New computational solution to quantify synthetic material porosity from optical microscopic images

This paper presents a new computational solution to quantify the porosity of synthetic materials from optical microscopic images. The solution is based on an artificial neuronal network of the multilayer perceptron type and a backpropagation algorithm is used for training. To evaluate this new solution, 40 sample images of a synthetic material were analysed and the quality of the results was confirmed by human visual analysis. In addition, these results were compared with ones obtained with a commonly used commercial system confirming their superior quality and the shorter time needed. The effect of images with noise was also studied and the new solution showed itself to be more reliable. The training phase of the new solution was analysed confirming that it can be performed in a very easy and straightforward manner. Thus, the new solution demonstrated that it is a valid and adequate option for researchers, engineers, specialists and other professionals to quantify the porosity of materials from microscopic images in an automatic, fast, efficient and reliable manner.

[1]  João Manuel R. S. Tavares,et al.  Evaluation of multilayer perceptron and self-organizing map neural network topologies applied on microstructure segmentation from metallographic images , 2009 .

[2]  Li Miao-quan.  Microstructure evolution model based on deformation mechanism of titanium alloy in hot forming , 2005 .

[3]  S. J. Dwyer,et al.  On radiographic image analysis , 1976 .

[4]  L. Hein,et al.  An image analysis study of pit formation on Ti–6Al–4V , 2003 .

[5]  R. Herzog,et al.  Numerical simulation of segmentation cracking in thermal barrier coatings by means of cohesive zone elements , 2005 .

[6]  David L. Elliott,et al.  A Better Activation Function for Artificial Neural Networks , 1993 .

[7]  Abbas Ebnonnasir,et al.  Artificial neural network modeling for evaluating of epitaxial growth of Ti6Al4V weldment , 2006 .

[8]  J. Tavares,et al.  Brinell and Vickers Hardness Measurement Using Image Processing and Analysis Techniques , 2010 .

[9]  Ralph Müller,et al.  Architecture and properties of anisotropic polymer composite scaffolds for bone tissue engineering. , 2006, Biomaterials.

[10]  Julian R. Jones,et al.  Bioactive glass and hybrid scaffolds prepared by sol–gel method for bone tissue engineering , 2005 .

[11]  A. Bahrami,et al.  Prediction of porosity percent in Al–Si casting alloys using ANN , 2006 .

[12]  Koshun Iha,et al.  Artificial neural networks applied to epoxy composites reinforced with carbon and E-glass fibers: Analysis of the shear mechanical properties , 2007 .

[13]  Tommy W. S. Chow,et al.  Neural Networks and Computing - Learning Algorithms and Applications , 2007, Series in Electrical and Computer Engineering.

[14]  M. Zolensky,et al.  The porosity and permeability of chondritic meteorites and interplanetary dust particles , 1997 .

[15]  Hind Taud,et al.  Porosity estimation method by X-ray computed tomography , 2005 .

[16]  李晓丽,et al.  Microstructure evolution model based on deformation mechanism of titanium alloy in hot forming , 2005 .

[17]  A. L. Horovistiz,et al.  An image processing method for morphology characterization and pitting corrosion evaluation , 2002 .

[18]  R. R. Menezes,et al.  Obtenção de mulita porosa a partir da sílica da casca de arroz e do acetato de alumínio (Porous mullite obtained using silica from rice husk and aluminum acetate) , 2008 .

[19]  F. J. Ramirez-Fernandez,et al.  Gas sensitive porous silicon devices: responses to organic vapors , 2003 .

[20]  Carmen Serrano,et al.  Image classification based on color and texture analysis , 2000, IWISPA 2000. Proceedings of the First International Workshop on Image and Signal Processing and Analysis. in conjunction with 22nd International Conference on Information Technology Interfaces. (IEEE.

[21]  Yevgeniy V. Bodyanskiy,et al.  Neuro-Fuzzy Kolmogorov's Network for Time Series Prediction and Pattern Classification , 2005, KI.

[22]  Ferdinand van der Heijden.  Image Based Measurement Systems: Object Recognition and Parameter Estimation , 1995 .

[23]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[24]  V. H. C. de Albuquerque,et al.  Tool Effects on Hybrid Laminates Drilling , 2010 .

[25]  Ali Shokuhfar,et al.  Artificial neural network modeling of mechanical alloying process for synthesizing of metal matrix nanocomposite powders , 2007 .

[26]  Jan Kusiak,et al.  Modelling of microstructure and mechanical properties of steel using the artificial neural network , 2002 .

[27]  Kwan-Kyu Park,et al.  Protective effect of bioactive ceramics on liver injury: regulation of pro-inflammatory cytokins expression , 2009, Journal of materials science. Materials in medicine.

[28]  A. K. Pilkey,et al.  An evaluation of global thresholding techniques for the automatic image segmentation of automotive aluminum sheet alloys , 2004 .

[29]  Aidong Li,et al.  Fabrication of uniform porous alumina materials by radio frequency (RF) magnetron sputtering , 2008 .

[30]  Dong-li Sun,et al.  Artificial Neural Network Models for Predicting Flow Stress and Microstructure Evolution of a Hydrogenized Titanium Alloy , 2007 .

[31]  Prasad K. Yarlagadda,et al.  Prediction of welding parameters for pipeline welding using an intelligent system , 2002 .

[32]  Victor Hugo C. de Albuquerque,et al.  A new solution for automatic microstructures analysis from images based on a backpropagation artificial neural network , 2008 .

[33]  R. Langer,et al.  Designing materials for biology and medicine , 2004, Nature.

[34]  A. C. Spowage,et al.  Image segmentation and analysis for porosity measurement , 2007 .

[35]  Da‐Wen Sun,et al.  Automatic measurement of pores and porosity in pork ham and their correlations with processing time, water content and texture. , 2006, Meat science.

[36]  João Manuel R. S. Tavares,et al.  Evaluation of Delamination Damage on Composite Plates using an Artificial Neural Network for the Radiographic Image Analysis , 2010 .