Object Recognition using Random Image-lines

View-based recognition is a conceptually simple, relatively robust method for object recognition. Current techniques use small, simplistic object databases requiring, in many cases, large processing training and/or recognition times. In this paper we propose an extension to the view-based object recognition paradigm based on the classification of line segments of 2D image views that achieves high generalisation recognition rates with reduced computational times. 1 Introduction Three-dimensional (3D) object recognition (OR) can be defined as the ability to automatically recognise one or more objects in isolation or in a complex, cluttered 2D scene. Prior knowledge of the known objects is made available to the 3D object recognition system by developing a 3D model of the object or, by training the system on one or more image views of the scene. The system can then detect and recognise objects in a 2D scene instance by matching the precompiled object models or training data with the scene..