{
  "paper_id": "df166416f3bfce0e97ea5a982fa68c29",
  "paper_title": "Improving Person Recognition by Weight Adaptation of Soft Biometrics",
  "paper_authors": [
    "Shaghayegh Gharghabi",
    "Bita Azari",
    "Faraz Shamshirdar",
    "Reza Safabaki"
  ],
  "publication_date": "October 20-21, 2016",
  "publication_venue": "6th International Conference on Computer and Knowledge Engineering (ICCKE 2016)",
  "abstract": "One of the main challenges of current person recognition techniques lies on difficulties of recognition in various poses. Recently, attention has been focused on using soft biometric information extracted from the human body to overcome the biometric recognition system's limitation in unconstrained environments. In this paper, we integrate the face and body information in a linear combination. We propose a novel approach in which the weights of features in the recognition system are adapted based on the reliability of the detected joints extracted from the body and the correlation between features. We evaluate the proposed approach in recognizing a five person group in various poses such as sitting and circular walking. The method was applied to a service robot equipped with the Kinect sensor. The results show a mean improvement of 4.39% after weight adaptation based on the correlation between features and 6.88% after consideration of the reliability of the features.",
  "keywords": [
    "Weight Adaptation",
    "Person Recognition",
    "soft biometrics",
    "Kinect"
  ],
  "paper_institutions": [
    "Robotics Research Center, Amirkabir University of Technology",
    "Department of Computer Engineering, Amirkabir University of Technology"
  ],
  "output_language": "zh",
  "provider": "doubao",
  "model": "ark-code-latest",
  "prompt_template": "simple",
  "extracted_at": "2026-08-16T19:46:43.849880Z",
  "template_tag": "simple",
  "summary": "### 摘要\n\n本文针对不同姿态下人物识别难题，提出将人脸与身体软生物特征线性融合的方法。结合稀疏表示分类（SRC）进行人脸识别，并利用Kinect获取的骨骼数据计算14个身体特征。基于特征间相关性和关节可靠度，分别提出相关权重自适应（CWA）和可靠度权重自适应（RCWA）算法。在包含5人、四种姿态（站立、直线行走、圆形行走、坐姿）的自建数据集上评估，以站立姿态为训练，其他为测试。使用识别率作为指标，结果显示CWA较无权重自适应的组合基线提高4.39%，RCWA（AF）进一步提高6.88%，达到87.11%平均识别率，验证了权重自适应的有效性。未来工作包括部分遮挡和更多姿态下的识别，以及随时间无监督更新训练集。该方法部署于服务机器人，使用RGBD传感器。\n\n### 关键要点\n\n- 提出结合人脸与身体软生物特征进行人物识别，以应对姿态变化、遮挡和低分辨率等问题。\n- 利用稀疏表示分类（SRC）进行人脸识别，具有高准确率和实时性。\n- 使用Kinect和OpenNI骨架跟踪器提取15个关节的3D坐标，计算14个关节间距离作为身体特征。\n- 基于Pearson相关系数计算特征间相关性，设计CWA算法降低高相关特征的权重，提高低相关特征权重。\n- 考虑骨架关节可靠度，提出RCWA算法，根据可靠关节数量调整特征权重。\n- 自建包含5人、四种姿态（站、直线走、圆形走、坐）的数据集，以站立为训练，其余为测试。\n- 实验显示仅在坐姿下，人脸识别率76.84%，身体识别率44.93%，融合后81.69%，而RCWA(AF)达到95.01%。\n- 平均识别率：人脸40.48%、身体67.23%、无权重融合80.23%、CWA84.62%、RCWA(RF)85.47%、RCWA(AF)87.11%，CWA较融合基线提升4.39%，RCWA提升6.88%。\n- 特征权重基于可靠关节比例调整，认为可靠关节越多，估计关节越可靠。\n- 该方法适用于服务机器人等场景，但限制于5人小群体，且姿态变化有限。\n- 未来将研究部分遮挡和更多姿态，以及开发无监督算法以适应外观随时间变化。"
}