Download the latest version (2.0) of the data set of biomass texture images released under the GNU Public License.
If you use this data set (or a modified version of it) in any scientific work, please cite the corresponding paper:
Radu T. Ionescu, Andreea L. Popescu, Marius Popescu, Dan Popescu: BiomassID: A Biomass Type Identification System for Mobile Devices. Computers and Electronics in Agriculture, vol. 113, pages 244-253, 2015. [BibTeX]
The Biomass Texture data set 2.0 contains 360 images of 512x512 pixels representing close up photos of four types of biomass resulted after the processing of wheat, municipal waste, corn, and park wood, respectively. Photos where taken at different zoom levels under various lighting conditions.
A few random samples of biomass images are given below:
This data set can be used as a benchmark to assess the performance level of a classifier that aims to identify the four types of biomass: wheat, waste, corn, and park wood.
Version 1.0 of the data set of biomass texture images is a subset of version 2.0. More precisely, version 1.0 consists of the first 270 images included in version 2.0.
If you use version 1.0 of the data set (or a modified version of it) in any scientific work, please cite the corresponding paper:
Radu T. Ionescu, Andreea L. Popescu, Dan Popescu, Marius Popescu: Local Texton Dissimilarity with Applications on Biomass Classification. In Proceedings of VISAPP, Lisbon, Portugal, 2014. [BibTeX]
The Biomass Texture data set 1.0 contains 270 images of 512x512 pixels representing close up photos of three types of biomass resulted after the processing of wheat, municipal waste and corn, respectively. Photos where taken at different zoom levels under various lighting conditions.
A few random samples of biomass images are given below:
This data set can be used as a benchmark to assess the performance level of a classifier that aims to identify the three types of biomass: wheat, waste, and corn, respectively.
The authors thank Mircea Popescu from CBAB Biotehnol and Ion Ionescu from Ecosal Prest for providing biomass samples of various types for the Biomass Texture data set.