Brazilian Coffee Scenes Dataset

This dataset is a composition of scenes taken by SPOT sensor in 2005 over four counties in the State of Minas Gerais, Brazil: Arceburgo, Guaranesia, Guaxupé and Monte Santo. It has many intraclass variance caused by different crop management techniques. Also, coffee is an evergreen culture and the South of Minas Gerais is a mountainous region, which means that this dataset includes scenes with different plant ages and/or with spectral distortions caused by shadows.


The whole image set of each country was partitioned into multiple tiles of 64 x 64 pixels. The identification of coffee crops (i.e. ground-truth annotation) was performed manually by agricultural researches. The dataset has:
Type Tiles
non-coffee (less than 10% of coffee pixels) 35.577
coffee (at least 85% of coffee pixels) 1.438

4 folds have 600 images each and the 5th has 476 images, all folds are balanced with coffee and non-coffee samples (50% each).

Please, cite this dataset as:

O. A. B. Penatti, K. Nogueira, J. A. dos Santos. Do Deep Features Generalize from Everyday Objects to Remote Sensing and Aerial Scenes Domains? In: EarthVision 2015, Boston. IEEE Computer Vision and Pattern Recognition Workshops, 2015.

	title={Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?},
	author={Penatti, Ot{\'a}vio AB and Nogueira, Keiller and Dos Santos, Jefersson A},
	booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition workshops},


We thank Rubens Lamparelli and Cooxupé for the image sets.

Categories: DatasetsDownloads

Related Posts


Fashion Dataset

Fashion Dataset This dataset is a composition of fashion images and associated tags and comments crawled from two fashion-related social networks, namely and The first part of this dataset (related to the Read more…


Region-based Annotated Child Pornography Dataset

This dataset is a private database that belongs to the Brazilian Federal Police. The paper "A Benchmark Methodology for Child Pornography Detection" describes the structure of the dataset. The aim of the dataset is to assess and compare the performance of child pornography detection methods.


Deep Semantic Segmentation of Mammographic Images

MIAS and INbreast are mammographic datasets for the detection and diagnosis of breast cancer. With the dawn of digital mammograms, one important preprocessing step for the tasks of detection and diagnosis is the removal of the Read more…