Tree Species Dataset consisting of Images of the Bark, Leaves or Needles

This dataset consists of 3 subsets:

Leaves of the most common Austrian broad leaf trees: Ash (25), Beech (30), Hornbeam (34), Mountain oak (22), Sycamore maple (23)

Bark of the most common Austrian trees: Ash (34), Beech (16), Black pine (166), Fir (127), Hornbeam (42), Larch (200), Mountain oak (77), Scots pine (190), Spruce (213), Swiss stone pine (96), Sycamore maple (22)

Needles of the most common Austrian conifers: Black pine (107), Fir (10), Larch (114), Scots pine (10), Spruce (13), Swiss stone pine (21)

The leaf dataset consists of 134 images of five Austrian broad leaf trees which were scaled to either 800 pixel height or 600 pixel width. Every class has 25 to 34 images. While the beech, hornbeam, mountain oak and sycamore maple are complete leaves, the ash is compound, more precise a pinnate leaf.

The dataset of bark images contains 1183 images of eleven Austrian trees. Every class has 16 to 213 images. These images were also scaled to a size of either 800 pixel height or 600 pixel width. The dataset of the black pine, fir, larch, scots pine and spruce are divided in 3 sub-classes. The first containing images of the trees when they are younger than 60, in the second one images of trees with an age of 60 to 80, and the last one with images of trees which are older than 80. These separation is necessary because especially the bark of these trees differs at different ages.

The dataset of the needle images contains 275 of 6 Austrian conifers. Each class contains 10 to 114 images. Conifers can be divided into two classes: The first class are the fir and the spruce on which the needles grow separate on the branch and the second class are the species on which the needles grow in clusters. It can be seen that the fir, scots pine, and spruce images have been made with perfect lighting conditions, whereas the other images have been photographed in the nature.

These datasets were gathered by employees of the ”Osterreichische ¨ Bundesforste AG“ in autumn 2009 and spring 2010.

This database may be used for non-commercial research purpose only. If you publish material based on this database, we request you to include a reference to:

Fiel, S. & Sablatnig, R. (2010): Leaf classification using local features In: Proc. of 34th annual Workshop of the Austrian Association for Pattern Recognition (AAPR), 2010, 69-74 pdf

Fiel, S. (2010): Automated Identification of Tree Species from Images of the Bark, Leaves or Needles, Master Thesis, Vienna University of Technology pdf