Application of global thresholding in bread porosity evaluation

Year 2015, , 111 - 115, 13.11.2015

Atanaska Bosakova-ardenska

https://doi.org/10.18201/ijisae.30637

Abstract

The white bread is one of most popular food in Bulgaria. Its quality is defined by standards and control is also standardized. The white bread has four groups of quality parameters - organoleptic, physicochemical, chemical contaminants and microbiological. This paper presents one research over white bread porosity which is one of physicochemical parameters. By standard evaluation of bread porosity is time expensive procedure. Current research proposes one fast computer based approach for white bread porosity evaluation. In experiments are used three brands white breads. The images of breads are binarized with four known algorithms and coefficient of diversity (ratio of white pixels and all image pixels) for resulting binary images is calculated. This coefficient corresponds with bread porosity. Experimental results show that one of these algorithms – Vector Median Thresholding, is appropriate for bread porosity evaluation.

Keywords

Global Thresholding, Vector Median Thresholding, White Bread, Porosity Evaluation.

References

• Approved Standard "BULGARIA" - 02/2011 - Bread "White", Ministry of Agriculture and Food, Sofia, 2011 (in Bulgarian)
• Gonzalez R., R. Woods, Digital image processing (second edition), Prentice Hall, 2002
• Abutaleb A., Automatic Thresholding of Gray-Level Pictures Using Two-Dimensional Entropy, COMPUTER VISION, GRAPHICS AND IMAGE PROCESSING, 1989, vol. 47, Issue 1, pp 22-32
• C. Stauffer, W.E.L. Grimson, Adaptive background mixture models for real-time tracking, Computer Vision and Pattern Recognition, 1999
• Tsai, W-H, Moment-Preserving Thresholding: A New Approach, in CVGIP, vol.29, pp 377-393, 1985
• A. Andreeva, Hr., L. Kostadinova-Georgieva, At. Bosakova-Ardenska, Evaluation of porosity of bread by image processing, Scientific conference with international participation „Food science, engineering and technologies – 2013“, Scientific works Volume LX, Plovdiv, 2013, pp. 1136-1139 (in Bulgarian)
• Otsu, N., A threshold selection method from Gray-Level Histograms, IEEE Transactions man and cybernetics, vol. smc-9, no. 1, 1979, pp. 62-66
• Andreeva H., A. Bosakova-Ardenska, L. Kostadinova-Georgieva, Comparison of two methods for automatic image binarization, Scientific conference “Computer science and technologies”, Varna, 2014, ISSN 1312-3335, pp 138-143
• http://www.djvu-soft.narod.ru/bookscanlib/project.htm
• Andreeva H., N. T. Katrandjiev, Possibilities for analysis and assessment of quality characteristics of flour-based food on the base of image processing in Matlab, Scientific conference with international participation „Food science, engineering and technologies – 2013“, Scientific works Volume LIX, Plovdiv, 2012, pp. 680-684 (in Bulgarian)
• Krasteva I., L. Kostadinova-Georgieva, H. Andreeva, S. Nikolova, Calibration of laboratory machine vision system for quality control of food products, Scientific conference with international participation „Food science, engineering and technologies – 2013“, Scientific works Volume LX, Plovdiv, 2013, pp. 1148-1152 (in Bulgarian)