Content-Based Image Recognition and Tagging by Deep Learning Methods

Deep learning techniques is growing wider day by day in the process of Content based Image retrieval (CBIR). The recognition of the image is based on its shape, attributes, and tag. It is challenging to establish the connection between semantic ideas in the vast real-world applications. The social media is dominating the globe by throwing its wide range of features where the people are finding difficulty in choosing their suitable objects or images because of any redundancy. So the proposed method is based on Content-based image recognition and tagging by using deep learning techniques. The tagging of the image is used here for easy identification of the objects. The Geon similarity model is used to extract the maximum similarity of the different images by its accurate and rapid computation methods. The modified grey wolf optimization method and the novelty based convolution neural network, ResNet-50, is applied here as a hashing technique and classifier to get high recognition rate and accuracy values when compared to the state of art methods. The performance attributes of the modified convolutional neural network give a high value of precision, accuracy, recall, and mAP.