RECOGNIZING 3D OBJECTS BY USING MODELS LEARNED AUTOMATICALLY FROM 2D TRAINING IMAGES

摘要

A scheme for learning and recognizing 3D objects from their 2D views is presented. The scheme proceeds in two stages. In the first stage, we try to learn a prototype automatically from 2D training images of different objects which belong to the same object class and consequently have similar shapes of parts and similar adjacency relations between the parts. In the second stage, the generated prototype is used to recognize learned objects or the objects similar to the learned ones from images of complex real scenes and got satisfactory results.