• Prof Arti Devmane
• Sapna Nilkanth Kedar
• Nandini khandade
• Utkarsha Dhanawade

The proliferation of digital images on the internet and personal devices has created a pressing need for efficient image retrieval systems. This paper proposes a Similar Image Finder (SIF) utilizing machine learning techniques to address this challenge. The system employs a combination of feature extraction methods, such as Convolutional Neural Networks (CNNs), to capture the visual characteristics of images. These features are then mapped into a lower-dimensional space using dimensionality reduction techniques like t-distributed Stochastic Neighbor Embedding (t-SNE) or Principal Component Analysis (PCA). The resulting representations enable efficient comparison and retrieval of visually similar images. Moreover, the system can be trained on large datasets to learn discriminative features that generalize well across various image types and domains. Experimental results demonstrate the effectiveness of the proposed SIF in retrieving visually similar images accurately and efficiently. Additionally, the system's scalability and potential applications in image search engines, content recommendation systems, and digital asset management are discussed.

similar image finder, CNN, PCA, Image search engines.

"Similar Image Finder Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.94-100, June-2024, Available :http://www.jetir.org/papers/JETIRGH06015.pdf

"Similar Image Finder Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp94-100, June-2024, Available at : http://www.jetir.org/papers/JETIRGH06015.pdf