Coffee plant image segmentation and disease detection using JSEG algorithm
Resumo
Brazil is the largest coffee producer in the world, and then there are many challenges to maintain the high quality and purity of the beans. Thus, it is important to study coffee plants, and help agronomists to detect diseases, such as rust, with resources of computer science. In this work, it is described experiments using image segmentation algorithm JSEG, which is capable to segment images in multi-scale. Using a coffee tree image database RoCoLe (Robusta Coffee Leaf Images), the JSEG algorithm is used to segment these images in four scales. It is selected typical segments in each scale and they are grouped using similarity of normalized color histograms. In this way the several scales segmentations are compared. It is concluded that the segments in scales 1 and 2, in which the colors are more homogeneous then in scales 3 and 4, are adequate to use as training samples for the detection of rust diseases.
Referências
D.Suhartono, W.A.Derwin, L.Miranty, Y.Muhamad, Expert System in Detecting Coffee Plant Diseases, International Journal of Electrical Energy, vol. 1, n.3, pp.156-162, 2013.
J.G.A. Barbedo, A Review on the Main Challenges in Automatic Plant Disease Identification Based on Visible Range Images, Biosystems Engineering, vol. 144, pp. 52-60, 2016.
V. Metre, J. Ghorpade, An Overview of the Research on Texture Based Plant Leaf Classification, IJCSN-International Journal of Computer Science and Network, vol.2, n.3, pp. 1-12, 2013.
A. D. Mengistu, D.M.Alemayehu, S.G.Mengistu, Ethiopian Coffee Plant Diseases Recognition Based on Imaging and Machine Learning Techiniques, International Journal of Database Theory and Applications, vol.9, n.4, pp.79-88, 2016.
A.S.A.Mettleq, S.Abu-Naser, A Rule Based System for the Diagnosis of Coffee Diseases, International Journal of Academic Information Systems Research, vol. 3, pp. 1-8, 2019.
J. Parraga-Alava, K.Cusme, A. Loor, E. Santander, RoCoLe: A robusta coffee leaf images dataset for evaluation of machine learning based methods in plant diseases recognition, Data in Brief, vol.25 pp. 1-5,2019.
L.X.B.Sorte, C.T.Ferraz, F.Fambrini, R.R.Goulart, J.H.Saito, Coffee Leaf Disease Recognition Based on Deep Learning and Texture Attributes, Procedia Computer Science, vo.159, pp.135-144, 2019.
M.V.Pagudpud, Exploring the Smartphone Manipulation Skills in a Coffee Farming Community Using Clustering Algorithm, ICMSSP: Proceedings of the 2009th 4th International Conference on Multimedia Systems and Signal Processing, pp.52-56, maio de 2019.
Y.Deng, B.S. Manjunath, Unsupervised Segmentation of Color-Texture Regions in Images and Video, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.23, n.8, pp. 800-810, 2001.
L.C.Lulio, M.L.Tronco, A.J.V. Porto, JSEG-based image segmentation in computer vision for agricultural mobile robot navigation, IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA), pp. 1-6, 15-18 Dezembro, 2009.
F.Fambrini, Y. Iano, D.G.Caetano, A.A.D. Rodriguez, C. Moya, E. Carrara, A. Rangel, F.C. Cabelo, J.V. Zubem, L.M.D.V. Cura, J.B. Destro-Filho, J.R. Campos, J.H. Saito, GPU Cuda JSEG Segmentation Algorithm associated with Deep Learning Classifier for Electrical Network Images Identification, Procedia Computer Science, vol. 126, pp. 557-565, 2018.
C.J. Henry, Near Sets: Theory and Applications, Academic Doctoral Thesis, University of Manitoba, Winnipeg, Manitoba R3T 5V6, Canada, 2010.
J.F. Peters, Near Sets, General Theory About Nearness of Objects, Applied Mathematical Sciences, vol.1, n.53, pp.2609-2629, 2007.
