Design a Framework for Content Based Image Retrieval Using Hybrid Features Analysis Ankit Kumar 1 , Kamred Udham Singh 2* , Linesh Raja 3 , Teekam Singh 4 , Chetan Swarup 5 , Abhishek Kumar 6 1 Computer Science and Engineering, Swami Keshvanand Institute of Technology, Management & Gramothan, Jaipur 302017, India 2 Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan 701, Taiwan 3 Department of Computer Application, Manipal University Jaipur, Jaipur 303007, India 4 Department of Mathematics, Graphic Era Hill University, Society, Area, Clement Town, Dehradun 248002, Uttarakhand, India 5 Basic Science, College of Science and Theoretical Studies, Saudi Electronic University, Riyadh-Male Campus, Riyadh 11673, Saudi Arabia 6 Department of Computer Science and IT, JAIN (Deemed to be University), Bengaluru 560069, India Corresponding Author Email: 11004033@gs.ncku.edu.tw https://doi.org/10.18280/ts.380520 ABSTRACT Received: 25 August 2021 Accepted: 2 October 2021 In recent years, scholars have found content-based image recovery to be a particularly interesting and exciting field. This field develops quick image recovery algorithms that are very similar to pictures from various data sources. There is currently a lot of space and sources for data storage. Finally, once data sources are obtained, there is just competition for the exact and best result. The result is filtered using the heuristic correlation based on the above features of the photographs. The overall matching scores are calculated by adding all these individual feature ratings. The recommended method will be used to retrieve all images containing the content of the query image. The scores will be used to rate the match. The results of the combined method simulation demonstrate that the strategy is successful. This proposed model will improve the accuracy of search results. This research model, like the other metadata models on the web, is interactive and familiar for searching pictures from huge databases and data sources. This model also has a number of handy features built in to improve precision and efficiency. Although there are a few little mysteries in this model, they must be answered subsequently. Keywords: RGB, HSV, image content, histogram, CBIR, efficiency 1. INTRODUCTION In today's world, CBIR (Content Based Image Retrieval) is a wide subject that is open to new ideas and growth [1, 2]. There are two techniques for searching for images: the first is text-based searching, which is the old-fashioned manner, and the second is content-based or retrieval methods, which is also known as query by example searching. In the first approach, the user must input the keywords for the photos, and the search will proceed on the basis of the keywords entered. This method may be seen in action in the Google search engine. When using the content-based image retrieval technique, on the other hand, there are certain image factor contents, and these contents are in the form of distances. These distances can simply be matched with the query image for an accurate result. In a typical query image, the user can provide a field of interest for the researchers who will be working on the image. The usage of the internet and World Wide Web applications is rising at an exponential rate, as is the amount of data available to users. Every day, or we might say every minute, a massive quantity of picture database is added to the internet, and this number is growing by the minute. Because of this, it is clear that we require effective and efficient retrieval systems for this massive picture collection in order to obtain correct results. The development of new techniques and attempts to alter existing methods are ongoing activities for researchers working toward the achievement of these types of approaches. For searching the visually similar images from a large database is done by its visual information. It is obvious that the system using this method of retrieving the images from database need not to face the drawbacks of text-based searching. By means no need of entering the keywords manually, because now the search is based on visual information itself. The searching of images with the help of their visual content like color, texture and shape is called CBIR (Content Based Image Retrieval). CBIR is system or technique to organize and retrieve the images on behalf of their visual information. The following are the two main steps for CBIR [3]: 1. The image has to change in mathematical form by re- encoding and stored in a database. 2. There should be a method to compare the query and stored images (mathematical forms). An image is a collection of pixels and it will remain same with contained features except it is not re encoded into other form. These pixels have gap between them, and this gap contains the visual information about the image, so by re- encoding process this information can be capture and store. This process is called feature extraction. The mathematical form that images contains called its signature and the components of signature are called features [4, 5]. A color moment is an example of signature constructed from color feature. Some visual information about the image Traitement du Signal Vol. 38, No. 5, October, 2021, pp. 1449-1459 Journal homepage: http://iieta.org/journals/ts 1449