The Random Neural Network Model for Texture Generation

Abstract

The generation of artifical textures is a useful function in image synthesis systems. The purpose of this paper is to describe the use of the random neural network (RN) model developed by Gelenbe to generate various textures having different characteristics. An eight parameter model, based on a choice of the local interaction parameters between neighbouring neurons in the plane, is proposed. Numerical iterations of the field equations of the neural network model, starting with a randomly generated gray-level image, are shown to produce textures having different desirable features such as granularity, inclination, and randomness. The experimental evaluation shows that the random network provides good results, at a computational cost less than that of other approaches such as Markov random fields. Various examples of textures generated by our method are presented.

G-Networks and Their Applications to Machine Learning, Energy Packet Networks and Routing: Introduction to the Special Issue

“…The RNN learning algorithm was applied to video compression (Cramer and Gelenbe [22], Gelenbe et al [141]), to recognize textures (Gelenbe and Feng [79]), and tumors in magnetic resonance images of the human brain (Gelenbe, Feng, and Krishnan [80]). Other applications of the random neural network that do not require learning include function optimization (Gelenbe, Koubi, and Pekergin [99]) and texture generation (Atalay and Gelenbe [9], Atalay, Gelenbe, and Yalabik [10]). Applications of the RNN were published for video compression (Cramer, Gelenbe, and Bakircioglu [20,21]), complex recognition tasks (Abdelbaki, Gelenbe, and El-Khamy [1], Abdelbaki, Gelenbe, and Kocak [2], Abdelbaki et al [3], Aguilar and Gelenbe [8], Gelenbe, Ghanwani, and Srinivasan [85], Hocaoglu et al [155]), and to the sensory search of patterns and objects (Gelenbe and Cao [74], Gelenbe and Koçak [97], Gelenbe, Koçak, and Wang [98]).…”

The Random Neural Network Applied to an Intelligent Search Assistant

“…The RNN represents more closely how signals are transmitted in many biological neural networks where they actual travel as spikes or impulses, rather than as analogue signal levels. It has been used in different applications including network routing with cognitive packet networks [10], search for exit routes for evacuees in emergency situations [11,12], pattern based search for specific objects [13], video compression [14], and image texture learning and generation [15].…”

Texture Classification and Retrieval Using the Random Neural Network Model

“…After the random neural network model (RNN) have introduced by Gelenbe [24,25], it is used for solving several different problems [26,27,28,29,30,31,32,33,34,35,36]. In their studies, Atalay, Gelenbe and Yalabik [31,32] propose a texture generation algorithm using RNN model, and they obtain good results and concluded that RNN can be used to represent and analyze texture.…”

“…In their studies, Atalay, Gelenbe and Yalabik [31,32] propose a texture generation algorithm using RNN model, and they obtain good results and concluded that RNN can be used to represent and analyze texture. Furthermore, there are many areas in remote sensing which textural information extracted from aerial imagery play an important role and lots of research are done recently on this topic.…”