Particle Identification by Image Processing

Bonifazi, Giuseppe; Massacci, P.

doi:10.14356/kona.1996017

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two main procedures based on the Fourier analysis of a profile may be applied to the morphologic characterization of a particle [1]. The first method is based on Fixed Angular Boundary Sampling (FABS) [47] and the second is based on Fixed Boundary Segment Sampling (FBSS) [48].…”

Section: Fourier Analysismentioning

confidence: 99%

Effect of Comminution on Particle Shape and Surface Roughness and Their Relation to Flotation Process: A Review

Ahmed

2009

JES. Journal of Engineering Sciences

View full text Add to dashboard Cite

Section: Fourier Analysismentioning

confidence: 99%

Effect of Comminution on Particle Shape and Surface Roughness and Their Relation to Flotation Process: A Review

Ahmed

2009

JES. Journal of Engineering Sciences

View full text Add to dashboard Cite

“…No feedback from the environment is provided during learning . A more successful classification may be achieved by feedforward neural networks using a back-propagation learning algorithm [ 13,18]. Competitive learning is applied when no information regarding class membership of input patterns is available.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

“…A number of methods, incl uding determination of vario us shape factors (compacity, Feret diameter, irregularity factors , sphericity, as pect ratio, etc. ), fracta l dimensions, crystal sig natures and their derivatives, geometrical methods of approximation to polygons, as wel l as Fo urier coefficients have been used a nd discussed [ 1- 12,18]. However, most of these shape descriptors either do not have the prerequisites of ideal shape parameters, namely invariance to tran slation, rotation , scal ing and the starting point, or are reported as a single value factor which resu lts in a low discrimi na tin g powe r amo ng various s hapes.…”

Section: Introductionmentioning

confidence: 99%

Classification of Crystal Shape Using Fourier Descriptors and Mathematical Morphology

Bernard‐Michel¹,

Rohani²,

Pons³

et al. 1997

Part & Part Syst Charact

View full text Add to dashboard Cite

The performances of two image analysis methods for the classification of some randomly selected KCl crystals from a crystallization experiment into four two‐dimensional classes (nearly circular, square, rectangular and irregular) are compared. The first method uses the first 15 Fourier descriptors of the angular bend as a function of arc length of the periphery of the particles, whereas the second method is based on a combination of seven geometrical and morphological parameters of the crystals using a commercially available image analysis system (Visilog, Noesis, Orsay, France). The feedforward neural network with back‐propagation learning algorithm and discriminant factorial analysis (STATlab, SLP, Ivry sur Seine. France) were found to classify the crystals with similar success.

show abstract

“…A systematic imaging based procedure [2] was applied on the particle products [3] resulting from the different criogenic comminution tests. Results envisaged as particles present a different shape ( Figure 1) according to the different comminution temperature applied ( Figure 2).…”

mentioning

confidence: 99%

Morphological and Morphometrical Characteristics of Particulate Solids To Recycle Resulting from Electric Cables Crio-comminution.

et al. 2003

Self Cite

View full text Add to dashboard Cite

Waste disposal is nowadays a well-known critical problem for environmental protection. For this reason, in the last years, the research in the field of waste recycling increased more and more with the specific target to find solutions oriented to reduce the environmental impact of waste and to recover precious metals and other useful materials. In this perspective it assumes great importance the possibility to recover waste products resulting from material goods dismantling, or from products at the end of their "life cycle", or simply from "common" household or industrial waste [1]. Electric cables represent a great family belonging to such a class of products.The possibility to recover metals from electric cables has been investigated in this work. Electric cables are usually constituted by various components, different for chemical-physical attributes, that is: i) conductors (i.e. copper or aluminum), ii) shield materials, usually metallic, iii) insulating materials (i.e. PVC, PE, rubber) and iv) coating materials (i.e plastic or metals). The study was particularly addressed to verify the effect of the comminution of such products when performed at different temperatures, ranging from room up to criogenic conditions, utilizing different cooling media as CO 2 (-20°C) and nitrogen (-100°C). More specifically the parameters investigated have been particles morphological and morphometrical attributes and their degree of liberation, being these parameters of primarily importance in respect of the further electrostatic separation processes (particle surface charge and flow modalities) and final reuse (mixture properties).A systematic imaging based procedure [2] was applied on the particle products [3] resulting from the different criogenic comminution tests. Results envisaged as particles present a different shape (Figure 1) according to the different comminution temperature applied ( Figure 2). Particle profile roughness seems to be particularly influenced by temperature ( Figure 3). More specifically the results obtained through criogenic comminution show, in average, a lower size class distribution for the products in comparison with those obtainable at room temperature. Moving from room temperature to CO 2 and nitrogen environmetal controlled comminution, particles show a decreasing value of fractal dimension [4], of Feret diameter and of the area/perimeter ratio. Such results have to be economically analyzed and compared in respect of the different level of energy required for the two approaches.

show abstract

Particle Identification by Image Processing

Abstract: This paper reviews techniques for obtaining and processing images of particles and objects (irradiation, response, surveying, storage and analysis)

Cited by 6 publications

References 12 publications

Effect of Comminution on Particle Shape and Surface Roughness and Their Relation to Flotation Process: A Review

Effect of Comminution on Particle Shape and Surface Roughness and Their Relation to Flotation Process: A Review

Classification of Crystal Shape Using Fourier Descriptors and Mathematical Morphology

Morphological and Morphometrical Characteristics of Particulate Solids To Recycle Resulting from Electric Cables Crio-comminution.

Contact Info

Product

Resources

About