欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为正确选择应用于人脸表情识别的支持向量机相关参数,提高表情识别准确率,提出一种应用于表情识别的基于细菌觅食算法的支持向量机参数选择方法。利用细菌觅食算法,通过模拟细菌觅食行为的趋向性操作、复制操作和迁移操作对应用于表情识别的支持向量机的参数进行寻优,避免寻优陷入局部最优,实现参数优化。实验结果表明,采用该方法能够使人脸表情识别分类结果具有更高的准确率。
英文摘要：
To choose the parameters of the support vector machine（SVM）used in facial expression recognition,and improve recognition rate,a method using bacteria foraging algorithm（BFA）to choose the best parameters of the SVM used in facial expression recognition was presented.BFA was used to optimize the parameters of the SVM by chemotaxis,reproduction,elimination and dispersal as bacteria forage for food.The method let parameter optimization avoid falling into local optimum and chose the best SVM parameters.The experimental results show that the facial expression recognition using the SVM optimized by BFA has a higher recognition rate.
同期刊论文项目
同项目期刊论文
The estimation of shear wave propagation in ultrasound elasticity imaging by using BP neural network
Photoacoustic microscopy image resolution enhancement via directional total variation regularization
Kernel Sparse Multi-task Learning for Hyperspectral Image Classification with Empirical Mode Decompo
Multiscale Hessian filter-based segmentation and quantification method for photoacoustic microangiog
Time reversal reconstruction algorithm based on PSO optimized SVM interpolation for photoacoustic im
Feature analysis of Acoustic Emission sources for the rail defect detection by the ？nite element met
Kernel Sparse Multitask Learning for Hyperspectral Image Classification With Empirical Mode Decompos
Collaborative construction of measurement matrix and reconstruction algorithm in compressive sensing
Kronecker compressive sensing-based mechanism with fully independent sampling dimensions for hypersp
Efficient cooperative compressive spectrum sensing by identifying multi-candidate and exploiting det
Deterministic Measurement Matrix Generation for Compressive Data Gathering and Reconstruction in WSN
Shrinkage-Based Alternating Projection Algorithm for Efficient Measurement Matrix Construction in Co
期刊信息
位置：