Computers & Geosciences 27 (2001) 1111–1117 Characterisation of flotation froth colour and structure by machine vision Giuseppe Bonifazi a, *, Silvia Serranti a , Fabio Volpe b , Riccardo Zuco b a Dipartimento di Ingegneria Chimica, dei Materiali, delle Materie Prime e Metallurgia, Universita ` degli Studi di Roma ‘‘La Sapienza’’ Via Eudossiana 18, 00184, Roma, Italy b Euroimage SpA, Roma, Italy Received 1 July 1999; received in revised form 28 February 2000; accepted 3 March 2000 Abstract It is well known and well recognised that flotation is a process that is complex to monitor and study if a classical approach based on the evaluation of the signals resulting from sensors is adopted. Sensors are usually strategically positioned in the bank cells and detect global process variables such as pH, reagent addition, froth level, on-stream chemical analysis, particle size distribution, etc. In the last ten years several studies have been carried out with the main goal to utilise imaging techniques to detect froth bubbles characteristics and to evaluate the flotation process performance. In this paper an approach of this type is described. More specifically, image processing techniques to automatically measure the colour and the structure of the froth bubbles are presented and the results are discussed. All the investigations are carried out on digital sample images collected in an industrial flotation plant operating in steady- state conditions. The colour analysis is performed on the whole surface of the froth images considering different colour reference systems (RGB, HSV, HSI); the morphological measurements are obtained after the application of selected enhancement and segmentation techniques, necessary to consider the bubbles as separate domains. The multiple correlation analysis performed between froth mineral concentrations (Cu, MgO, Zn and Pb content) and the extracted colour and structure parameters are good in most situations. # 2001 Elsevier Science Ltd. All rights reserved. Keywords: Flotation process; Froth colour; Froth structure; Image processing 1. Introduction Froth flotation is a process strongly influenced by many factors related to the floated ore (grade, particles size distribution, degree of liberation, surface properties, etc.) and with the process variables (reagent content, pH, froth speed, etc.). The control of the process is in fact very difficult to realise even if many studies have been devoted to this subject. A contribution to the solution of this problem can be given by the application of digital imaging techniques to the froth images directly acquired in the plant. Flotation froth colour and structure are commonly recognised as important visual features in the control of the industrial flotation performance. In this perspective, the visual appearance of a froth surface can be analysed using digital imaging procedures able to describe the morphological (e.g. Sadr-Kazemi and Cilliers, 1997) and colour character- istics (e.g. Oestreich et al., 1995) of the froth itself. Such characteristics can be in fact correlated, in a quantitative way, with the chemical parameters measured in the flotation plant, allowing a better understanding of the process (e.g. Moolman et al., 1994). In this study the froth colour and structure determined by image analysis techniques, were correlated with the mineral concentra- tion analysed in the froth. Adopting a multiple correlation analysis considering both colour and mor- phological parameters, it is shown that good correlation *Corresponding author. Fax: +39-06-4458-5618. E-mail address: bonifazi@imagemp.ing.uniroma1.it (G. Bonifazi). 0098-3004/01/$ - see front matter # 2001 Elsevier Science Ltd. All rights reserved. PII:S0098-3004(00)00152-7