Title :
A neural network structure for detecting straight line segments
Author_Institution :
Center for Inf. Sci. & Process., Tuiuti Univ. of Parana, Curitiba, Brazil
Abstract :
A new method for detecting one-pixel wide vertical, horizontal and diagonal line segments in binary images, is presented. It is based on using four slabs of neural networks, each of which is composed of a set layers. Each layer consists of a number of neurons that is determined by the slab type. The whole image is used as input to each slab, and the information processing in each slab occurs in parallel, decreasing, therefore, computation time and allowing hardware implementation. The method was tested with various types of binary images and the obtained results were satisfactory. In addition, the method was robust against random noise, such as straight lines impeded in a cloud of points
Keywords :
computational complexity; image processing; multilayer perceptrons; parallel processing; random noise; stability; binary images; computation time; hardware implementation; multilayer neural network slabs; neural network structure; one-pixel wide line segment detection; random noise robustness; straight line segment detection; Concurrent computing; Hardware; Image segmentation; Impedance; Information processing; Neural networks; Neurons; Noise robustness; Slabs; Testing;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.833513
