计算机应用 ›› 2016, Vol. 36 ›› Issue (3): 820-826.DOI: 10.11772/j.issn.1001-9081.2016.03.820

• 虚拟现实与数字媒体 • 上一篇    下一篇

基于偏最小二乘回归局部形状关系建模的颅面复原方法

贺毅岳1,2, 马自萍3, 高妮2, 耿国华2   

  1. 1. 西北大学 经济管理学院, 西安 710127;
    2. 西北大学 信息科学与技术学院, 西安 710127;
    3. 北方民族大学 数学与信息科学学院, 银川 750021
  • 收稿日期:2015-08-25 修回日期:2015-10-22 出版日期:2016-03-10 发布日期:2016-03-17
  • 通讯作者: 贺毅岳
  • 作者简介:贺毅岳(1982-),男,湖南娄底人,讲师,博士,CCF会员,主要研究方向:医学图像图形处理、量化投资;马自萍(1977-),女,宁夏吴忠人,副教授,博士,主要研究方向:图像处理;高妮(1982-),女,陕西咸阳人;博士研究生,主要研究方向:智能学习算法;耿国华(1955-),女,山东莱州人,教授,博士生导师,主要研究方向:医学图像图形处理。
  • 基金资助:
    国家自然科学基金资助项目(61172170,61462002,61372046);陕西省自然科学基金资助项目(2015JQ7278)。

Craniofacial reconstruction method based on partial least squares regression model of local craniofacial morphological correlation

HE Yiyue1,2, MA Ziping3, GAO Ni2, GENG Guohua2   

  1. 1. School of Economics and Management, Northwest University, Xi'an Shaanxi 710127, China;
    2. School of Information Science and Technology, Northwest University, Xi'an Shaanxi 710127, China;
    3. School of Mathematics and Information Science, North University for Nationalities, Yinchuan Ningxia 750021, China
  • Received:2015-08-25 Revised:2015-10-22 Online:2016-03-10 Published:2016-03-17
  • Supported by:
    This work is partially supported by the National Nature Science Foundation of China (61172170, 61462002, 61372046), the Natural Science Foundation of Shaanxi Province (2015JQ7278).

摘要: 针对基于主成分分析(PCA)的颅面联合统计复原中建模方法未充分考虑颅骨对面皮表面形状影响的局部性、模型对颅骨与面皮之间形状变化关系描述能力不足的问题,提出一种基于偏最小二乘回归(PLSR)局部形状关系建模的颅面复原方法。首先,深入分析基于PCA的颅面整体形状统计建模方法的缺陷,以及利用PLSR进行局部形状关系统计建模的优势;然后,将PLSR引入到颅面形状关系建模过程中,以按照法医人类学知识分类和具有生理点对应关系的颅面三维表面模型为训练集,针对每一类面皮上的每一个表面顶点,建立关于与其局部紧密相关的颅骨表面顶点集的PLSR坐标计算模型;进而,利用面皮表面顶点的坐标计算模型获得待复原面皮各顶点坐标来实现面貌复原,并给出基于PLSR局部形状关系建模的颅面复原方法的具体步骤;最后,给出通过PLSR局部形状关系建模进行颅面复原的多个实例,并采用有效复原能力和绝对误差等多种评估指标进行对比评估。实验结果表明,基于PLSR局部形状关系建模方法能显著提高颅面复原的准确度。

关键词: 颅面复原, 局部形状关系, 统计建模, 偏最小二乘回归, 复原效果评估

Abstract: Focusing on the issue that the significant localized characteristics of the influence of skull on the facial surface shape are not fully considered in the existing joint statistical craniofacial reconstruction methods based on Principal Component Analysis (PCA) modeling, which leads to the inadequate description ability of the craniofacial morphological correlation models, by employing these methods and describing the morphological relationship between skull and face, a new craniofacial reconstruction method based on a Partial Least Squares Regression (PLSR) model of local craniofacial morphological correlation was proposed. Firstly, the defects of the joint statistical shape model based on PCA with skull and face as a whole and the advantages of the local morphological correlation model based on PLSR were deeply analyzed. Secondly, by introducing PLSR into the modeling of craniofacial morphological correlation, and based on craniofacial 3D surface model, whose physiological consistent correspondence was established, and classified according to forensic anthropology knowledge, the PLSR coordinate calculation model for each vertex of facial surface was constructed, with those closely related vertex set on skull as its independent variables. Thirdly, with the coordinates of the unknown skull surface model as input values of the coordinate calculation model, the coordinate of each vertex of the predicted face model was acquired, from which the predicted face could be reconstructed, and the concrete procedure of the new reconstruction method was elaborated. Finally, several craniofacial reconstruction experimentations by applying the new reconstruction method based on PLSR were given, and the new reconstruction method was comparatively analyzed and evaluated by the indicators including effectiveness of reconstruction and absolute error. The experimental results show that the new reconstruction method significantly improves the accuracy of craniofacial reconstruction.

Key words: craniofacial reconstruction, local morphological correlation, statistical modeling, Partial Least Squares Regression (PLSR), reconstruction evaluation

中图分类号: