CAJ | 학술논문

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。
위정학선택응용우인검표정식별적지지향량궤상관삼수，제고표정식별준학솔，제출일충응용우표정식별적기우세균멱식산법적지지향량궤삼수선택방법。이용세균멱식산법，통과모의세균멱식행위적추향성조작、복제조작화천이조작대응용우표정식별적지지향량궤적삼수진행심우，피면심우함입국부최우，실현삼수우화。실험결과표명，채용해방법능구사인검표정식별분류결과구유경고적준학솔。
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 ,elimi‐nation 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 .