3D Object Categorization Using Spin-Images with MPI Parallel Implementation | ||||
IJCI. International Journal of Computers and Information | ||||
Article 6, Volume 3, Issue 1, June 2014, Page 75-87 PDF (546.69 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/ijci.2014.33969 | ||||
View on SCiNiTO | ||||
Authors | ||||
D. Hegazy; A. Hamdy* ; W. Elkilany | ||||
Computer Systems Department, Ain Shams University | ||||
Abstract | ||||
Object recognition and categorization are two important key features of computer vision. Accuracy aspects representresearchchallengeforbothobjectrecognitionandcategorization techniques. High performance computing (HPC) technologies usually manage the increasing time and complexity of computations. In this paper, an approach utilizing3Dspin-imagesfor3Dobjectcategorizationisproposed.Themaincontributionofthisapproach is that item ploys the MPI techniques in a unique way to extract spin-images. The technique proposed utilizes the independence between spin-images generated a teach point. Time estimation of this technique has shown dramatic decrease of the categorization time proportion alto number of workers used. | ||||
Keywords | ||||
Object categorization; spin-image; support vectormachine; MPI | ||||
Statistics Article View: 180 PDF Download: 259 |
||||