Search

Aiming at the problem of the computational complexity and low segmentation precision of the multi-threshold image segmentation method, this paper proposed an ISCA based multi-threshold image segmentation method. Firstly, this method used a chaotic initialization technique to improve the quality of initial population. Secondly, it introduced an adaptive strategy to adjust the parameters according to the fitness values. Finally, it utilized an opposition-based learning strategy, then selected the better particles. The results of the Berkeley image and the plant canopy image segmentation experiments show that this method has a satisfied performance in terms of running time and segmentation accuracy. And it has a strong robustness. [ABSTRACT FROM AUTHOR]

Copyright of Forest Engineering is the property of Forest Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Forest Engineering is the property of Forest Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problem that the standard particle swarm algorithm is easy to fall into the local optimum which leads to poor image segmentation effect, a hybrid particle swarm optimization algorithm combined with simulated annealing algorithm is used to optimize the threshold selection process of multi-threshold image segmentation. The variance function between Otsu classes is used as the fitness function of the algorithm and simulated annealing algorithm is used to avoid jumping into local optimum. The experiment results show that the algorithm can effectively deal with the problem of complex plant canopy image segmentation, and can improve the image segmentation accuracy while guaranteeing the operation efficiency. It provides a theoretical basis for improving the reliability of plant growth condition evaluation and the accuracy of leaf information, with a strong engineering practicability. [ABSTRACT FROM AUTHOR]