| Using image processing to detect Tetranychus urticae pest on a strawberry plant leaf |
| Paper ID : 1352-NICAME1402 |
| Authors: |
|
Alireza Ansarimovahed1, Ahmad Banakar *2, سید محمد جاویدان3, محمد مهرآبادی3 1Tarbiat Modares University, Faculty of Agriculture,Tehran 2هیات علمی 3دانشگاه تربیت مدرس |
| Abstract: |
| Early and accurate detection of pests in greenhouses is one of the most important factors in dealing with plant pests. In this research, the ability of the image processing technique to detect the Tetranychus urticae pest of strawberry plants was investigated. Digital images were prepared from infected strawberry plant leaves. Then, in order to process the provided image, the pest detection algorithm was developed in the software. Color processing was used to isolate the apparent spots of the infected parts from the leaf surface. The results showed that the presented algorithm was able to detect the contaminated points in the tested image sample with 97.3% accuracy; therefore, in order to improve the detection, shape features were extracted from black and white images of infected leaves. Dimensionless features such as roundness, aspect ratio, compactness and surface ratio of infected parts related to Tetranychus urticae pest were extracted and analyzed. The results of the research showed that the proposed method has a high ability in distinguishing plant pests and diseases and can be used as a powerful tool alongside experts in this field. |
| Keywords: |
| plant pests, machine vision, colored spaces, data analysis |
| Status : Paper Accepted (Oral Presentation) |
