Leaf classification using local features

This paper proposes a method for an automatic identification of plant species from low quality pictures of their leaves created using mobile devices. Since the images should be taken from all kind of people the condition of the image taking cannot be controlled. Thus to avoid segmentation of the images local features are used which are scale and rotation invariant. For classification a Support Vector Machine using a “bag-of-keypoint” is applied. Preliminary results are shown on a dataset of leaves from the five most common broadleaf trees in Austria.

[1]  Jun Kong,et al.  Plant Species Identification Based on Neural Network , 2008, 2008 Fourth International Conference on Natural Computation.

[2]  Yuxuan Wang,et al.  A Leaf Recognition Algorithm for Plant Classification Using Probabilistic Neural Network , 2007, 2007 IEEE International Symposium on Signal Processing and Information Technology.

[3]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[4]  De-shuang Huang,et al.  Computer-Aided Plant Species Identification (CAPSI) Based on Leaf Shape Matching Technique , 2006 .

[5]  He Peng,et al.  Machine Recognition for Broad-Leaved Trees Based on Synthetic Features of Leaves Using Probabilistic Neural Network , 2008, 2008 International Conference on Computer Science and Software Engineering.

[6]  Gabriela Csurka,et al.  Visual categorization with bags of keypoints , 2002, eccv 2004.

[7]  Qing Wang,et al.  Leaf Image Retrieval with Shape Features , 2000, VISUAL.

[8]  Zhiyong Wang,et al.  Shape based leaf image retrieval , 2003 .

[9]  Paul M. de Zeeuw,et al.  Towards an Online Image-Based Tree Taxonomy , 2007, Industrial Conference on Data Mining.

[10]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[11]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[12]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.