'''LESH (Local Energy based Shape Histogram)''' is a robust image descriptor that can be used in computer vision tasks. It can be used to get an efficient description of the underlying shape.The LESH feature descriptor is built on local energy model of feature perception. It encodes the underlying shape well, by accumulating local energy of the underlying signal along several filter orientations. several local histograms from different parts of the image/patch are generated and concatenated together into a 128-dimentional compact spatial histogram. The LESH features can be used in applications like shape-based image retrieval, object detection, pose estimation etc.▼
More details can be found in the related publication.
▲'''LESH (Local Energy energy-based Shapeshape Histogramhistogram (LESH)''' is a robustproposed [[image descriptor that can be used]] in [[computer vision tasks]]. It can be used to get an efficienta description of the underlying shape. The LESH feature descriptor is built on local energy model of feature perception, see e.g. [[phase congruency]] for more details. It encodes the underlying shape well, by accumulating local energy of the underlying signal along several filter orientations., several local [[histograms]] from different parts of the image/patch are generated and concatenated together into a 128-dimentionaldimensional compact spatial histogram. It is designed to be [[scale invariant]]. The LESH features can be used in applications like shape-based image retrieval, medical image processing, object detection, and [[3D Pose Estimation|pose estimation etc]].
== See also ==
* [[Feature detection (computer vision)]]
* [[Scale-invariant feature transform]]
* [[SURF | Speeded Up Robustup Featuresrobust features]]
*[http://www.cv.tu-berlin.de/publicationsfileadmin/fg140/Head_Pose_Estimation.pdf Sarfraz, S., Hellwich, O.:"Head Pose Estimation in Face Recognition across Pose Scenarios", Proceedings of VISAPP 2008, Int. conference on Computer Vision Theory and Applications, Madeira, Portugal, pp. 235-242, January 2008 (Best Student Paper Award).]
