Effective Splicing Localization Based on Image Local Statistics

• Published in: Cybersecurity, Privacy and Freedom Protection in the Connected World pp. 221 - 233
• Main Authors: Sekhar, P. N. R. L. Chandra, Shankar, T. N.
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Advanced Sciences and Technologies for Security Applications
• Subjects: Block artificial grids; Cosine dissimilarity; Object segmentation; Splicing localization
• ISBN: 9783030685331; 3030685330
• ISSN: 1613-5113; 2363-9466
• DOI: 10.1007/978-3-030-68534-8_14

In the digital era, people freely share pictures with their loved ones and others using smartphones or social networking sites. The news industry and the court of law use the pictures as evidence for their investigation. Simultaneously, user-friendly photo editing tools make the validity of pictures on the internet are questionable to trust. Intense research work is going on in image forensics over the last two decades to bring out such a picture’s trustworthiness. In this paper, an efficient statistical method based on Block Artificial Grids in double compressed JPEG images is proposed to identify areas attacked by image manipulation. In contrast to existing approaches, the proposed approach extracts the local characteristics from individual objects of the manipulated image instead of the entire image, and pair-wise dissimilarity is obtained between those objects and exploits the manipulated region, which has the highest variance among other objects. The experimental results reveal the proposed method’s superiority over other current methods.