Multi-Class Crops Plant Leafs Classification Using Machine Learning Techniques
Main Article Content
Abstract
in this paper, we introducing a plant disease detection system. The aim is to use image classification techniques based on Machine Learning (ML). The proposed plant disease detection technique has applied in three phases, feature selection, learning, and testing. In feature selection we use color, texture and shape features of image, which are used in various Image Information Retrieval (IR) technique. In order to recover shape features two segmentation techniques K-Means and Fuzzy c Means (FCM) algorithm is used. Next for the texture analysis LBP (Local Binary pattern) has used. Further for color features, the Color Grid Movement (CGM) has considered. In addition, to prepare effective features, different combinations of features have also been prepared. These combinations are used for image classification. The Support Vector Machine (SVM) and Artificial Neural Network (ANN) has considered for classification task. The experimentations with a popular image dataset Plant Village has been used for simulating the effectiveness of the proposed model. However, in this work have used limited number of crops namely corn, grapes and apple. After implementation of the crops disease detection model the experimental performance of all the combinations of features and classifiers has been measured. The Accuracy, error rate, memory and time consumption has considered as criteria to be select most appropriate model for plant disease detection model. The results show the combination of FCM, LBP and CGM outperform as compared to other combinations. Additionally, when this combination is used with the SVM and ANN, than ANN demonstrate higher accuracy in detection of disease in plant. Finally, the future extension of the proposed work has also been discussed
Downloads
Metrics
Article Details
Licensing
TURCOMAT publishes articles under the Creative Commons Attribution 4.0 International License (CC BY 4.0). This licensing allows for any use of the work, provided the original author(s) and source are credited, thereby facilitating the free exchange and use of research for the advancement of knowledge.
Detailed Licensing Terms
Attribution (BY): Users must give appropriate credit, provide a link to the license, and indicate if changes were made. Users may do so in any reasonable manner, but not in any way that suggests the licensor endorses them or their use.
No Additional Restrictions: Users may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.