Machine learning is very important technology that can support people in different disciplines (Agriculture, health centers, household, transportation, etc) and different levels of life. Machine learning increases accuracy. It uses various types of data (image, video, audio and text) for different purposes and applications. Our work mainly focuses on cactus diseases detection to early prevent the reduction of productivity (quantitatively and qualitatively) of the cereal. To do this, the researchers have used 500 unhealthy and 72 healthy cactus images. The images were enhanced, noises were removed and images were segmented to create good model using imadjust, guided filter and K-means clustering techniques respectively. These image preprocessing techniques were selected from many techniques after implementing each technique and measuring their performances. As part of creating the model, feature extraction techniques (Color histogram, Bag of features and GLCM) were applied to extract color, bag of features and texture and respectively. After testing the model applying these features, bag of features were found to be best for creating better model and they were selected as features of our model. We created our machine learning model using bag of features applying linear SVM. Other machine learning algorithms were used to train and test the model for detecting the diseases, but linear SVM was found with best performance (97.2%). In this task, 75% of each class were used for training and 25% were used for testing the model. Finally, the similarity for classification was checked using linear kernel, RBF kernel and Polynomial kernel and an average accuracy of 94% was achieved though linear kernel is the best classifying method with an accuracy of 98.951%.

Machine learning, supervised learning, unsupervised learning, training, classification, feature, bag of features, algorithm, k-means, MSE, PNSR, and linear SVM

[1]. Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani: “An Introduction to Statistical Learning with Applications in R, Springer Texts in Statistics, 2013.
[2]. http://www.cs.princeton.edu/~schapire/talks/picasso-minicourse.pdf:“Machine Learning Algorithms for Classification”, accessed on 22-04-2019 at 2:00 PM.
[3]. https://www.tutorialspoint.com/software_architecture_design/architecture_models.htm: “Software Architecture and Design Architecture Models”, accessed on 03-03-2019 at 8:00 PM.
[4]. R. William Lewis, Computing Consultant, “Introduction to Scientific Computing with MATLAB”, SAW Training Course, MATLAB R2015a.
[5]. Anna Fabijańska, Dominik Sankowski: “Image Noise Removal – The New Approach”, International Journal of Computer Aided Design System in Microelectronics, February 2007.
[6]. R. Srinivas, Satarupa Panda: “Performance Analysis of Various Filters for Image Noise Removal in Different Noise Environment”, International Journal of Advanced Computer Research, December 2013.
[7]. D. Palani, K. Venkatalakshmi E. Venkatraman: “Implementation & Comparison of Different Segmentation Algorithms for Medical Imaging”, International Journal of Innovative Research in Science, Engineering and Technology, March 2014.
[8]. Er. Anjna, Er.Rajandeep Kaur: “Review of Image Segmentation Technique”, International Journal of Advanced Research in Computer Science, May 2017.
[9]. Gajendra Singh Chandel, Ravindra Kumar, Deepika Khare, Sumita Verma: “Analysis of Image Segmentation Algorithms Using MATLAB”, International Journal of Engineering Innovation & Research, 2012.
[10]. Zoltan Kato, Ting-Chuen Pong: “A Markov random field image segmentation model for color textured images”, Image and Vision Computing, March 2006.
[11]. Daniel Zemene Mequanint: “Automatic Malaria Detection from Images of Microscopic Thin Blood Films”, unpublished MSc thesis, March 2016.
[12]. Stephen O’hara and Bruce A. Draper: “Introduction to the Bag of Features Paradigm for Image Classification and Retrieval”, First Edition, Jan 17, 2011.
[13]. www.ens-lyon.fr/LIP/Arenaire/ERVision/bof_classification_winter.pdf:“Bag-of-features for image classification”, accessed on 08-05-2019 at 6:14 PM.
[14]. shodhganga.inflibnet.ac.in/bitstream/10603/44194/8/08_chapter3.pdf: “Color feature extraction”, accessed on 04-05-2019 at 11:00 AM.
[15]. Fritz Albregtsen: “Statistical Texture Measures Computed from Gray Level Coocurrence Matrices”, First Edition, November 5, 2008.
[16]. Hailay Beyene Berhe, Narayan A. Joshi: “Image Processing Techniques for Cactus (Beles) Diseases detection (implementation and analysis)”, February 2019.