We present a comprehensive review of the Hough transform, HT, in image processing and computer vision. It has long been recognized as a technique of almost unique promise for shape and motion analysis in images containing noisy, missing, and extraneous data but its adoption has been slow due to its computational and storage complexity and the lack of a detailed understanding of its properties. However, in recent years much progress has been made in these areas. In this review we discuss ideas for the efficient implementation of the HT and present results on the analytic and empirical performance of various methods. We also report the relationship of Hough methods and other transforms and consider applications in which the HT has been used. It seems likely that the HT will be an increasingly used technique and we hope that this survey will provide a useful guide to quickly acquaint researchers with the main literature in this research area.

A survey of the Hough transform

A general-purpose computer vision system must be capable of recognizing three-dimensional (3-D) objects. This paper proposes a precise definition of the 3-D object recognition problem, discusses basic concepts associated with this problem, and reviews the relevant literature. Because range images (or depth maps) are often used as sensor input instead of intensity images, techniques for obtaining, processing, and characterizing range data are also surveyed.

Three-dimensional object recognition

https://onlinelibrary.wiley.com/doi/pdf/10.1207/s15516709cog0603_1

Connectionist Models and Their Properties

A general method for model-based object recognition in occluded scenes is presented. It is based on geometric hashing. The method stands out for its efficiency. We describe the general framework of the method and illustrate its applications for various recogni- tion problems both in 3-D and 2-D. Special attention is given to the recognition of 3-D objects in occluded scenes from 2-D gray scale images. New experimental results are included for this important case.

Geometric Hashing: A General And Efficient Model-based Recognition Scheme

This is a primer on extended Gaussian images Extended Gaussian images are useful for representing the shapes of surfaces They can be computed easily from: 1 needle maps obtained using photometric stereo; or 2 depth maps generated by ranging devices or binocular stereo Importantly, they can also be determined simply from geometric models of the objects Extended Gaussian images can be of use in at least two of the tasks facing a machine vision system: 1 recognition, and 2 determining the attitude in space of an object Here, the extended Gaussian image is defined and some of its properties discussed An elaboration for nonconvex objects is presented and several examples are shown

/pdf/extended-gaussian-images-htjigybo6q.pdf

Extended Gaussian images

An important problem in vision is to detect the presence of a known rigid 3-D object. The general 3-D object recognition task can be thought of as building a description of the object that must have at least two parts: 1) the internal description of the object itself (with respect to an object-centered frame); and 2) the transformation of the object-centered frame to the viewer-centered (image) frame. The reason for this decomposition is parsimony: different views of the object should have minimal impact on its description. This is achieved by factoring the object's description into two sets of parameters, one which is view-independent (the object-centered component) and one which is view-varying (the viewing transformation). Often a description of the object is known beforehand and the task reduces to finding the objectframe to viewer-frame transformation. This paper describes a method for handling this case: a known object is detected by finding changes in orientation, translation, and scale of the object from its canonical description. The method is a Hough technique and has the characteristic insensitivity to occlusion and noise.

Viewer Independent Shape Recognition

Relaxation in a conceptual hierarchy is proposed as a useful principle in the design of a visual recognition system. The domain of the implementation is Kanade's Origami world. The hierarchy is described along with the connection patterns that define the complete network. Advantages of this system are a uniform approach to intermediate and low level vision, inherent parallel approach and sharing of partial results to dynamically cut down the search for a correct match.

Daniel Sabbah

Papers

Viewer Independent Shape Recognition

Design of a highly parallel visual recognition system

Detecting object orientation from surface normals.