Retrieving similar images from a large image database is a critical task. The solution to this problem is the use of a Content-Based Image Retrieval System. The images are described through their content, there is three predominant content existing in an image like color, shape, and texture. In this paper, we are evaluating the performance of the CBIR system using two methods. The first method consists of Block Truncation coding (BTC) with Grey level co-occurrence matrix (GLCM). The second method consists of Use of CNN. The feature extraction technique is achieved based on an input query image from the database and features are saved in a feature dataset. A proposed strategy retrieves similar images from a database that fulfills the user's desire. The similarity measurement can be done using the Euclidean distance and hashing technique. The overall performance of the retrieval system has been analyzed through the parameters Precision and Mean Average Precision. The experimental result shows encouraging results using CNN which leads to improving accuracy.
Pneumonia is a dangerous and serious lung disease. Generally, Chest Radiographs are used to detect pneumonia. This article describes a new method based on Convolutional Neural Network (CNN) classifiers that can identify pneumonia from a patient’s X-ray. Hence, we are proposing pneumonia detection based on CNN using chest X-ray. In this paper, we analyze the existing methods of pneumonia detection and classification techniques. The performance of the proposed CNN model is compared with VGG19 and ResNet50-V2. Performance evaluation is done using Precision and Recall. The proposed CNN model provides higher accuracy compared to existing CNN models.
In today's world due to multimedia development, there is a huge image database. Content-Based Image retrieval (CBIR) is a widely used method for image retrieval from a large image database. Existing retrieval methods are based on the basic content of an image like color, Shape, and Texture. The system based on basic features requires more time for processing and provides less accuracy. To reduce time and improve accuracy we are proposing CBIR Using CNN in this paper. CNN is used for feature extraction and similarity measurement Hamming distance is used. In this technique, the user has to provide an image as an input query image. The similar images related to the query image are displayed as a result. The performances of a system are evaluated by precision and mean average precision (MAP). After comparing with existing methods, we found encouraging results that lead to improving accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.