Medical, Aromatic, and Narcotic Plants Classification using an Artificial Neural Network | ||||
| Fayoum University Journal of Engineering | ||||
| Article 8, Volume 4, Issue 2, June 2021, Page 122-137 PDF (630.81 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/fuje.2021.205537 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Margret E. Abdel Malek  ; Rania A. Abuelsoud; Ahmed A. Nashat
| ||||
| Electrical Engineering Department – Faculty of Engineering – Fayoum University | ||||
| Abstract | ||||
| Medical, Aromatic, and Narcotic plants are a natural treasure that grows in the desert without human being interference. They can be used in pharmaceutical industries (medicines), medical usage (medical anesthetic), perfumes industries, and cooking. Thus, they are very useful, available, and can be utilized for the sake of human beings. On the other hand, some of these plants are harmful to our bodies and must be strictly prohibited. So, it is necessary to design and implement an image processing system to detect these plants. This system can be applied by the Ministry of Agriculture and Armed Force. After surveying deserts and taking photos of plants by a small camera attached to a drone, they can be inserted into the system to detect the type of captured plant and take action. In this paper, an automatic computer vision system is proposed to identify six types of desert plants. First, a nine-class collected database is prepared. Second, an artificial neural network-based framework, which uses color, DWT, the ratio between the major and the minor axes of the plants, and Tamura statistical texture features, is employed to classify plants. Outcomes and the results of the suggested system have competed with several techniques such as the SVM, the Naive Bayes, the KNN, the decision tree, and discriminant analysis classifiers. Results reveal that the proposed system has the highest overall recognition rate, which is 94.3%, among other techniques. | ||||
| Keywords | ||||
| Image segmentation; Features extraction; Medical Plants; Aromatic Plants; Narcotic Plants; DWT; Plants Classification; Computer vision; Artificial neural network | ||||
|
Statistics Article View: 139 PDF Download: 158 |
||||
