Scholarlink

<p>Face pose prediction is a fundamental computer vision job crucial to many applications like facial biometrics, surveillance, Human-computer Interaction (HCI), and surveillance. Several methods have been developed to identify the pose of the face. But, the existence of multiple traits made the forecast more difficult to make. Additionally, the model’s accuracy of recognition declined. So, a novel Chimp-based Zfnet Recognition Mechanism (CbZRM) was designed in this work. The face image data are initialized and filtered for the noise features. Subsequently, the meaningful facial image features from the image are analyzed using the fitness function of the Chimp to identify the facial pose. Later, the detected postures are categorized. The designed CbZRM is implemented in Python with the face pose dataset. The accuracy, Recall, recognition rate, precision, f1-score, and error rate results are obtained and compared with the previous approaches. The CbZRM method achieved a higher performance than the current methods.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent convolutional strategy for the pose and face recognition

  • 期刊论文

  • 发表日期：

    2025年7月1日

查看全文
  • Ponukumati Jyothi,
  • Dasari Haritha,
  • Karuna Arava

摘要

Face pose prediction is a fundamental computer vision job crucial to many applications like facial biometrics, surveillance, Human-computer Interaction (HCI), and surveillance. Several methods have been developed to identify the pose of the face. But, the existence of multiple traits made the forecast more difficult to make. Additionally, the model’s accuracy of recognition declined. So, a novel Chimp-based Zfnet Recognition Mechanism (CbZRM) was designed in this work. The face image data are initialized and filtered for the noise features. Subsequently, the meaningful facial image features from the image are analyzed using the fitness function of the Chimp to identify the facial pose. Later, the detected postures are categorized. The designed CbZRM is implemented in Python with the face pose dataset. The accuracy, Recall, recognition rate, precision, f1-score, and error rate results are obtained and compared with the previous approaches. The CbZRM method achieved a higher performance than the current methods.