Skip to main content

Table 4 Common datasets for plant diseases and pests detection

From: Plant diseases and pests detection based on deep learning: a review

Species Collection environment Link
PlantVillage-Dataset: 50,000 images of classified plant diseases of 14 crop varieties and 26 diseases [84] Detached leaves on a plain background
Rice Leaf Diseases Data Set: three classes of diseases: Bacterial leaf blight, Brown spot, and Leaf smut, each having 40 images [85, 86] Captured with a white background in direct sunlight
Image Database for Plant Disease Symptoms (PDDB): 2326 images of 171 diseases and other disorders affecting 21 plant species [87] Field
New Plant Diseases Dataset (Augmented): 87 K rgb images of healthy and diseased crop leaves which is categorized into 38 different classes Detached leaves on a plain background
38 disease classes from PlantVillage dataset and 1 background class from Stanford’s open dataset of background images—DAGS [88] Network
18,222 images annotated with 105,705 northern leaf blight (NLB) lesions [89] Field
40 classes of insects from rice, maize, soybean, sugarcane and cotton crops Field
17,624 high quality JPG image data of rice, wheat and maize of 200 GB Field
PlantDoc dataset: 2598 data points in total across 13 plant species and up to 17 classes of diseases [63] Field
Northern Leaf Blight (NLB) dataset for Maize Field
3651 images of apple leaf disease [90] Field
IP102: Insect Pest Recognition Database: 75,000 images belonging to 102 categories [91] Field
A database of eight common tomato pest images [92] Network