1,721,054 research outputs found
Particle Identification By Image Processing
No full textThe paper reviews techniques for obtaining and processing images of particles and objects (irradiation, response, surveying, storage and analysis). It presents the methodologies thanks to which images can be classified and recognised (detection of domains, boundaries, shapes and textures) with a view to detecting correlations between the information provided by the images and the physical and chemical properties of the examined particles. It discusses procedures for recognizing the boundaries of images of particles, for analysing their properties (geometrical, Fourier series, fractals, etc.) and for recognizing the structures and textures of multi-component particles. The instruments used to acquire and store the images and the hardware needed to process the digitized information are described and analysed. The software needed to analyse the data (loading, color-level correction, enhancement, filtering, thresholding and labelling) are presented. Procedures for classifying vector structures that may be used to characterize images of individual particles (pattern vectors) or classes of particles (feature vectors) are discussed and those which are used to recognize particles are analysed. Applications of the above methodologies and several case studies concerning mineral grains (free and associated), polished sections of minerals, macerals, inorganic and organic materials are described
Image Processing Application to Particulate Solids Identification
No full textThe subject of particulate solid identification is examined from the point of view of image analysis applications. Many different conditions are taken into consideration: i) individual particles or particles in bulk; ii) standing or flowing objects; iii) B&W or RGB colour images; iv) the outline or the inside of the image domains; v) Fourier or Fractal analysis of particle boundary; vi) particle domain characterisation by pictorial or textural analysis; vii) feature extraction; viii) recognition and classification by classic statistical methods and/or ix) innovative methods as neural networks
STATISTICAL ADAPTIVE AND NEURAL NET CLASSIFIERS APPLIED TO SOLID WASTE PROCESSING: A CRITICAL COMPARISON Statistical adaptive and neural network classifiers applied to solid waste processing: a critical comparison
No full textThe adoption, in these last years, of specialised equipment or complex processing architectures developed to separate solid waste materials, resulting from the selective collection of solid urban waste (equipment or manufactured goods dismantling at the end of their life cycle) requires more and more control systems able to “qualify” the products during the processing. Such a goal, when implemented “on-line”, is usually realised in two steps. The attributes (physical, chemical, morphological, morphometrical, textural, etc.) of the materials resulting from processing are detected and numerically modelled. The resulting feature vector is then “handled” by a software architecture performing the required recognition/classification procedure and defining the quality of the investigated products. “Feed-back” or “feed-forward” control strategies can be then applied to improve equipment or processing architectures performances. In this paper are analysed and described the problems encountered and the results achieved when statistical adaptive classifiers or a neural net based architectures are adopted to define an “artificial intelligence software unit” able to perform the recognition of several solid waste materials, at industrial recycling processing plant level, starting from their preliminary optical recognition
Cullets (Glass Fragments) Quality Control by Artificial Vision: a Textural Based Approach
No full textGlass fragments (cullets) to be recycled present different market values according to their colour. Glass recycling plants perform cullets sorting mainly discriminating coloured glasses from white and half white glasses. Cullets which are collected without distinctions of colour, can be used primarily for the production of green glass and only in part for the production of yellow glass. The production of white glass requires that only cullets of that colour be employed. At present, machines for the separation of cullets according to colour are not capable of producing an efficient classification of all the different types. In this paper are analysed the possibility that could be offered by the adoption of a colour imaging based approach to realise cullets sorting, analysing the textural attributes. This study was addressed on the effects that cullets surface status and characteristics produce on the detected colour-textural characteristics and they can influence the further classification
Cullets (glass fragments) quality control by artificial vision: a color based approach
No full textGlass fragments (cullets) to be recycled present different market values according to their color. Glass recycling plants perform cullets sorting mainly discriminating colored glasses from white and half white glasses; furthermore sorting presents some other technological limits concerning the minimum cullet size, about 45 mm, that is possible to analyze. In this paper are analyzed the possibility that could be offered by the adoption of a color imaging based approach to realize cullets sorting. This study was mainly focused on the effects that cullets surface status and characteristics produce on the detected color digital spectra and how they can influence the further classification. All the tests have been performed on glass samples as they result after the cleaning stage, impurities removal, of an industrial glass recycling plant
Digital spectrometry applied to glass and ceramic sorting
No full textMaterials surface characteristics can be investigated analysing their spectral response when properly energised by a suitable source. When the source is represented by a light spectra of known characteristics the surface material response can thus be evaluated adopting a spectrophotometric approach. The analyses of the detected spectra can give useful information concerning the material characteristics and/or surface properties and status. In this perspective digital spectrophotometry can be considered as one of the basic techniques to characterise materials. The application of such a technique is usually confined in “high-tech” environments and can results quite expensive and difficult to apply in industrial “on-line” processes. In this paper recent advances in imaging spectrophotometry devices and techniques are presented with reference to the possibility to recognise different glass fragments (cullets) according to their colour and the presence of transparent polluting fragments, that is the distinction between glass from ceramic glass fragments. The work will identify the main factors influencing the selection of the proper hardware to perform the analysis and the different possible solutions in terms of installations and plant layouts. Case studies will be presented and analysed with particular reference to different classes of bulk products, glass and ceramic glass waste product to recycle, presenting different physical and surface status properties
ORE LIBERATION MODELING BY MINERALS TOPOLOGICAL EVALUATION
No full textLiberation of valuable minerals from multiphase ores is one of the main goat of a size reduction process. Great importance is thus assumed by models able to give a detailed provisional description of the ore liberationcomminution process. In the definition of these models, the hypotheses usually adopted for ore textural and structural characterisation are dramatically simplified due to the great difficulty of translating and incorporating such characteristics in numerical form. This paper describes the possibilities offered by a full colour multispectral image analysis system for evaluating the liberation characteristics of an ore. The procedures and the related algorithms have been developed in order to permit a full recognition and morphological modelling of the different mineralogical species inside the images acquired by optical microscopy. A topological map containing a reduced body of data is related with the liberation characteristics of minerals. The system incorporates all the procedures able both to process the previously derived information and to test different comminution strategies based on the topological assessment of the species and the selected theoretical comminution net
Ore mineral particle morphologyand modelling by on-line optical systems
No full textIn the present work the possibilty to utilize the orphometrical and morphological characteristics of a particulate solids system in a slurry flow to monitorate and to control a continuos process is considered. This goal has been reached by mean of an optical system able to acquire, to handle and to process the pictorial information derived by a suitable hardware architecture designed to realize the best lighting, focusing and sampling conditions for the examined flow stream domain. The procedure has been tested using different flow stream slurries coming from different sections of a beneficiation plant. A suitable strategy and a consequent software architecture has been set up in order to assure to the system the necessary speed and the stability to achieve correct on-line mesurements and control
- …
