CitrusUAT: A Dataset of Orange Citrus sinensis Leaves for Abnormality Detection Using Image Analysis Techniques

This dataset provides a collection of color images taken from the orange leaves of Citrus sinensis (L.) Osbeck species with diseases, nutritional deficiencies, and pest symptoms, which are suitable for developing abnormality detection algorithms based on digital image analysis techniques. The dataset comprises 953 color images divided into 12 classes of orange leaves: Healthy, Huanglongbing (HLB), Greasy spot, Iron deficiency, Magnesium deficiency, Manganese deficiency, Nitrogen deficiency, Zinc deficiency, Texas citrus mite, Red scale, Red scale sequelae, and Citrus leafminer. Each color image was segmented by a thresholding method to obtain a binary mask of the leaf region. Samples were analyzed by the quantitative real-time polymerase chain reaction (qPCR) diagnostic test to detect the Ca. L. asiaticus bacterium that causes HLB disease. A full description of the CitrusUAT dataset can be found in the following article: Wilfrido Gómez-Flores, Juan José Garza-Saldaña, Sóstenes Edmundo Varela-Fuentes. "CitrusUAT: A dataset of orange Citrus sinensis leaves for abnormality detection using image analysis techniques," Data in Brief, vol. 52, p. 109908, 2024, DOI: https://doi.org/10.1016/j.dib.2023.109908 Any research originating from its usage is required to cite this paper.