International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
|
Volume 43 - Issue 22 |
Published: April 2012 |
Authors: Meenakshi M. Pawar, Sanman Bhusari, Akshay Gundewar |
![]() |
Meenakshi M. Pawar, Sanman Bhusari, Akshay Gundewar . Identification of Infected Pomegranates using Color Texture Feature Analysis. International Journal of Computer Applications. 43, 22 (April 2012), 30-34. DOI=10.5120/6404-8792
@article{ 10.5120/6404-8792, author = { Meenakshi M. Pawar,Sanman Bhusari,Akshay Gundewar }, title = { Identification of Infected Pomegranates using Color Texture Feature Analysis }, journal = { International Journal of Computer Applications }, year = { 2012 }, volume = { 43 }, number = { 22 }, pages = { 30-34 }, doi = { 10.5120/6404-8792 }, publisher = { Foundation of Computer Science (FCS), NY, USA } }
%0 Journal Article %D 2012 %A Meenakshi M. Pawar %A Sanman Bhusari %A Akshay Gundewar %T Identification of Infected Pomegranates using Color Texture Feature Analysis%T %J International Journal of Computer Applications %V 43 %N 22 %P 30-34 %R 10.5120/6404-8792 %I Foundation of Computer Science (FCS), NY, USA
In this study, a new approach is used to automatically detect the infected pomegranates. In the development of automatic grading and sorting system for pomegranate, critical part is detection of infection. Color texture feature analysis is used for detection of surface defects on pomegranates. Acquired image is initially cropped and then transformed into HSI color space, which is further used for generating SGDM matrix. Total 18 texture features were computed for hue (H), saturation (S) and intensity (I) images from each cropped samples. Best features were used as an input to Support Vector Machine (SVM) classifier and tests were performed to identify best classification model. Out of selected texture features, features showing optimal results were cluster shade (99. 8835%), product moment (99. 8835%) and mean intensity (99. 8059%).