**2. The methods for extracting visual characteristics**

The extraction of features from images is the basis of any computer vision system that does recognizing. These characteristics can contain both text (keywords; annotations, etc.), and visual characteristics (color, texture, shapes, faces, etc.). We will focus on techniques for extracting these visual features only. And for that the visual characteristics (descriptors) are classified in two categories general descriptors and specific domain descriptors [7, 8]:

#### **2.1 General descriptors**

They contain low-level descriptors that give a description of color, shape, regions, textures and movement.

**Color:** Color is one of the most used visual characteristics in facial recognition systems or anything like that. It is relatively robust to the complexities of the background and independently of the size and orientation of the image. The most well-known representation of color is the histogram, which denotes the frequencies of occurrence of the intensities of the three color channels. Many other representations of this characteristic exist: we speak especially of the moments of color. The mathematical basis of this approach is that each color distribution can be characterized by its color moments. Furthermore, most of the information on color is concentrated on lower order moments which are respectively: mean, standard deviation, color skewness, variance, median, etc.

**Texture:** A wide variety of texture descriptors have been proposed in the literature. These were traditionally divided into statistical, spectral, structural and hybrid [9] approaches. Among the most popular traditional methods are probably those based on histograms, Gabor filters [10], co-occurrence matrices [11] and models (lbp) [12]. These descriptors present various strengths and weaknesses, in particular as regards their invariance with respect to the acquisition conditions.

**Shape:** Over the past two decades, 2D shape descriptors have been actively used in 3D search engines and sketch-based modeling techniques. Some of the most popular 2D shape descriptors are curvature scale space (CSS) [13], SIFT [14], and SURF [15]. In fact, in the literature, 2D shape descriptors are classified into two main categories: contours and regions. Outline-based shape descriptors extract shape entities from the outline of a shape only. In contrast, region-based shape descriptors obtain shape characteristics of the entire region of a shape. In addition, hybrid techniques have also been proposed, combining techniques based on the contour and the [16] region.

**Movement:** Movement is related to the movement of objects in the sequence and to the movement of the camera. The latter information is provided by the capture device, while the rest is implemented by means of image processing. The set of descriptors is the following [7]: Motion Activity Descriptor (MAD), Camera Motion Descriptor (CMD), Motion Trajectory Descriptor (MTD), and Warp and Parametric Motion Descriptor (WMD and PMD).

**5**

*Towards Large Scale Image Retrieval System Using Parallel Frameworks*

**Location:** The location of items in the image is used to describe items in the spatial domain. In addition, elements can also be located in the [7] time domain: Region Locator Descriptor (RLD), Spatio Time Locator Descriptor (STLD).

Image classification is an important step in the image recognition process. Indeed, many image classification techniques have been proposed to date. It is considered to be one of the main types of machine learning. Various studies have been carried out in order to choose the best technique for classifying [17] images.

It is one of the subdomains of artificial intelligence (AI) which uses a series of techniques to let computers learn, (that is, gradually improve the performance of the computer on a task specific) with data, without being explicitly programmed. Indeed, machine learning covers a vast field of tasks. Below are the types of

**Supervised learning (classification):** In this case, the entries are tagged by an expert, and the algorithm must learn from the tags of these entries in order to predict the class of each new entry. In other words, from a set of observations X and another set of measures Y, we seek to estimate the dependencies between X and Y. **Unsupervised learning (clustering):** In this case, the entries are not labeled, no expert is available, and the algorithm must predict the class of each entry. The objective of this type of learning is to describe how the data is organized and to

**Semi-supervised learning:** the algorithm combines labeled and unlabeled

**4. A content-based image retrieval system for large-scale images** 

**Learning to learn:** where the algorithm learns its own inductive bias based on

Indeed, the most of conventional CBIR systems are evaluated on small bases of images that fit easily in main memory, such as Caltech-101 [19], Caltech-256 [20] or

Recently, the increase in images produced in different fields has enabled the acquisition and storage of a large amount of images, which offers new concepts such as Big Data, which are of huge volumes of images from a variety of sources, produced in real time and exceeding the storage capacity of a single machine. Indeed, these images are difficult to process with traditional image retrieval

As digital cameras become more affordable and ubiquitous, digital images are growing exponentially on the Internet, such as ImageNet 1 [22] which consists of 14,197,122 images labeled for 21,841 classes. Indeed, this enormous quantity of images makes the task of classification of images much more complex and difficult to perform, especially since traditional processing and storage methods do not

This challenge motivated us to develop a new image search and classification system allowing the storage, management and processing of large quantities of

always manage to cope with this enormous quantity of images.

*DOI: http://dx.doi.org/10.5772/intechopen.94910*

**3. Image classification**

**3.1 What is machine learning?**

extract homogeneous subsets.

previous experience.

**databases**

PASCAL VOC [21].

systems.

machine learning described in this section [18]:

examples to generate an appropriate function or class.

**Location:** The location of items in the image is used to describe items in the spatial domain. In addition, elements can also be located in the [7] time domain: Region Locator Descriptor (RLD), Spatio Time Locator Descriptor (STLD).
