COLOUR IMAGE RECOGNITION BASED ON SINGLE-LAYER NEURAL NETWORKS OF MIN/MAX NODES Radek Holota * Abstract: An image recognition system can be based on a single-layer neural network composed of Min/Max nodes. This principle is easy to use for greyscale images. However, this article deals with the possibilities of utilising neural nets for colour image recognition. Several principles are demonstrated and tested by recently developed software. A new modified Min/Max node Single Layer Net, suitable for recognition in HSV (Hue Saturation Value) colour space, is presented in this paper. Key words: Neural network, image recognition, Min/Max nodes, colour, face recognition Received: March 9, 2009 Revised and accepted: August 21, 2012 1. Introduction Image recognition systems are now subject to intensive development. One of the possibilities is that of utilising neural nets. This option has been the main subject of cooperation between the Dept. of Applied Electronics and Telecommunications, University of West Bohemia, and the Dept. of Electrical and Electronic Engineering (now Electronic and Computer Engineering) at Brunel University, U.K. over the past two decades. A great part of this research work is documented in the literature [1, 2, 3, 4]. One topic of cooperation was focused on single-layer neural nets with Min/Max nodes [5, 1]. The single-layer network using Min/Max nodes is similar to the technique of Aleksander and Stonham [6] using logic nodes and based upon the original concepts of Bledsoe and Browning [7]. The network of Min/Max nodes could respond directly to multi-level values and so it could provide powerful pattern recognition properties. The natural progression of this technique was to consider the recognition of coloured images and the feasibility of such a system was later proposed [2, 3]. * Radek Holota Department of Applied Electronics and Telecommunications, Faculty of Electrical Engineering, University of West Bohemia, Univerzitni 26, 306 14 Pilsen, The Czech Republic, phone: +420 377 634 231, E-mail: holota5@kae.zcu.cz c ⃝ICS AS CR 2012 395