Big Scientific Data Project Zone II Versions ZH2 Vol 4 (4) 2019
An image dataset for field crop disease identification
Dataset URL >>
: 2019 - 03 - 20
: 2019 - 06 - 26
: 2019 - 04 - 17
: 2019 - 12 - 31
22268 607 0
Abstract & Keywords
Abstract: According to the report of Food and Agriculture Organization of the United Nations, the annual natural loss rate caused by agricultural pests and diseases reached more than 37%. Identification and control of agricultural pests and diseases is significant for improving agricultural yield. Traditional manual recognition methods are not accurate enough since they rely on subjective experience. In recent years, computer vision-based methods have developed gradually. These methods are more objective and support real-time online diagnosis. As these methods depend on large-scale training samples, building an image dataset for machine learning modeling is very important for efficiently identifying agricultural diseases and pests. Therefore, we have constructed an image dataset for agricultural diseases and pests research (IDADP) which covers such aspects of agricultural diseases and pests as image acquisition, classification, labeling, storage and modeling. Meanwhile, this image dataset provides online diagnosis of agricultural diseases and related technical consultation services for scholars and agricultural technicians. The image dataset currently has about 200 GB of high-quality agricultural disease images, including field crops such as rice, wheat and corn. Essentially different from existing agricultural disease map resources which mostly contain only 3 to 5 typical symptom images, our dataset consists of the original image data of the same kind of crop diseases with high resolution and high similarity. Each disease has hundreds or even thousands of images, which can be used as training samples for machine learning modeling of disease identification. As a standard dataset for machine learning modeling in large data environment, this image dataset will provide valuable basic data resources. And it has important applicability in promoting the development of agricultural disease identification.
Keywords: agricultural disease; field crops; disease identification; standard image dataset; training sample
Dataset Profile
TitleAn image dataset for field crop disease identification
Data corresponding authorLei Chen (, Yuan Yuan (
Data authorsLei Chen, Yuan Yuan
Time range2013 – 2018
Geographical scopeChina
Data volume200 GB
Data formatSQL Server
Data service system<>
Sources of fundingThe 13th Five-year Informatization Plan of Chinese Academy of Sciences (XXH13505-03-104); National Natural Science Foundation of China (31871521).
Dataset compositionThe dataset contains 15 disease images of rice, wheat and maize, each of which corresponds to a folder. Concretely, there are 6 folders of rice diseases, including bacterial blight of rice, rice false smut, rice blast, rice brown spot, rice sheath blight and rice bacterial leaf streak; 5 folders of wheat diseases, including wheat powdery mildew, wheat head blight, wheat spindle streak mosaic virus, gerlachia nivalis and wheat leaf rust; and 4 folders of maize diseases, including corn northern leaf blight, southern corn rust, corn southern leaf blight and corn rust. Each folder contains the original JPG files named by pipeline number of the disease image and the intro.txt file which introduces the basic information of the disease and its control methods. This dataset contains 17 624 high quality JPG image data.
Article and author information
Lei Chen
Yuan Yuan
Publication records
Released: April 17, 2019 ( VersionsZH1
Published: Dec. 31, 2019 ( VersionsZH2