An object recognition system based on convolutional neural networks and angular resolutions

摘要

The development of 3D object recognition often requires a huge amount of data in the training process, especially when deep learning methods are involved so that the training can be convergent. The problem is that the availability of free 3D object datasets is usually quite limited, so some researchers have proposed several techniques to overcome this problem. In this work, we propose a novel algorithm, making use of angular resolutions and convolutional neural networks for 3D object recognition, and it collects image shapes or contours from real objects by placing them on a rotating display to record the appearances from multiple angular views. The chosen angular resolution is in the range of 0-180 degrees, and the selection of viewing angle is done by a binary search. We have conducted a comparative experiment on the accuracy of 6 well-known network architectures, including GoogleNet, CaffeNet, SqueezeNet, ResNet18, ResNet32, and ResNet50, to see how far these architecture networks can adapt to the angular resolution techniques that we propose for the classification of objects outside the lab environment. We also propose another way with the use of incremental learning, where we integrate our proposed method that uses GoogleNet model with two existing weights pre-trained models, i.e., AlexNet and VGG16. In other words, our proposed method helps address the limitations of other models with the weights of existing pre-trained methods to recognize new classes that were not recognized.