• Chamakuri Upendar
• Chitikela Srinivas
• Raju Bulla

The exponential growth of digital visual content in recent years has posed significant challenges in the management and organization of image datasets. Among these challenges, the presence of duplicate or visually similar images stands as a pervasive problem, causing data clutter, inefficient resource utilization, and hindering image retrieval tasks. In response to this issue, the "Image Duplicate Detection with CNN using imagededup" project offers an innovative and automated solution. This project employs the potent combination of Convolutional Neural Networks (CNNs) and the specialized image processing library, imagededup, to achieve the primary objective of detecting and managing duplicate images within diverse image datasets. By harnessing the feature extraction capabilities of CNNs and the efficient hashing techniques provided by imagededup, the system automates the detection and removal of duplicate images. This automation not only optimizes storage utilization but also improves image retrieval efficiency, resulting in a cleaner and more user-friendly image database.

imagededup, CNN, detection, feature extraction

"A FRAMEWORK TO DETECT DUPLICATE IMAGES USING CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.a481-a485, March-2024, Available :http://www.jetir.org/papers/JETIR2403063.pdf

"A FRAMEWORK TO DETECT DUPLICATE IMAGES USING CNN", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppa481-a485, March-2024, Available at : http://www.jetir.org/papers/JETIR2403063.pdf