The dataset is created to emulate uncontrolled environment. Three different Android phones were used namely Samsung J1, Samsung J5 and Samsung A7 with varying megapixels. There are 34200 images of 12 different perennial plants in this dataset. These plants are commonly found local perennial plants which have utilised by the local community as medicinal plant.
1.Distance of the camera from the leaf : 5cm,10cm,15cm,20cm,25cm and 30cm
2.Tilt of the camera : 45 degree to left and right with reference to the leaf at 10cm, 20cm and 30cm
3.Zoom from a distance of 30cm from the leaf : 1x, 1.5x, 2x, 2.5x, 3x, 3.5x and 4x
4.White balance : Sun,Cloudy,Incandescent and Fluorescent
5.ISO : 100, 200, 400 and 800
6.Exposure : -2, -1, 0 , +1, +2
Please take note : For White Balance, ISO and Exposure, the images are captured in two different ways. One, the distance at which camera is facing the leaf are 10cm, 20cm and 30cm. Two, the camera is tilted at 45-degree relative to the right side of the leaf, where the images were captured at 10cm, 20cm and 30cm
Publications
1. Pushpanathan, K., Hanafi, M., Mashohor, S., & Fazlil Ilahi, W. F. (2020). Machine learning in medicinal plants recognition: a review. Artificial Intelligence Review, 1-23.| Quartile: Q1 | Impact Factor: 5.747 | DOI:10.1007/s10462-020-09847-0
2. Pushpanathan, K., Hanafi, M., Masohor, S., & Ilahi, W. F. F. (2022). MYLPHerb-1: A Dataset of Malaysian Local Perennial Herbs for the Study of Plant Images Classification under Uncontrolled Environment. Pertanika Journal of Science & Technology, 30(1). | Quartile: Q4 | Impact Factor: 0.79 | DOI:10.47836/pjst.30.1.23
