Recognition of wheat grain quality using log-hough representation and neural networks

• Autorzy: Mikrut Z. , Kubiak A.
• Języki publikacji: EN

Abstrakty

EN

Assessment of raw product quality constitutes one of the most important issues in the agricultural sectors of food production, processing and storage. In wheat grain quality assessment, the evaluation of the percentage of broken grains in a single variety sample is one of the most important criteria. In the present work, we propose a solution based on a computer vision system and neural networks. An algorithm which performs normalization of the size and rotation angle of a single grain image in the log-polar space is developed. The grain edge image is subsequently transformed to the accumulative log-Hough space and projected onto the coordinate system axes. The resulting representation undergoes classification and variety discrimination with the use of the Kohonen Self Organizing Map. The effectiveness of this representation has been verified with the use of a backpropagation neural network and the k-Nearest Neighbors method. The average classification rate within a single wheat variety exceeds 97%, which qualifies the method for practical applications.

Słowa kluczowe

EN

log-polar transform; log-Hough transform; wheat grain; shape recognition

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2008
• Tom: Vol. 17, No. 4
• Strony: 425--449
• Opis fizyczny: Bibliogr. 26 poz., rys., tab., wykr.

Twórcy

autor

Mikrut Z.

autor

Kubiak A.

• Institute of Automatics, AGH University of Science and Technology, Mickiewicza 30, 30-059 Krakow, Poland,

Bibliografia

• [1] Hough P. V. C.: Method and Means for Recognizing Complex Patterns, US Patent 3069654, 1962.
• [2] Freeman H. : Computer processing of line-drawing images, ACM Computing Surveys, 6(1), 57-98, 1974.
• [3] Schwartz E. L.: Spatial Mapping in the Primate Sensory Projection: Analytic Structure and Relevance to Perception, Biological Cybernetics, 25, 181-194, 1977.
• [4] Pratt W. K.: Digital Image Processing, John Wiley, New York, 1978.
• [5] Weiman C. F. R.: Polar exponential sensor arrays unify iconic and hough space representation, Proc. SPIE vol. 1192: Intelligent Robots and Computer Vision VIII, 832-842, 1989.
• [6] Leavers V. F.: Shape detection in computer vision using the hough transform, Springer-Verlag, London, 1992.
• [7] Sandini G., Tistarelli M.: Vision and space-variant sensing, In: H. Wechsler ed., Neural Networks for Perception, Academic Press Inc., Boston, 1992.
• [8] Wilson J. C., Hodgson R. M.: Log-polar mapping applied to pattern representation and recognition, in: L. Shapiro, A. Rosenfeld eds., Computer Vision and Image Processing, Academic Press Inc., Boston, 1992.
• [9] Lee S., Choi Y.: Unconstrained handwritten zip code recognition, Proc. WCNN, Portland, 1993.
• [10] Liao K., Paulsen M. R., Reid J. F., Ni B. C., Bonifacio-Maghirang E. P.: Corn kernel breakage classification by machine vision using a neural network classifier, Trans, of the ASAE, 36(6), 1949-1953, 1993.
• [11] Buermann M., Schmid R., Reitz P.: Bruchkornbestimmung-atomatisiertes verfahren mit digitaler bildanalyse, Landtechnik 4, 200-201, 1995.
• [12] Deck S. H., Morrow C. T., Heinemann P. H., Sommer III H. J.: Comparison of neural network and traditional classifier for machine vision inspection of potatoes, Applied Engineering in Agriculture, 11(2), 319-326, 1995.
• [13] Kohonen T.: Self-organizing maps, Springer-Verlag, Berlin Heidelberg, 1995.
• [14] Ghazanfari A., Irudayara J., Kusalik A.: Grading pistachio nuts using neural network approach, Trans, of the ASAE, 39(6), 2319-2324, 1996.
• [15] Ritter G. X., Wilson J. N.: Computer vision algorithms in image algebra, CRC Press, Boca Raton, 1996.
• [16] Sakai N., Yonekawa S., Matsuzaki A.: Two dimensional image analysis of the shape of rice and its application to separating varieties, J. of Food Engineering, 27, 397- 407, 1996.
• [17] Ghazanfari A., Wulfsohn D., Irudayara J.: Machine vision grading of pistachio nuts using gray-level histogram, Canadian Agricultural Engineering 40(10), 61- 66, 1998.
• [18] Tadeusiewicz R., Mikrut Z.: Neural-based object recognition support: From Classical Preprocessing to Space-Variant Sensing, Proc. NC '98, Vienna, Austria, 463-468, 1998.
• [19] Chtioui Y., Panigrahi S., Backer L. F.: Rough sets theory as a pattern classification tool for quality assessment of edible beans, Trans. of the ASAE, 42(4), 1145-1152, 1999.
• [20] Duin R. P. W.: PRTools_3: A matlab toolbox for pattern recognition, Delft University of Technology, 2000.
• [21] Leavers V. F.: Use of the two-dimensional radon transform to generate a taxonomy of shape for the characterization of abrasive powder particles, IEEE Trans, on PAMI. 1411-1423, 2000.
• [22] Majumdar S., Jayas D. S.: Classification of cereal grain using machine vision. I morphology models. Transaction of the ASAE, 43(6), 1669-1675, 2000.
• [23] Schneider H., Kubiak A.: Erkennen von Bruchkornern mit neuronalen netzcn. Bornimer Agrartechnishe Berichte, 25, 7-13, 2000.
• [24] Mikrut Z.: Recognition of objects normalized in Log-polar space using kohonen networks, Proc. ISPA '01, Pula, Croatia, 308-312, 2001.
• [25] Kubiak A., Mikrut Z.: The application of log-Hough transform and neural networks to identify broken wheat grains. Automatics AGH UST 8(3), 477- 486 (in Polish), 2004 .
• [26] Paliwal J., Jayas D. S., Visen N. S., White N. D. G.: Quantification of variations in machine-vision-computed features on cereal grains, Canadian Biosystems Engineering, 47, 7.1-7.6, 2005.