Three-dimensional Object Classification Research Articles

Multi-channel Joint Sparse Learning Model for Non-rigid Three-dimensional Object Classification

Abstract In order to solve the issues of inadequate feature description and inefficient feature learning model existing in current classification methods, this article proposes a multi-channel joint sparse learning model for three-dimensional (3D) non-rigid object classification. First, the authors adopt a multi-level measurement of intrinsic properties to create complementary shape descriptors. Second, they build independent and informative bag of features (BoF) by embedding these shape descriptors into the visual vocabulary space. Third, a max-dependency and min-redundancy criterion is applied for optimal feature filtering on each BoF dictionary based on mutual information; meanwhile, each dictionary is learned and weighted according to its contribution to the classification task, and then a compact multi-channel joint sparse learning model is constructed. Finally, the authors train the joint sparse learning model followed by a Softmax classifier to implement efficient shape classification. The experimental results show that the proposed method has stronger feature representation ability and promotes greatly the discrimination of sparse coding coefficients. Thus, the promising classification performance and the powerful robustness can be obtained compared to the state-of-the-art methods.

Effects of stereoscopic disparity on early ERP components during classification of three-dimensional objects.

This study investigates the effects of stereo disparity on the perception of three-dimensional (3D) object shape. We tested the hypothesis that stereo input modulates the brain activity related to perceptual analyses of 3D shape configuration during image classification. High-density (256-channel) electroencephalogram (EEG) was used to record the temporal dynamics of visual shape processing under conditions of two-dimensional (2D) and 3D visual presentation. On each trial, observers made image classification judgements ('Same'/'Different') to two briefly presented, multi-part, novel objects. On different-object trials, stimuli could either share volumetric parts but not the global 3D shape configuration and have different parts but the same global 3D shape configuration or differ on both aspects. Analyses using mass univariate contrasts showed that the earliest sensitivity to 2D versus 3D viewing appeared as a negative deflection over posterior locations on the N1 component between 160 and 220 ms post-stimulus onset. Subsequently, event-related potential (ERP) modulations during the N2 time window between 240 and 370 ms were linked to image classification. N2 activity reflected two distinct components - an early N2 (240-290 ms) and a late N2 (290-370 ms) - that showed different patterns of responses to 2D and 3D input and differential sensitivity to 3D object structure. The results revealed that stereo input modulates the neural correlates of 3D object shape. We suggest that this reflects differential perceptual processing of object shape under conditions of stereo or mono input. These findings challenge current theories that attribute no functional role for stereo input during 3D shape perception.

Three-dimensional object classification using shadow moire´ and neural network

A method of recognizing and classifying 3-D shapes with continuous surfaces by integrating shadow moire technique and neural network is presented. Unlike existing methods of 3-D shape recognition that use range images of polyhedral objects or objects of different geometries such as cones, rods, spheres, etc., the proposed method classifies continuous surfaces that are geometrically similar. The objects selected to test the classification method are eggs of four different grades. The shadow moire technique, which has greater sensitivity compared to structured lighting or laser scanning, is used to obtain moire patterns on the surface of the eggs. From the moire pattern images 14 parameters are extracted and used as input to a multilayer feedforward neural network. The results of the classification using the neural network show that the prediction accuracy attainable is 60% when classification is performed on all four grades. The accuracy increased to 95% when three of the grades are classified.

Three-dimensional object recognition from two-dimensional images using wavelet transforms and neural networks

Three-dimensional object classification from 2-D IR images is shown. The wavelet transform is used for edge detection. Edge tracking is used for removing noise effectively in the wavelet transform. The in- variant Fourier descriptor is used to describe the contour curves. Invari- ance under out-of-plane rotation is achieved by the feature space trajec- tory neural network working as a classifier. © 1998 Society of Photo-Optical Instrumentation Engineers. (S0091-3286(98)01203-3)