DocumentCode :
2501161
Title :
Local Directional Pattern (LDP) – A Robust Image Descriptor for Object Recognition
Author :
Jabid, Taskeed ; Kabir, Md Hasanul ; Chae, Oksam
Author_Institution :
Dept. of Comput. Eng., Kyung Hee Univ., Yongin, South Korea
fYear :
2010
fDate :
Aug. 29 2010-Sept. 1 2010
Firstpage :
482
Lastpage :
487
Abstract :
This paper presents a novel local feature descriptor, the Local Directional Pattern (LDP), for describing local image feature. A LDP feature is obtained by computing the edge response values in all eight directions at each pixel position and generating a code from the relative strength magnitude. Each bit of code sequence is determined by considering a local neighborhood hence becomes robust in noisy situation. A rotation invariant LDP code is also introduced which uses the direction of the most prominent edge response. Finally an image descriptor is formed to describe the image (or image region) by accumulating the occurrence of LDP feature over the whole input image (or image region). Experimental results on the Brodatz texture database show that LDP impressively outperforms the other commonly used dense descriptors (e.g.,Gabor-wavelet and LBP).
Keywords :
image classification; image texture; object recognition; Brodatz texture database; code sequence; edge response values; image descriptor; local directional pattern; local feature descriptor; local image feature; local neighborhood; object recognition; pixel position; relative strength magnitude; texture classification; Databases; Histograms; Image edge detection; Lighting; Noise; Pixel; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Video and Signal Based Surveillance (AVSS), 2010 Seventh IEEE International Conference on
Conference_Location :
Boston, MA
Print_ISBN :
978-1-4244-8310-5
Type :
conf
DOI :
10.1109/AVSS.2010.17
Filename :
5597095
Link To Document :
بازگشت