3D Object Recognition System Based On Local Shape Descriptors and Depth Data Analysis

摘要

Background: A physical object, which is actually in 3D form, is captured by a sensor/camera (in case of computer vision) and seen by a human eye (in case of a human vision). Whensomeone is observing something, many other things are also involved there which make it more challengingto recognize. After capturing such a thing by a camera or sensor, a digital image is formedwhich is nothing other than a bunch of pixels. It is becoming important to know that how a computerunderstands images.Objective: This paper is for highlighting novel techniques on 3D object recognition system with localshape descriptors and depth data analysis.Methods: The proposed work is applied to RGBD and COIL-100 datasets and this is of four-fold aspreprocessing, feature generation, dimensionality reduction, and classification. The first stage of preprocessingis smoothing by 2D median filtering on the depth (Z-value) and registration by orientationcorrection on 3D object data. The next stage is of feature generation and having two phases of shapemap generation with shape index map and SIFT/SURF descriptors. The dimensionality reduction is thethird stage of this proposed work where linear discriminant analysis and principal component analysisare used. The final stage is fused on classification.Results: Here, calculation of the discriminative subspace for the training set, testing of object data andclassification is done by comparing target and query data with different aspects for finding propermatching tasks.Conclusion: This concludes with new proposed approach of 3D Object Recognition. The local shapedescriptors are used for 3D object recognition system to implement and test. This system is achieves89.2% accuracy for Columbia object image library-100 images by using local shape descriptors.