OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Changed the object_detector interface slightly. In particular, it now handles 

the adjust_threshold argument slightly differently in that it does not add it
to the output detection score anymore.
This commit is contained in:
Davis King 2013-03-31 15:18:24 -04:00
parent 238effb9c6
commit f2426231b9
2 changed files with 10 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
dlib/image_processing/object_detector.h
View File

@ -293,10 +293,10 @@ namespace dlib
if (w.size() != 0)
{
std::vector<std::pair<double, rectangle> > dets;
const double thresh = w(scanner.get_num_dimensions()) + adjust_threshold;
const double thresh = w(scanner.get_num_dimensions());
scanner.load(img);
scanner.detect(w, dets, thresh);
scanner.detect(w, dets, thresh + adjust_threshold);
for (unsigned long i = 0; i < dets.size(); ++i)
{

12
dlib/image_processing/object_detector_abstract.h
View File

@ -153,15 +153,19 @@ namespace dlib
- #dets.size() == the number of detected objects.
- #dets[i].first gives the "detection confidence", of the i-th
detection. This is the detection value output by the scanner
minus the threshold, therefore this is a value > 0.
minus the threshold.
- #dets[i].second == the bounding box for the i-th detection.
- #get_scanner() will have been loaded with img. Therefore, you can call
#get_scanner().get_feature_vector() to obtain the feature vectors or
#get_scanner().get_full_object_detection() to get the
full_object_detections for the resulting object detection boxes.
- The detection threshold is adjusted by having adjust_threshold added
to it. Therefore, an adjust_threshold value > 0 makes detecting
objects harder while a negative one makes it easier.
- The detection threshold is adjusted by having adjust_threshold added to
it. Therefore, an adjust_threshold value > 0 makes detecting objects
harder while a negative one makes it easier. Moreover, the following
will be true for all valid i:
- #dets[i].first >= adjust_threshold
This means that, for example, you can obtain all possible detections as
outputs by setting adjust_threshold equal to negative infinity.
!*/
template <