Scholarlink

<p>Pose and gender prediction has evolved as increasingly significant recognition fields in deep networks. It plays a crucial role in facial biometrics, detecting attention, surveillance, etc. Identifying pose and gender is a portion of facial analysis focused on image classification. Various methods have been developed for predicting pose and gender, but they have some complications. Therefore, this work builds a novel Red Fox-based Google Net (RFbG) as a recognition framework. The face images are initially gathered, and the noisy features are removed. Essential elements are extracted from the image and analyzed. Red Fox optimization does this process. Therefore, the analyzed images are classified. Python is trained with the pose and gender recognition datasets in the proposed RFbG. The performance criteria, such as F1 score, accuracy, Recall, Precision, and error rate, are computed. The performance of the proposed RFbG gained a higher accuracy with a very low error rate. </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

A robust deep learning framework for accurate pose and gender prediction

  • 期刊论文

  • 发表日期：

    2026年3月11日

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

摘要

Pose and gender prediction has evolved as increasingly significant recognition fields in deep networks. It plays a crucial role in facial biometrics, detecting attention, surveillance, etc. Identifying pose and gender is a portion of facial analysis focused on image classification. Various methods have been developed for predicting pose and gender, but they have some complications. Therefore, this work builds a novel Red Fox-based Google Net (RFbG) as a recognition framework. The face images are initially gathered, and the noisy features are removed. Essential elements are extracted from the image and analyzed. Red Fox optimization does this process. Therefore, the analyzed images are classified. Python is trained with the pose and gender recognition datasets in the proposed RFbG. The performance criteria, such as F1 score, accuracy, Recall, Precision, and error rate, are computed. The performance of the proposed RFbG gained a higher accuracy with a very low error rate.