Content-based image retrieval based on corel dataset using deep learning

A popular technique for retrieving images from huge and unlabeled image databases are content-based-image-retrieval (CBIR). However, the traditional information retrieval techniques do not satisfy users in terms of time consumption accuracy. Additionally, number accessible to growing due web development transmission networks. As result, digital creation occurs many places. Therefore, quick access these like a query collections provides significant challenges need an effective technique. Feature extraction similarity measurement important performance CBIR This work proposes simple but efficient deep-learning framework based on convolutional-neural networks (CNN) feature phase CBIR. The proposed CNN aims reduce semantic gap between low-level high-level features. measurements used compute distance database When first 10 pictures, experiment Corel-1K dataset showed that average precision was 0.88 with Euclidean distance, which big step up state-of-the-art approaches.