刘 娟,胡 敏,黄 忠.基于区域 NSBP 特征的加权证据融合表情识别[J].电子测量与仪器学报,2020,34(11):132-139 |
基于区域 NSBP 特征的加权证据融合表情识别 |
Weighted evidence fusion expression recognition based on regional NSBP features |
|
DOI: |
中文关键词: 表情识别 NSBP 特征 加权证据融合 Dempster 组合规则 |
英文关键词:facial expression recognition neighbour smooth binary pattern feature weighted evidence fusion Dempster combination rule |
基金项目:国 家 自 然 科 学 基 金 ( 61672202, 61702012 )、 安 徽 省 自 然 科 学 基 金 ( 1908085MF195 )、 安 徽 省 重 点 实 验 室 开 放 课 题 项 目(ACAIM180203)、中央高校基本科研业务费专项资金(PA2020GDSK0061)、安徽省高校协同创新项目(GXXT-2019-030)资助 |
|
Author | Institution |
Liu Juan | 1. School of Electronic Engineering and Intelligent Manufacturing, Anqing Normal University,2. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, School of Computer and Information, Hefei University of Technology |
Hu Min | 2. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, School of Computer and Information, Hefei University of Technology |
Huang Zhong | 1. School of Electronic Engineering and Intelligent Manufacturing, Anqing Normal University,2. Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine, School of Computer and Information, Hefei University of Technology |
|
摘要点击次数: 440 |
全文下载次数: 566 |
中文摘要: |
为了提取鲁棒性强的人脸纹理特征并提高区域特征决策融合的性能,提出一种基于邻近平滑二值模式( neighbor smooth
binary pattern, NSBP)特征描述子和加权证据融合(weighted evidence fusion, WEF)的表情识别新方法。 首先,提出了一种 NSBP
描述子,通过判定水平、垂直及对角线方向上的“中心”像素点灰度值是否在各梯度方向上两邻域的灰度值范围内来对图像进
行编码;然后基于提取的眉毛、眼睛和嘴巴区域的 NSBP 纹理特征来构造证据的初始基本概率分配(basic probability assignment,
BPA);最后针对登普斯特-谢弗(Dempster-Shafer, D-S)证据理论在证据之间存在冲突时进行融合的不足,提出一种加权证据修
正的合成方法,以完成 3 个区域证据的决策融合。 实验结果表明,该方法在 CK(Cohn-Kanade)数据库上的平均表情识别率和识
别时间分别为 95. 25%、765 ms,与其他相关方法的比较也验证了其有效性。 |
英文摘要: |
In order to extract robust facial features and improve the decision-level fusion of multi-regional features, a new expression
recognition method based on neighbor smooth binary pattern ( NSBP) feature descriptor and weighted evidence fusion ( WEF) is
proposed. First, a NSBP descriptor is proposed to encode the image by determining whether the gray values of the center pixels in the
horizontal, vertical and diagonal directions are within the gray value range of two neighborhoods in each gradient. Then the initial basic
probability assignments (BPA) of evidences are constructed based on the extracted NSBP texture features of the eyebrows, eyes, and
mouth regions. Finally, aiming at the deficiency of Dempster-Shafer (D-S) evidence theory in conflict evidence fusion, a synthetic
method of weighted evidence revision is proposed to realize the decision fusion of three regional evidences. Experimental results show that
the recognition rate of this method on the Cohn-Kanade ( CK) database is 95. 25%, and the average recognition time is 765 ms,
compared with other related methods, the effectiveness of this method is also verified. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|