Design and Research of Digital Image Forensics Algorithm

• 발행기관: 한국컴퓨터게임학회
• 저자명: Sandeep Gupta
• 간행물 정보: 『한국컴퓨터게임학회논문지』제34권 3호, 109~120쪽, 전체 12쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2021.09.30

영문 초록

With the wide application of camera equipment, digital image, as an important information carrier, has gradually integrated into me their lives. With the popularity of image editing software, people have to re-examine seeing is believing ideas. In recent years, there have been frequent incidents of image fraud in the fields of news media, judicial notarization and scientific research. Therefore, judging the authenticity and originality of digital images has become an urgent problem to be solved in the field of forensics. Tamper often change the image and its information through different image operations which affecting the reader s authenticity of things. Therefore, it is of great significance to detect the operation history of digital images. Based on the above research background, this paper first summarizes the research status of image operation forensics algorithm, and then obtains evidence from digital image muti-operation. The accuracy, practicability and robustness of the algorithm are proposed. In this paper, an image muti-operation forensics method with JPEG robustness is proposed. Experiments show that this method has a good performance in JPEG robust detection with high quality factor and low quality factor.

목차

1. Introduction

2 Experimental processes

3. Analysis of experimental results

4. Conclusions

키워드

Muti-operation Forensic algorithm Treatment Deep learning robustness