الفهرس | Only 14 pages are availabe for public view |
Abstract Bin Picking is one of the most difficult tasks for a robot to perform specially for unorganized parts. Machine vision is a vital tool that enables robots to perform this important task. This thesis introduces two vision based systems which give a robot the ability to recognize and localize automatically unorganized parts from a pile. The object recognition technique in the first system is based on shape contour and region features. These derived features are invariant with respect to scaling, rotation, translation, and affine transformation of the objects. The extracted features are used for training both Self Organizing Map (SOM) and Multi Layer Perceptron (MLP) neural networks for classification purpose. Several examples are given to demonstrate the efficiency of the proposed system. It is found that the combination of Affine Invariant Moments, Gray Moments, Geometric Features, and Fourier Descriptors performs the most successful single feature in recognition performance. The object recognition technique in the second system is based on the important object features. Important object features are obtained in two steps: firstly; by segmenting the object boundary at multiple scales through the use of its Iterative curvature scale space (ICSS) and secondly; by concentrating on each scale separately in order to search for groups of segments which distinguish an object from others. These groups of segments are; then, used to build a model database through the use of artificial neural networks (ANNs). |