• Kritika Sharma
• Shraddha Mane
• Jyoti Ware
• Prof.. Zarina Shaikh

During previous number of years, the planet Wide Web (WWW) has become a particularly well-liked data source. To with success utilize the huge amount of knowledge that the net provides, we wish a good thanks to explore it. Image knowledge is far additional voluminous than matter knowledge, and visual data can't be indexed by ancient methods Developed for compartment allocation matter data. Therefore, Content-Based Image Retrieval has received a wonderful deal of interest among the analysis community. A CBIR system operates on the visible options at low-level of a user's input image that makes it difficult for the users to plot the input and additionally does not supply adequate retrieval results. In CBIR system, the study of the helpful illustration of options and appropriate similarity metrics is very necessary for improving the performance of retrieval task. Linguistics gap has been the most issue that happens between image pixels at low level and linguistics at high-level understood by humans. Among varied ways, machine learning (ML) has been explored as a feasible thanks to cut back the linguistics gap. Galvanized by the present success of deep learning ways for pc vision applications, during this paper, we tend to aim to confront AN advance deep learning methodology, referred to as Convolutional Neural Network (CNN), for learning feature representations and similarity measures. During this paper, we tend to Explored the applications of CNNs towards determination classification and retrieval issues. For retrieval of comparable pictures, we tend to in agreement on victimization transfer learning to apply the Google Net deep design to our downside. Extracting the last-but-one absolutely connected layer from the retraining of Google Net CNN model served because the feature vectors for each image, computing Euclidian distances between these feature vectors which of our question image to come the highest matches within the dataset.

Deep Learning, Convolutional Neural Network, Transfer Learning,

"Image Retrieval Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.a729-a732, June-2021, Available :http://www.jetir.org/papers/JETIR2106100.pdf

"Image Retrieval Using Deep Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppa729-a732, June-2021, Available at : http://www.jetir.org/papers/JETIR2106100.pdf