Spotting the Differences between Two Images

Raghunadh M V; Srikanth Kotakonda

doi:10.55549/epstem.1343280

Conference Paper

Year 2023, Volume: 22, 142 - 151, 01.09.2023

Raghunadh M V Srikanth Kotakonda

https://doi.org/10.55549/epstem.1343280

Abstract

References

Bianco,S., Ciocca, G., & Schettini, R.(2015). How far can you get by combining change detection algorithms? ArXiv.
Girshick, R., Donahue,J., Darrell,T.,& Malik, J.(2014) Rich feature hierarchies for accurate object detection and segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, 587.
Jain,R., & Doermann,D.S.(2013). Visualdiff: Document image verification and change detection. 2013 12th International Conference on Document Analysis and Recognition, 40–44.
Qin, H., Yan, J., Li, X., & Hu,X.(2016). Joint training of cascaded cnn for face detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3456– 3465.
Wu,J., Ye,Y., Chen,Y., Weng, Z.(2018).Spotting the difference by object detection. ArXiv.

Spotting the Differences between Two Images

Year 2023, Volume: 22, 142 - 151, 01.09.2023

Raghunadh M V Srikanth Kotakonda

https://doi.org/10.55549/epstem.1343280

Abstract

This paper presents a generalized solution to the classical problem of spotting the differences between two images. In this digital era, the authenticity of an image has become a big challenge to the researchers and engineers in the field of computer vision and image processing. Due to the rapid developments in digital technology, creation of photographic fakes and image manipulation has become easily accessible to everyone. With the availability of open-source editing software tools, the possibility of various image manipulations like image forgery, image tampering and image splicing have become almost inevitable. This paper addresses the problem by using classical image processing techniques along with the state-of-the-art YOLOv8 deep learning object detection algorithm. The results obtained are very promising when the model is trained on a synthetic dataset of 700 pairs of images. The uniqueness of the dataset is that each pair of images is different from any other pair of images and the number of differences between any two images may vary from 1 to 50.

Keywords

ORB , SIFT , SSIM , CNN , YOLO

References

Bianco,S., Ciocca, G., & Schettini, R.(2015). How far can you get by combining change detection algorithms? ArXiv.
Girshick, R., Donahue,J., Darrell,T.,& Malik, J.(2014) Rich feature hierarchies for accurate object detection and segmentation. Proceedings of the IEEE conference on computer vision and pattern recognition, 587.
Jain,R., & Doermann,D.S.(2013). Visualdiff: Document image verification and change detection. 2013 12th International Conference on Document Analysis and Recognition, 40–44.
Qin, H., Yan, J., Li, X., & Hu,X.(2016). Joint training of cascaded cnn for face detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3456– 3465.
Wu,J., Ye,Y., Chen,Y., Weng, Z.(2018).Spotting the difference by object detection. ArXiv.

There are 5 citations in total.

Details

Primary Language	English
Subjects	Computer Software
Journal Section	Articles
Authors	Raghunadh M V Srikanth Kotakonda
Early Pub Date	August 15, 2023
Publication Date	September 1, 2023
Published in Issue	Year 2023 Volume: 22

Cite

APA	M V, R., & Kotakonda, S. (2023). Spotting the Differences between Two Images. The Eurasia Proceedings of Science Technology Engineering and Mathematics, 22, 142-151. https://doi.org/10.55549/epstem.1343280