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
Hi-index | 0.00 |
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%.