Copyright © 2026 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{169663,
        author = {S.Jahnavi and Shanmukha Priya and Sandeep Kumar and Sai Sandeep},
        title = {Facial Photo Blending System  By Using Digital Image Processing},
        journal = {International Journal of Innovative Research in Technology},
        year = {2024},
        volume = {11},
        number = {6},
        pages = {2026-2033},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=169663},
        abstract = {This paper introduces a new Photo Blending system approach to FSS in pursuit of performance enhancement regarding verification and recognition identity, which current approaches typically fail to realize when it tends to miss some important specific identity information in the traditional approach. Inter-domain transfer occurs without losing any critical facial structures that are learnt as regressor between test and training photos; and intra-domain transfer tries to boost recovery of identity-specific information through a mapping of relationships between sketches and photographs across different identities. To facilitate research in this area, we present FS2K, a comprehensive dataset containing 2,104 image-sketch pairs that encompass various sketch styles, backgrounds, and facial attributes. Additionally, we propose FSGAN, a baseline method that utilizes facial-aware masking and style- vector expansion, significantly outperforming existing state-of-the art models on the FS2K dataset. Our dual Path Frame- work With its finest adjustment of coarse crossdomain reconstructed texture into a finer resolution and then combined with detailed refinement, in addition to a spatial feature calibration module that boosts alignment, the proposed method supports exemplar-guided image-to-image translation and fine-grained cross domain editing tasks. Thorough experiments demonstrate that the aforementioned method is better in both photo-to- sketch synthesis and identification recognition tasks; consequently, our framework contributes valuable insights as well as resources to the FSS research community.},
        keywords = {Face Sketch Synthesis (FSS), Inter-domain Transfer, FS2K Dataset, FSGAN, Dual Path Framework.},
        month = {November},
        }