Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{150218,
        author = { S. Aashmi Miranda  and Dr. K. Thulasimani},
        title = {DETECTION OF FAKE COLORIZED IMAGES USING DENSE CONVOLUTION  NETWORK },
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {7},
        number = {4},
        pages = {104-110},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=150218},
        abstract = {-  Image forgery implies altering the digital image to some meaningful or valuable data. Image forensics is a well developed field that analyzes the images of specific conditions to build up trust and genuineness. Although image editing techniques can provide significant appreciation of the image or entertainment value, they may also be used with malicious intent. An emerging image editing technique is colorization, in which gray scale images are colorized with realistic colors. But this technique may also be intentionally applied to certain images to confound object recognition algorithms. In this work, it is observed that, colorized images, usually change the images using a variety of mechanisms. The digital image developed from the  colorization Method  possess statistical differences in their RGB channels, hue and saturation channels and also need to observe statistical inconsistencies in the dark and bright channels, because the colorization process will mainly  affect the dark and bright channel values. Based on the experiments in the hue, saturation, dark and bright channels, two simple yet effective detection method Histogram based and Feature Encoding based Fake Colorized Image Detection along with the dense convolution network are proposed for  detecting the fake colorized images},
        keywords = {image forgery, image detection, histogram, feature encoding, neural network.},
        month = {},
        }