• Varun S
• Nagaraja S. R

The research implements Spatial Transformer Networks (STNs) as an advancement strategy for near-duplicate image detection algorithms built with deep learning models. The Spatial Transformer Network (STN) helps the system master spatial transformation corrections for translation and rotation and scaling and cropping of images which are typical near-duplicate image variations. By integrating STNs into Convolutional Neural Networks (CNNs) together with Vision Transformers (ViTs) the models obtain the capability to normalize image alignment prior to feature extraction. Using STNs in image detection systems creates improved performance levels in near-duplicate image recognition. The investigation combines different STN architectures and integration methods to obtain optimal system performance results. This project enhances image retrieval methods and similarity analysis through the correction of SIFT and SURF limitations in addition to resolving current deep learning technique challenges. The experimental process will demonstrate the operational effectiveness of STNs for illuminating spatial differences in near-duplicate image detection.

Near-duplicate image detection, Spatial Transformer Networks (STNs), Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), spatial transformations, image alignment, deep learning

"Enhancing near duplicate image detection using spatial transformer networks in deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 5, page no.k796-k803, May-2025, Available :http://www.jetir.org/papers/JETIR2505B69.pdf

"Enhancing near duplicate image detection using spatial transformer networks in deep learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 5, page no. ppk796-k803, May-2025, Available at : http://www.jetir.org/papers/JETIR2505B69.pdf