Research Article
Pollen Recognition and Classification Method Based on Local Binary Pattern
@INPROCEEDINGS{10.1007/978-3-030-97124-3_40, author={Haotian Chen and Zhuo Wang and Yuan An}, title={Pollen Recognition and Classification Method Based on Local Binary Pattern}, proceedings={Simulation Tools and Techniques. 13th EAI International Conference, SIMUtools 2021, Virtual Event, November 5-6, 2021, Proceedings}, proceedings_a={SIMUTOOLS}, year={2022}, month={3}, keywords={Local binary pattern Texture feature Pollen recognition}, doi={10.1007/978-3-030-97124-3_40} }- Haotian Chen
Zhuo Wang
Yuan An
Year: 2022
Pollen Recognition and Classification Method Based on Local Binary Pattern
SIMUTOOLS
Springer
DOI: 10.1007/978-3-030-97124-3_40
Abstract
Aiming at the problem of low resolution and small sample size of pollen images, this paper proposes a pollen image classification method based on local binary mode. This method first performs preprocessing such as sharpening and normalization on the pollen image. For the preprocessed image, calculate the local binary pattern. Then extract the directional gradient histogram operator of the local binary pattern calculation result as the identification feature. And finally, use the SVM as the classifier for the classification and recognition of the three-dimensional pollen image. Through the experiment on the European Confocal standard pollen database, the results show that the recognition rate of this method can exceed 95% at the highest, and at the same time, it has better robustness to the proportion and pose changes of pollen images, and has better recognition effect than traditional methods.
