Abstract
In this work, a unique database of 6726 multispectral images of coffee leaves is presented. These images were captured in JPG format for the RGB photos and in TIF format for the five multispectral bands: blue, green, red, NIR and red edge, providing a detailed view of different wavelengths of the electromagnetic spectrum. Images in TIF format have a color depth of 16 bits per pixel, ensuring good quality. The blue band (Band 1) captures light in the blue region of the spectrum, approximately 450 to 500 nm. The green band (Band 2) records light in the green region, approximately between 500 and 620 nm. The red band (Band 3) captures light in the red region, between 620 and 750 nm. The red-edge band (Band 4) lies between the red band and the NIR, and is sensitive to the transition between green vegetation and non-vegetation, around 840 nm. Finally, the near infrared band (Band 5) captures light in the near infrared region, between 750 and 900 nm. For ease of identification, images are labeled as follows: if the image name ends in 0, it is an RGB image; if it ends in 1, it corresponds to the blue band; if it ends in 2, to the green band; if it ends in 3, to the red band; if it ends in 4, to the red-edge band; and if it ends in 5, to the near-infrared band. The images show coffee leaves with and without lesions caused by the Hemileia vastatrix fungus, known as coffee rust. These samples were collected from Colombian coffee farms and the images were captured under controlled lighting conditions to ensure quality and consistency. This database is an invaluable resource for precision agriculture research and early detection of crop diseases. With these 6726 images, researchers can use advanced image processing and machine learning techniques to identify differences between healthy leaves and those affected by rust. This can lead to the development of effective predictive models, enabling early detection and more efficient management of diseases in coffee plantations, optimizing production and reducing economic losses for farmers.