Content-Based Image Retrieval and Fusion

**3**

**Chapter 1**

**Abstract**

frameworks

**1. Introduction**

Frameworks

we draw a conclusion in Section 9.

*Saliha Mezzoudj*

Towards Large Scale Image

Retrieval System Using Parallel

Recently, the increasing use of mobile devices, such as cameras and smartphones,

has resulted in a dramatic increase in the amount of images collected every day. Therefore, retrieving and managing these large volumes of images has become a major challenge in the field of computer vision. One of the solutions for efficiently managing image databases is an Image Content Search (CBIR) system. For this, we introduce in this chapter some fundamental theories of content-based image retrieval for large scale databases using Parallel frameworks. Section 2 and Section 3 presents the basic methods of content-based image retrieval. Then, as the emphasis of this chapter, we introduce in Section 1.2 A content-based image retrieval system for large-scale images databases. After that, we briefly address Big Data, Big Data processing platforms for large scale image retrieval. In Sections 5, 6, 7, and 8. Finally,

**Keywords:** big data processing platforms, image retrieval system, big data, parallel

Computer vision (also called artificial vision or digital vision) is a branch of artificial intelligence whose main goal is to allow a machine to analyze, process and understand one or more images taken by an acquisition system (example: cameras, mobile, etc.) [1]. It is used to automate the tasks that the human visual system can do: recognition, motion analysis, scene reconstruction, and image restoration [1]. In this chapter, we are interested in the recognition task, there are several specialized applications based on recognition exist, such as content image search (CBIR) and image classification systems. Image classification is an important task in the field of computer vision, and it requires the development of robust classification systems, which can improve the performance

of vision systems. Indeed, most image CBIR systems have three stages:

CBIR system returns the closest images to the user [2, 3].

the core of current image classification systems.

• The first step: it is the extraction of low-level characteristics of the images (extraction of descriptors). Indeed, the use of low-level image descriptors is

• the searching step, in which the feature vector of a query image is computed and compared to the image feature vectors of the database. As a result, the
