Learning Hough Transform: A Neural Network Model

2001 ◽  
Vol 13 (3) ◽  
pp. 651-676 ◽  
Author(s):  
Jayanta Basak
Keyword(s):  
Neural Network ◽  
Neural Network Model ◽  
Hough Transform ◽  
Visual Information ◽  
Two Dimensional ◽  
Large Space ◽  
Space Requirement ◽  
Straight Line ◽  
Higher Dimensional ◽  
Efficient Representation

A single-layered Hough transform network is proposed that accepts image coordinates of each object pixel as input and produces a set of outputs that indicate the belongingness of the pixel to a particular structure (e.g., a straight line). The network is able to learn adaptively the parametric forms of the linear segments present in the image. It is designed for learning and identification not only of linear segments in two-dimensional images but also the planes and hyperplanes in the higher-dimensional spaces. It provides an efficient representation of visual information embedded in the connection weights. The network not only reduces the large space requirement, as in the case of classical Hough transform, but also represents the parameters with high precision.

MAGNOCELLULAR PATHWAY FOR ROTATION INVARIANT NEOCOGNITRON

1993 ◽  
Vol 04 (01) ◽  
pp. 43-54 ◽  
Author(s):  
CHRISTOPHER HIAN-ANN TING
Keyword(s):  
Neural Network ◽  
Visual System ◽  
Neural Network Model ◽  
Visual Information ◽  
Input Pattern ◽  
Arbitrary Orientation ◽  
Magnocellular Pathway ◽  
Rotation Invariant ◽  
Parvocellular Pathway ◽  
Simulation Programme

In the mammalian visual system, magnocellular pathway and parvocellular pathway cooperatively process visual information in parallel. The magnocellular pathway is more global and less particular about the details while the parvocellular pathway recognizes objects based on the local features. In many aspects, Neocognitron may be regarded as the artificial analogue of the parvocellular pathway. It is interesting then to model the magnocellular pathway. In order to achieve "rotation invariance" for Neocognitron, we propose a neural network model after the magnocellular pathway and expand its roles to include surmising the orientation of the input pattern prior to recognition. With the incorporation of the magnocellular pathway, a basic shift in the original paradigm has taken place. A pattern is now said to be recognized when and only when one of the winners of the magnocellular pathway is validified by the parvocellular pathway. We have implemented the magnocellular pathway coupled with Neocognitron parallel on transputers; our simulation programme is now able to recognize numerals in arbitrary orientation.

A Solution for Two-Dimensional Mazes with Use of Chaotic Dynamics in a Recurrent Neural Network Model

2004 ◽  
Vol 16 (9) ◽  
pp. 1943-1957 ◽  
Author(s):  
Yoshikazu Suemitsu ◽  
Shigetoshi Nara
Keyword(s):  
Neural Network ◽  
State Space ◽  
Network Model ◽  
Neural Network Model ◽  
Chaotic Dynamics ◽  
Dimensional Space ◽  
Dynamical Structure ◽  
Two Dimensional ◽  
Time Step ◽  
The Neural Network

Chaotic dynamics introduced into a neural network model is applied to solving two-dimensional mazes, which are ill-posed problems. A moving object moves from the position at t to t + 1 by simply defined motion function calculated from firing patterns of the neural network model at each time step t. We have embedded several prototype attractors that correspond to the simple motion of the object orienting toward several directions in two-dimensional space in our neural network model. Introducing chaotic dynamics into the network gives outputs sampled from intermediate state points between embedded attractors in a state space, and these dynamics enable the object to move in various directions. System parameter switching between a chaotic and an attractor regime in the state space of the neural network enables the object to move to a set target in a two-dimensional maze. Results of computer simulations show that the success rate for this method over 300 trials is higher than that of random walk. To investigate why the proposed method gives better performance, we calculate and discuss statistical data with respect to dynamical structure.

Image Intelligent Detection Based on the Gabor Wavelet and the Neural Network Combined Neural Network

2016 ◽  
Vol 13 (10) ◽  
pp. 7074-7079
Author(s):  
Yajun Xu ◽  
Fengmei Liang ◽  
Gang Zhang ◽  
Huifang Xu
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Network Model ◽  
Neural Network Model ◽  
Gabor Wavelet ◽  
Two Dimensional ◽  
Human Face ◽  
Gabor Wavelet Transform ◽  
Gabor Function ◽  
The Neural Network

This paper first analyzes the one-dimensional Gabor function and expands it to a two-dimensional one. The two-dimensional Gabor function generates the two-dimensional Gabor wavelet through measure stretching and rotation. At last, the two-dimensional Gabor wavelet transform is employed to extract the image feature information. Based on the BP neural network model, the image intelligent test model based on the Gabor wavelet and the neural network model is built. The human face image detection is adopted as an example. Results suggest that, when the method combining Gabor wavelet transform and the neural network is used to test the human face, it will not influence the detection results despite of complex textures and illumination variations on face images. Besides, when ORL human face database is used to test the model, the human face detection accuracy can reach above 0.93.

Bifurcation in two-dimensional neural network model with delay

2005 ◽  
Vol 26 (2) ◽  
pp. 210-217 ◽  
Author(s):  
Wei Jun-jie ◽  
Zhang Chun-rui ◽  
Li Xiu-ling
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Two Dimensional

Two-dimensional neural network model of the primate saccadic system

1994 ◽  
Vol 7 (6-7) ◽  
pp. 1115-1135 ◽  
Author(s):  
Kuniharu Arai ◽  
Edward L. Keller ◽  
Jay A. Edelman
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Two Dimensional ◽  
Saccadic System

scholarly journals Evaluation of Two-Dimensional Angular Orientation of a Mobile Robot by a Modified Algorithm Based on Hough Transform

2018 ◽  
Vol 18 (2) ◽  
pp. 112-122
Author(s):  
Dmitry N. Aldoshkin ◽  
Roman Y. Tsarev
Keyword(s):  
Mobile Robot ◽  
Hough Transform ◽  
Dimensional Space ◽  
Two Dimensional ◽  
Angular Orientation ◽  
Polygonal Chain ◽  
Straight Line ◽  
Robustness To Noise ◽  
Surrounding Space ◽  
Straight Lines

Abstract This paper proposes an algorithm that assesses the angular orientation of a mobile robot with respect to its referential position or a map of the surrounding space. In the framework of the suggested method, the orientation problem is converted to evaluating a dimensional rotation of the object that is abstracted as a polygon (or a closed polygonal chain). The method is based on Hough transform, which transforms the measurement space to a parametric space (in this case, a two-dimensional space [θ, r] of straight-line parameters). The Hough transform preserves the angles between the straight lines during rotation, translation, and isotropic scaling transformations. The problem of rotation assessment then becomes a one-dimensional optimization problem. The suggested algorithm inherits the Hough method’s robustness to noise.

Sign in / Sign up

Export Citation Format

Share Document