A multiple feature vector framework for forest species recognition

Authors:
Paulo R. Cavalin;Marcelo N. Kapp;Jefferson Martins;Luiz E. S. Oliveira
Affiliations:
Universidade Federal do Tocantins - UFT, Palmas (TO), Brazil;Universidade Federal da Integração Latino-Americana - Unila, Foz do Iguaçú (PR), Brazil;Universidade Tecnológica, Federal do Paraná - UTFPR, Toledo (PR), Brazil;Universidade Federal do Paraná - UFPR, Curitiba (PR), Brazil
Venue:
Proceedings of the 28th Annual ACM Symposium on Applied Computing
Year:
2013

Citing 5
Cited 0

On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns

IEEE Transactions on Pattern Analysis and Machine Intelligence
Blur Insensitive Texture Classification Using Local Phase Quantization

ICISP '08 Proceedings of the 3rd international conference on Image and Signal Processing
Handwritten character recognition through two-stage foreground sub-sampling

Pattern Recognition
Forest Species Recognition Using Color-Based Features

ICPR '10 Proceedings of the 2010 20th International Conference on Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this work we focus on investigating the use of multiple feature vectors for forest species recognition. As consequence, we propose a framework to deal with the extraction of multiple feature vectors based on two approaches: image segmentation and multiple feature sets. Experiments conducted on a 112 species database containing microscopic images of wood demonstrate that with the proposed framework we can increase the recognition rates of the system from about 55.7% (with a single feature vector) to about 93.2%.