广西师范大学学报（自然科学版）2017，Vol.35Issue(3)：45-52,8.DOI:10.16088/j.issn.1001-6600.2017.03.006
基于对比度金字塔图像融合的自发笑脸识别
Spontaneous Smile Recognition Based on CPD Image Fusion
摘要
Abstract
Spontaneous smile recognition is an important part in the field of facial expression recognition,which is widely used in many fields.This paper presents a spontaneous smile recognition method by fusing infrared and visible images based on contrast pyramid decomposition(CPD).Infrared and visible images are decomposed with 4 layers Gauss Pyramids respectively,and the corresponding contrast pyramids are built.Fusion image which is obtained by combining each layer of infrared image and visible image based on the fusion rule-pixel average.Then LBP features and LDP features are extracted from images,and smile and not smile expressions are classified by SVM classifier.The experimental results show that the smile recognition rates with the fusion images based on LBP features and LDP features can reach 96.69％ and 97.19％ respectively,and the overall recognition rates with the fusion images based on LBP features and LDP features can reach 96.51％ and 96.78％ respectively.These results are significantly better than the results with other methods.The results show that the proposed algorithm can improve the recognition performance of the spontaneous smile recognition.关键词
图像融合/对比度金字塔分解/笑脸识别/LBP特征/LDP特征Key words
image fusion/contrast pyramid decomposition/smile recognition/LBP feature/LDP feature分类
信息技术与安全科学引用本文复制引用
夏海英,喻潇琪..基于对比度金字塔图像融合的自发笑脸识别[J].广西师范大学学报（自然科学版）,2017,35(3):45-52,8.基金项目
广西自动检测技术及仪器重点实验室开发基金(YQ1402) （YQ1402）
广西多源信息挖掘与安全重点实验室开发基金(MIMS15-05) （MIMS15-05）
广西药用资源化学与药物分子工程重点实验室开发基金(CMEMR2014-B15) （CMEMR2014-B15）
国家星火计划重点项目(2015GA790002) （2015GA790002）
