**4. Software and applications**

There are a variety of software that can be used for image processing. For example, Matlab has many tools for image processing; it also facilitates to develop graphical user interfaces (GUI). ImageJ can be utilized for simple things, whereas Amira can be used for complex tasks. In case of medical applications, eFilm is one of the useful tools.

Applications of image processing range from medicine to entertainment and much more. Some of the important applications of image processing in the field of science, engineering, and technology include image sharpening and restoration, remote sensing, feature extraction, face detection, forecasting, optical character recognition, biometrics, medical imaging, optical sorting, augmented reality, virtual reality, video processing, microscope imaging, license plate recognition, lane departure caution, transportation, parking, transmission and encoding, machine vision, robotics, color processing, signature recognition, iris recognition, face recognition, forensics, automobile detection, fault detection, pattern recognition, military applications, and others. Following subsection has been dedicated to an application of license plate recognition (LPR) with systematic methodologies.

#### **4.1 License plate recognition**

Here is an example of different tasks and phases for a system to recognize license plates from the front and rear of the vehicle [58–60]. Input to the system is an image sequence acquired by a digital camera that consists of a license plate and its output is the recognition of characters on the license plate. The system consists of the standard four main modules in an LPR system which includes image acquisition, license plate extraction, license plate segmentation, and license plate recognition. The structure of the system is shown in **Figure 1**. The first task acquires the selected portion of the image (i.e., the portion which contains a license plate). The second task extracts the region that contains the license plate. The third task isolates the characters, consisting of letters and numerals, depending on the targeted License Plates. The last task identifies or recognizes the segmented characters.

**Image acquisition:** This is the first phase in an LPR system. This phase deals with acquiring an image by an acquisition method. In the LPR system, we need to use a high resolution digital camera to acquire the input image. The input image can be taken for example 640 × 480 pixels.

**License plate extraction:** License plate extraction is a key step in an LPR system, which influences the accuracy of the system significantly. This phase extracts the region of interest, i.e., the license plate, from the acquired image. The proposed

**Figure 1.** *Structure of the proposed system.*

approach involves four steps including vertical edge detection, size-and-shape filtering, vertical edge matching, and finding B/W (Black/White) ratio.

**License plate segmentation:** License plate segmentation takes the region of interest and attempts to divide it into individual characters. To ease the process of detecting the characters, the extracted plate is divided into independent images, each containing one isolated character with letters and numerals depending on the structure of the license plate. It is proposed to have segmentation using two methods: Pixel Count and Horizontal and Vertical Projection.

**License plate recognition:** The last phase in LPR system is to recognize the isolated characters. After splitting the extracted license plate into six images, the character in each image can be identified. There are many methods to recognize isolated characters; we suggest using Syntactic approach and Neural network approach.
