View Based Methods can achieve Bayes-Optimal 3D Recognition

Details View Based Methods can achieve Bayes-Optimal 3D Recognition View Based Methods can achieve Bayes-Optimal 3D Recognition

2007-12-02

arxiv.org/abs/0712.0137v1

Computer Science

Computer Vision and Pattern Recognition

Scientific paper

This paper proves that visual object recognition systems using only 2D Euclidean similarity measurements to compare object views against previously seen views can achieve the same recognition performance as observers having access to all coordinate information and able of using arbitrary 3D models internally. Furthermore, it demonstrates that such systems do not require more training views than Bayes-optimal 3D model-based systems. For building computer vision systems, these results imply that using view-based or appearance-based techniques with carefully constructed combination of evidence mechanisms may not be at a disadvantage relative to 3D model-based systems. For computational approaches to human vision, they show that it is impossible to distinguish view-based and 3D model-based techniques for 3D object recognition solely by comparing the performance achievable by human and 3D model-based systems.}

Affiliated with

Also associated with

No associations

Rating

View Based Methods can achieve Bayes-Optimal 3D Recognition 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 View Based Methods can achieve Bayes-Optimal 3D Recognition, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and View Based Methods can achieve Bayes-Optimal 3D Recognition will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-469406