• B.TEJASRI
• P.T.S .PRIYA

It is necessary to match slightly altered photos to the original image in order to find near duplicate images. This will make it easier to spot faked photographs. Visual has received a significant lot of attention. applications that require effective image signature and similarity metrics. Picture recoloring is a method that can change an image's colour or theme without being noticeable to the human eye. Although being one of the most common image alteration techniques, image recoloring cannot be detected using a specific method. Three feature extraction blocks and a feature fusion module make up the CNN-based deep architecture that our method uses. We create a dataset of recolored images and the related ground truth using several recoloring techniques in order to train the deep neural network. Comprehensive testing findings on the Recolored images produced by different approaches demonstrate how well-generalized and robust our proposed network is.

Altered photos, CNN Algorithm, Structural Similarity, inter-channel correlation, digital photography, forgery detection ,password Authentication, Augmentation

"DETECTION OF RECOLORED IMAGE USING A DEEP DISCRIMINATIVE MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.f8-f17, March-2023, Available :http://www.jetir.org/papers/JETIR2303502.pdf

"DETECTION OF RECOLORED IMAGE USING A DEEP DISCRIMINATIVE MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. ppf8-f17, March-2023, Available at : http://www.jetir.org/papers/JETIR2303502.pdf