NextCloud/dlib
1
0
Fork 0
mirror of https://github.com/davisking/dlib.git synced 2024-11-01 10:14:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

updated docs

Browse Source
This commit is contained in:
Davis King 2013-03-24 15:44:34 -04:00
parent e9823c79d8
commit 173a2b6190
3 changed files with 53 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

56
docs/docs/imaging.xml
View File

@ -85,6 +85,7 @@
<item>scan_image_movable_parts</item>
<item>find_points_above_thresh</item>
<item>scan_image_pyramid</item>
<item>scan_image_boxes</item>
<item>find_candidate_object_locations</item>
<item>test_box_overlap</item>
<item nolink="true">
@ -1631,6 +1632,45 @@
</component>
<!-- ************************************************************************* -->
<component>
<name>scan_image_boxes</name>
<file>dlib/image_processing.h</file>
<spec_file link="true">dlib/image_processing/scan_image_boxes_abstract.h</spec_file>
<description>
This object is a tool for running a classifier over an image with the goal
of localizing each object present. The localization is in the form of the
bounding box around each object of interest.
<p>
Unlike the <a href="#scan_image_pyramid">scan_image_pyramid</a> object which scans a
fixed sized window over an image pyramid, the scan_image_boxes tool allows you to
define your own list of "candidate object locations" which should be evaluated.
This is simply a list of rectangle objects which might contain objects of
interest. The scan_image_boxes object will then evaluate the classifier at each
of these locations and return the subset of rectangles which appear to have
objects in them.
</p>
This object can also be understood as a general tool for implementing the spatial
pyramid models described in the paper:
<blockquote>
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing
Natural Scene Categories by Svetlana Lazebnik, Cordelia Schmid,
and Jean Ponce
</blockquote>
<br/><br/>
The following feature extractors can be used with the scan_image_boxes object:
<ul style="margin-top:0em">
<li><a href="#hashed_feature_image">hashed_feature_image</a></li>
<li><a href="#nearest_neighbor_feature_image">nearest_neighbor_feature_image</a></li>
</ul>
</description>
</component>
<!-- ************************************************************************* -->
<component>
@ -1651,13 +1691,15 @@
<file>dlib/image_processing.h</file>
<spec_file link="true">dlib/image_processing/object_detector_abstract.h</spec_file>
<description>
This object is a tool for detecting the positions of objects in
an image. In particular, it is a simple container to aggregate
an instance of the <a href="#scan_image_pyramid">scan_image_pyramid</a>
class, the weight vector needed by scan_image_pyramid, and
an instance of <a href="#test_box_overlap">test_box_overlap</a>. The test_box_overlap
object is used to perform non-max suppression on the output of the
scan_image_pyramid object.
This object is a tool for detecting the positions of objects in an image. In
particular, it is a simple container to aggregate an instance of the <a
href="#scan_image_pyramid">scan_image_pyramid</a> or <a
href="#scan_image_boxes">scan_image_boxes</a> classes, the weight vector
needed by one of these image scanners, and finally an instance of
<a href="#test_box_overlap">test_box_overlap</a>. The test_box_overlap object
is used to perform non-max suppression on the output of the image scanner
object.
<p>
Note that you can use the
<a href="ml.html#structural_object_detection_trainer">structural_object_detection_trainer</a>

3
docs/docs/ml.xml
View File

@ -2591,7 +2591,8 @@ Davis E. King. <a href="http://jmlr.csail.mit.edu/papers/volume10/king09a/king09
<spec_file link="true">dlib/svm/structural_svm_object_detection_problem_abstract.h</spec_file>
<description>
This object is a tool for learning the parameter vector needed to use
a <a href="imaging.html#scan_image_pyramid">scan_image_pyramid</a> object.
a <a href="imaging.html#scan_image_pyramid">scan_image_pyramid</a> or
<a href="imaging.html#scan_image_boxes">scan_image_boxes</a> object.
<p>
It learns the parameter vector by formulating the problem as a <a href="#structural_svm_problem">structural

2
docs/docs/term_index.xml
View File

@ -1221,6 +1221,8 @@
<term file="imaging.html" name="scan_image"/>
<term file="imaging.html" name="scan_image_pyramid"/>
<term file="imaging.html" name="scan_image_boxes"/>
<term file="dlib/image_processing/scan_image_boxes_abstract.h.html" name="default_box_generator"/>
<term file="imaging.html" name="compute_box_dimensions"/>
<term file="imaging.html" name="create_single_box_detection_template"/>
<term file="imaging.html" name="create_overlapped_2x2_detection_template"/>