Deep CNN Based Hybrid Model for Image Retrieval

The popularity of deep features based image retrieval and classification task has grown a lot in the recent years. Feature representation on Convolutional Neural Networks (CNNs) found to be very effective terms accuracy by various researchers field visual content retrieval. which are neutral their domain knowledge with automatic learning capability from images demand applications. For improving expressive power, pre-trained CNN models use transfer can utilized training them huge volume datasets. In this paper, hybrid model for is being proposed using values hyper parameters as input parameters. performance compared existing showing higher precision recall