image analysis of leather

A paper has recently been published with Dr Malcolm Wilson, (Department of Computing and Immersive Technology, School of Science and Technology, University of Northampton ) and Professor Phil Picton (School of Science and Technology, University of Northampton ) as co-authors on image analysis of leather.

Saqib Kabeer, Geoff Attenburrow ,Phil Picton , Malcolm Wilson (2013)

Development of an image analysis technique for measurement of Poisson’s ratio for viscoelastic materials: application to leather.

J Mater Sci (2013) 48:744–749

DOI 10.1007/s10853-012-6789-0

Abstract

The application of a computerised image analysis system to simultaneously measure longitudinal and axial strain in naturally available anisotropic-viscoelastic material like leather is described. The results are used to calculate Poisson’s ratio and indicate that this parameter varies with position and orientation on the hide and depends on the degree of pre-existing fibre orientation.The origins of this dependency can be explained by a simple microstructural model. The practical implication of the findings for detecting lines of tightness maximum fibre’s orientation) is discussed.

The full paper can be found at: http://link.springer.com/content/pdf/10.1007%2Fs10853-012-6789-0 

Subjective Measurement of Leather Handle

A new paper looking a how experts in the leather industry assess leather quality is to be published in the The Amercian Leather Chemists Association Journal The Subjective Measurement of Leather Handle by Descriptive Sensory Analysis

Y. Wang , G. Attenburrow, P. Picton, S. Turner

Volume: 106      Number: 4    Abstract

Leather handle strongly relates to leather quality, and in the leather industries experts still manually assess it. In this paper a new approach, Descriptive Sensory Analysis, was applied when subjectively measure leather handle and thus a comprehensive handle profile was established. Ten attributes of leather samples were identified and quantified by a trained expert panel according to agreed procedures. Principal Component Analysis was used to reduce data dimensionalities and a conception 3D handle space was proposed and demonstrated to exhibit the handle attributes of leather. RESUMEN El comportamiento organoléptico de cuero está ligado fuertemente a la evaluación de calidad en el cuero, y en las industrias del cuero los expertos subjetivamente las evalúan por toque. En este artículo se presenta un nuevo enfoque, un Análisis de Descripción Sensorial, que se aplicó cuando el toque de cuero fue determinado subjetivamente, y luego un perfil descriptivo comprensivo fue establecido. Diez atributos de las muestras de cueros fueron identificados y cuantificados por un panel de expertos entrenados de acuerdo a los procedimientos previos acordados. Análisis de Componentes Principales se utilizó para reducir la redundancia de datos a una concepción del manejo en espacio 3D fue propuesto y demostrado efectivo para exhibir los atributos requeridos en la descripción del toque de cuero.

PREDICTING LEATHER HANDLE LIKE AN EXPERT BY ARTIFICIAL NEURAL NETWORKS

A paper has been recently published that combines artificial intelligence and leather science research looking at modelling the subjective assessment of leather handle.

Abstract

This study developed an artificial neural network model to predict the subjective assessment of leather handle by an expert using its measurable physical characteristics. A statistical method was applied to prune the inputs of the network and the “error band” conception was proposed during training.

More details can be found at:

Wang, Y., Picton, P., Turner, S. and Attenburrow, G (2011) Predicting Leather Handle like an Expert Artificial Neural Networks, Applied Artificial Intelligence, Volume 25, Issue 2  February 2011 , pages 180 - 192 ISSN: 0883-9514 DOI:10.1080/08839514.2011.545218