Wheat Dataset for Species Classification and Sunn Pest Damage Detection
Description
The dataset includes 6 different species of wheat; bezostaja, mufitbey, nacibey, sonmez-2001, tosunbey, and ekiz. Each of these species is divided into two conditions; damaged or healthy. In the dataset, there are 2502 healthy and 1063 sunn pest-damaged wheat grains. These wheat grains differ in various parameters such as width, length, color, stain condition, and wrinkled texture. In total, our dataset contains 83 sunn pest damaged and 87 healthy wheat grains images which make 170 images. While the file directory was created these were taken into account; the primary folder contains the species. Every species also have subfolders labeled damaged and healthy. These subfolders include the healthy and sunn pest damaged wheat grains images of the related species. Naming the images of bezostaja, mufitbey, nacibey, sonmez-2001, tosunbey and ekiz species start with 01, 02, 03, 04, 05, and 06 respectively. After the species part, naming is done according to whether it is damaged or healthy wheat. If the wheat grains in the image are damaged, it is labeled as 1, otherwise, it is labeled as 0. Finally, the sample number concat and forms the image name. According to all these rules mentioned above, the file name of the first image of the "bezostaja" species and in the "damaged" condition will be "01_1_01.png". ONLY ACADEMIC RESEARCH PURPOSE IS ALLOWED TO BE CONDUCTED USING THIS DATASET; COMMERCIAL USE IS NOT PERMITTED.
Files
Steps to reproduce
The images were captured with an Olympus omd m1 mark 2 with a lens 60mm makro. The images were taken from 1 meter height with a right angle on a white background and in a room that both has a window and a lightbulb with laboratory conditions. The crucial factor for capturing the images is to not cast a shadow from the camera.