An Image Recognition/Retrieval System: Design And Implementation

Introduction This paper describes the design and implementation of an image recognition / retrieval system using a parametric color histogram index. As the use of multimedia data has increased in recent years, efficient and efficient methods for storing and retrieving multimedia have been developed. In particular, images are used as important inputs in various fields. The field of content-based image retrieval is a hybrid research field requiring knowledge of computer vision and database system.

An image retrieval system is a computer system for viewing, retrieving and retrieving images from a large digital image database. Powerful natural, geographical and medical image retrieval using supervised classifiers focused on extracted features has been proposed. We implemented gray level co-occurrence matrix (GLCM), scale invariant feature technology (SIFT) and moment invariant features, extracted features from natural images, and performed GLCM and Gabor feature extraction on medical images.

This project includes the design and implementation of image processing system for face recognition using MATLAB. Because image processing is a complex task, you need to learn all the background information necessary for image formation and processing, and master key MATLAB functions that you must use. The purpose of this research was to study software applications that show how images are processed on a computer platform. Processing is done by comparing the sketch image with the real image and the matrix model using the MATLAB program. The image is displayed after the program is executed normally. To generate images from real images or matrices, use MATLAB functions. Various functions such as filtering and rotation can be used according to users. In this research, the photos and actual images being used are from the correct reference to the Internet, scanner, etc. Since this program uses only the MATLAB program, basic mathematical calculation can not be used.

Development of multifaceted authentication (MFR) system is useful for domain applications such as bank security management. In this project, students will experience the whole process of designing and implementing the MFR system. Important steps include database building, feature-based recognition algorithms, clustering and learning classification methods, system implementation, and robustness analysis. Learning pseudo metrics (LPM) can be used for data mining tasks, previous work showed that they have the ability to improve clustering and classification performance of semantic data. Random weighted neural networks (RWNNs) are a kind of probabilistic basis function networks proven to have excellent possibilities for modeling large scale data in high dimensional space. The project is aimed at developing an RWNN-based learning pseudo-metric framework for data mining. In this research, we use a benchmark dataset containing semantic clustering and classification.