mirror of
https://github.com/opencv/opencv.git
synced 2024-11-25 19:50:38 +08:00
c69312ea0d
modified SIFT to 1) double image before finding keypoints, 2) use floating-point internally instead of 16-bit integers, 3) set the keypoint response to the abs(interpolated_DoG_value). step 1) increases the number of detected keypoints significantly and together with 2) and 3) it improves some detection benchmarks. On the other hand, the stability of the small keypoints is lower, so the rotation and scale invariance tests now struggle a bit. In 2.5 need to make this feature optional and add some more intelligence to the algorithm. added test that finds a planar object using SIFT.
7 lines
214 B
CMake
7 lines
214 B
CMake
if(BUILD_ANDROID_PACKAGE)
|
|
ocv_module_disable(nonfree)
|
|
endif()
|
|
|
|
set(the_description "Functionality with possible limitations on the use")
|
|
ocv_define_module(nonfree opencv_imgproc opencv_features2d opencv_calib3d)
|