Scholarlink

In this chapter, a comprehensive overview of benchmark datasets and evaluation metrics used for assessing image forgery detection techniques is provided. It categorizes various publicly available datasets based on the type of forgery—such as copy-move, splicing, and synthetic image generation—and provides detailed descriptions of each dataset. Key datasets like CoMoFoD, CASIA TIDE, MICC, CISDE, ForgeryNet, and DeepGuardDB are discussed to highlight their significance in training and validating forgery detection algorithms. In addition, the chapter outlines evaluation metrics tailored to pixel-level, image-level, and region-level detection strategies.

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

Datasets and Evaluation

  • 章节

  • 发表日期：

    2026年

查看全文
  • Vipin Tyagi

摘要

In this chapter, a comprehensive overview of benchmark datasets and evaluation metrics used for assessing image forgery detection techniques is provided. It categorizes various publicly available datasets based on the type of forgery—such as copy-move, splicing, and synthetic image generation—and provides detailed descriptions of each dataset. Key datasets like CoMoFoD, CASIA TIDE, MICC, CISDE, ForgeryNet, and DeepGuardDB are discussed to highlight their significance in training and validating forgery detection algorithms. In addition, the chapter outlines evaluation metrics tailored to pixel-level, image-level, and region-level detection strategies.