will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-188350