Multi-view CSPMPR-ELM feature learning and classifying for RGB-D object recognition

Abstract

In order to fully utilize potential feature information of RGB-D images, current popular algorithms mainly use convolutional neural network (CNN) to execute both feature extraction and classification. Such methods could achieve impressive results but usually on the basis of an extremely huge and complex network. What’s more, since the fully connected layers in CNN form a classical neural network classifier, which is trained by gradient descent-based implementations, the generalization ability is limited and sub-optimal. To address these problems, this paper introduce a multi-view CNN-SPMP-RNN-ELM (MCSPMPR-ELM) model for RGB-D object recognition, which combines the power of MCSPMPR and fast training of ELM. It uses the MCSPMPR algorithm to extract discriminative features from raw RGB images and depth images separately. Then the abstracted features are fed to a nonlinear ELM classifier, which leads to better generalization performance with faster learning speed. At last, co-training is employed to learn from the unlabeled data using the two distinct feature sets by semi-supervised learning method. Experimental results on widely used RGB-D object datasets show that our method achieves competitive performance compared with other state-of-the-art algorithms specifically designed for RGB-D data.