In this experiment we count the number of features extracted using the LB approach and compared them to the features extracted using SIFT. We use a real image and a pi/2 rotated version of this image. We count the number of points with a distance smaller than 2 pixels between the extracted features and the projection of the rotated points from the original image.
Original image SIFT
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjzO1kWtr6cKeI1tomeYi19-NuEdj4vd-uEzdvCgi3I1t_h4s2L60rcR0ynP3DrOY-axtataoX6Dv4XwXyDxzfCMb-BsE16jbm9LwPqK3WB2YLFWVc-bRfmtWl2jPiC2XWQ-w1EQrvZP8Kd/s400/SIFT_features_real.png)
Rotated image SIFT
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEiVaqozkJ_MwXRWkuuy2OI93rKxrEnCKNFhlDts17mcBj2sNg3NzdgDQW9ejWGPG6BGcAOF49TzyQB6vJxGopZia1V_FKfQ5-K21x1Ce2Zeh_3CcXaIsJYlBTgEEgknnRNy3b2O9CnUvIhn/s400/SIFT_features_real_rotated.png)
TOTAL POINTS = 650
Original image LB
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhtLHBKuMzbXLUAoZtS4cvyFoxtAu8M0phEmciRAAjXb7QY_TQx0jZa_pXeNtG4KzJsU4uvN6vtviGOmMhd13NgyY17W6Z-2ZDp8D-R0KkwoPyFBYo7u9Pd5_LwaMOGQAj2pqP6LTSJwYNW/s400/LB_features_real.png)
Rotated image LB
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjjnYM7ppukJr1q5zdHsyTdt4nNa2NwBWahlxuXu9lOTya8UAA0HXZSPSHuNtHZHl4vrucYLIyKuHR4UpHYOTVQGl6VLs6KIxNJdcHpHa4duv0uylINK9EkGyxGE7oJZ8TUfQZqIuPOhinL/s400/LB_features_real_rotated.png)
TOTAL POINTS = 741
No comments:
Post a Comment