Complex network shape descriptor for 3D objects classification

The 3D object recognition is an important research field in robotics. The real world object classification, retrieval, localization and tracking from images (2D or 3D data) are very useful application of computer vision in many areas, for instance, robotics, industry, education, augmented reality and medicine. Locate and recognize 3D objects in the environment can serve to create robust landmarks for robot pose estimation and localization, and can also be very important in telepresence, teleoperation, and grasping tasks. On the other hand, complex networks applications are a growing research field, and their application on computer vision is still a very recent research topic. This work uses complex networks to create shape descriptors for 3D point clouds of objects, and then uses a machine learning algorithm (k-NN) for object classification. Experiments of object classification, considering only the 3D shape, were done using the well known UW-University of Washington RGB-D objects dataset. The results are comparable to the best results of recent methods on the same dataset.