BPNN Approach in Pixel Classification based Precision Segmentation for Agriculture Images

Abstract

Segmentation is a main process in the object recognition. Many times success of object recognition process depends on the precision of segmentation. The application of image processing technology, in the agricultural research, has made significant development [1]. With the advance processing capacity, soft computing and computer has attracted it as an alternative to human work [2]. In this paper, application of BPNN is plaid for segmenting gerbera flowers from offline Polyhouse images. Image segmentation is the foundation of many image analysis problems; any segmentation method with precision can positively influence the analysis process. [3] The agriculture images are subject to more complexes to process as they contain different size; shape objects and suffers from illumination, noise making segmentation more erroneous. The current study uses offline images captured from the natural scene of Polyhouse at arbitrary time. The flowers are segmented using Back propagation neural network. Total 30 images are used in the experiment where 10 images are used as training set and 20 images are used for testing data set. The input vector for the BPNN consist the color feature vector in form of R, G, B values extracted from every pixel, and BPNN classification divides the pixels into non flower pixel or flower pixel regions, giving segmentation.

References

• A Processing in Agriculture?: A Survey," vol. 52, no. 2, pp. . Vibhute and S. K. Bodhe, "Applications of Image 34–40, 2012.
• F. Mendoza, P. Dejmek, and J. M. Aguilera, "Predicting Ripening Stages of Bananas ( Musa cavendish ) by Computer Vision," no. 1, 1997.
• A. A. Ahmed, M. Vias, N. G. Iyer, C. Caldas, and J. D. Brenton, "Microarray segmentation methods significantly influence data precision. ," Nucleic Acids Res. , vol. 32, no. 5, p. e50, Jan. 2004.
• S. Weizheng, W. Yachun, C. Zhanliang, and W. Hongda, "Grading Method of Leaf Spot Disease Based on Image Processing," 2008 Int. Conf. Comput. Sci. Softw. Eng. , pp. 491–494, 2008.
• I. S. Ahmad, J. F. Reid, M. R. Paulsen, and J. B. Sinclair, "Color Classifier for Symptomatic Soybean Seeds Using Image Processing," Plant Dis. , vol. 83, no. 4, pp. 320–327, Apr. 1999.
• G. Anthonys and N. Wickramarachchf, "An Image Recognition System for Crop Disease Identification of Paddy fields in Sri Lanka," pp. 403–407, 2009.
• H. Saad, A. P. Ismaie, N. Othman, M. H. Jusohl, N. A. Ahmad, and K. P. Pinang, "Recognizing The Ripeness Of Bananas Using Artificial Neural," pp. 536–541, 2009.
• S. Cubero, E. Moltó, N. Aleixos, A. Gutiérrez, F. Juste, and J. Blasco, "Machine Vision System for the In-line Inspection of Fruit on a Mobile Harvesting Platform in Field Conditions," no. August 2010, pp. 26–27.
• F. J. Adamsen, T. A. Coffelt, J. M. Nelson, E. M. Barnes, and R. C. Rice, "Crop Ecology , Management & Quality Method for Using Images from a Color Digital Camera to Estimate Flower Number," pp. 704–709, 1997.
• A. -X. Hong, G. Chen, J. -L. Li, Z. -R. Chi, and D. Zhang, "A flower image retrieval method based on ROI feature. ," J. Zhejiang Univ. Sci. , vol. 5, no. 7, pp. 764–72, Jul. 2004.
• M. Soltani and M. Omid, "A New Mathematical Modeling of Banana Fruit and Comparison with Actual Values of Dimensional Properties," vol. 4, no. 8, pp. 104–113, 2010.
• F. Cointault and P. Gouton, "Texture or Color Analysis in Agronomic Images for Wheat Ear Counting," 2007 Third Int. IEEE Conf. Signal-Image Technol. Internet-Based Syst. , pp. 696–701, Dec. 2007.
• A. Kohan, A. M. Borghaee, M. Yazdi, S. Minaei, and M. J. Sheykhdavudi, "Robotic Harvesting of Rosa Damascena Using Stereoscopic Machine Vision," vol. 12, no. 2, pp. 231–237, 2011.
• T. Arif, Z. Shaaban, L. Krekor, and S. Baba, "Object Classification Via Geometrical , Zernike And Legendre Moments," 2009.
• M. H. Razali, W. I. Wan Ismail, A. R. Ramli, M. N. Sulaiman, and M. H. Harun, "Development of Image Based Modeling for Determination of Oil Content and Days Estimation for Harvesting of Fresh Fruit Bunches," Int. J. Food Eng. , vol. 5, no. 2, Jan. 2009.
• A. Z. Chitade, "Colour Based Image Segmentation Using K-Means Clustering," vol. 2, no. 10, pp. 5319–5325, 2010.
• R. S. Sarkate, N. V. Kalyankar, and P. B. Khanale, "Application Of Computer Vision And Color Image Segmentation For Yield Prediction Precision," 2013 Int. Conf. Inf. Syst. Comput. Networks, pp. 9–13, Mar. 2013.
• N. N. Kurniawati, S. N. H. S. Abdullah, S. Abdullah, and S. Abdullah, "Investigation on Image Processing Techniques for Diagnosing Paddy Diseases," 2009 Int. Conf. Soft Comput. Pattern Recognit. , pp. 272–277, 2009.
• L. Busin and N. Vandenbroucke, "Color Space Selection For Unsupervised Color Image Segmentation By Histogram Multithresholding Laboratoire LAGIS - UMR CNRS 8146 Université des Sciences et Technologies de Lille Bâtiment P2 59655 Villeneuve d ' Ascq - FRANCE Ecole d ' Ingénieurs du Pas-de," pp. 203–206, 2004.
• K. Bhattacharyya and K. K. Sarma, "ANN-based Innovative Segmentation Method for Handwritten text in Assamese," vol. 5, pp. 9–16, 2009.
• R. P. Krishnan, S. Sofiah, and M. Radzi, "Color Recognition Algorithm using a Neural Network Model in Determining the Ripeness of a Banana," no. October, pp. 11–13, 2009.
• A. F. Aji, Q. Munajat, A. P. Pratama, H. Kalamullah, J. Setiyawan, and A. M. Arymurthy, "Detection of Palm Oil Leaf Disease with Image Processing and Neural Network Classification on Mobile Device," Int. J. Comput. Theory Eng. , vol. 5, no. 3, pp. 528–532, 2013.
• S. T. Monteiro, Y. Minekawa, Y. Kosugi, T. Akazawa, and K. Oda, "Prediction of sweetness and amino acid content in soybean crops from hyperspectral imagery," ISPRS J. Photogramm. Remote Sens. , vol. 62, no. 1, pp. 2–12, May 2007.
• C. Amza, "A Review On Neural Network-Based Image Segmentation Techniques," no. 1, pp. 1–23.

Index Terms

Keywords