Automatic Flower Disease Identification Using Image Processing
| dc.contributor.advisor | Assabie, Yaregal(PhD) | |
| dc.contributor.author | Tigistu, Getahun | |
| dc.date.accessioned | 2018-06-20T06:47:58Z | |
| dc.date.accessioned | 2023-11-29T04:05:40Z | |
| dc.date.available | 2018-06-20T06:47:58Z | |
| dc.date.available | 2023-11-29T04:05:40Z | |
| dc.date.issued | 2015-02 | |
| dc.description.abstract | Currently, the cultivation of flowers is becoming popular. However, during the cultivation process there may be a number of challenges that affect it, one of which is flower disease. Most flower diseases are caused by insects, fungi, and bacteria. Identification of these diseases need experienced experts in this area. Thus, developing a system that automatically identifies flower diseases can help to support the experienced experts. In view of this, an image processing based system for automatic identification of flower disease is proposed. The proposed system consists of two main phases. In the first phase normal and diseased flower image are used to create a knowledge base. During the creation of the knowledge base, images are pre-processed and segmented to identify the region of interest. Then, seven different texture features of images are extracted using Gabor texture feature extraction. Finally, an artificial neural network is trained using seven input features extracted from the individual image and eight output vectors that represent eight different classes of disease to represent the knowledge base. In the second phase, the knowledge base is used to identify the disease of a flower. In order to create the knowledge base and to test the effectiveness of the developed system, we have used 40 flower images for each of the eight different classes of flower disease and we have a total of 320 flower images. From those images 85% of the Dataset is used for training and 15% of the data set is used for testing. The experimental result demonstrates that the proposed technique is effective technique for the identification of flower disease. The developed system can successfully identify the examined flower with an accuracy of 83.3%. Keywords: Gabor Feature Extraction, Artificial Neural Network, Texture Feature | en_US |
| dc.identifier.uri | http://etd.aau.edu.et/handle/123456789/1993 | |
| dc.language.iso | en | en_US |
| dc.publisher | Addis Ababa University | en_US |
| dc.subject | Gabor Feature Extraction; Artificial Neural Network;Texture Feature | en_US |
| dc.title | Automatic Flower Disease Identification Using Image Processing | en_US |
| dc.type | Thesis | en_US |