Article Preview
Top1. Introduction
Image enhancement aims to contrast improvement of the original images. When the image display appropriately, a computer system or human can extract the required information. The image enhancement methods can be classified into four main parts: Pseudo coloring, transformation, unique domain, and point domain. The transformation of the histogram is used to improve the contrast of gray-level images. The histogram equalization method is popular, but the disadvantages are that output images have unnatural contrast and lighting. Image enhancement can be used in different applications for image processing, such as contrast enhancement, noise reduction, edge restoration, and edge enhancement (Singh, Kohli, and Diwakar 2013)(Maini and Aggarwal 2010). Global histogram equalization is the most common way of enhancing contrast in a picture. During the previous few decades, many approaches are used to enhance the contrast of image like Range Limited Bi-Histogram equalization (RLBHE), Brightness Preserving Bi-Histogram Equalization (BBHE), Brightness Error Bi-Histogram Equalization (MMBEBHE), Equal Area DSIHE(Dualistic Sub-Image Histogram Equalization) and rightness Preserving Bi-Histogram Equalization (BBHE) (Singh, Kohli, and Diwakar 2013).
The firefly algorithm is a simulated evolutionary algorithm used for parallel searching on local and global extremum. The firefly algorithm-based local enhancement algorithm has been used to optimize parameters search for better enhancement. The firefly algorithm is a modern heuristic algorithm applied to the non-continuous and non-linear optimization problem. The characteristics of the firefly algorithm are like minimum computation rate and higher converging to optimization problem solution. The greedy heuristic method is used to contrast enhancement of images (Majumder and Irani 2006). Hassanzadeh et al. (Hassanzadeh, Vojodi, and Mahmoudi 2011) developed a firefly algorithm-based adaptive local enhancement algorithm to improve the detail and grayscale of source images. Gopal et al. (Dhal et al. 2015) developed two algorithms to improve the contrast between low-contrast images using chaotic sequence and levy flight. All algorithms were applied to optimized Boost Filter parameters. Ye et al. (Ye, Zhao, and Ma 2015) developed an adaptive firefly algorithm to find optimal parameters and produce a gray level curve transformation to enhance images. This algorithm achieved the effective optimal parameters in an adaptive manner, which results better. Samanta et al. (Samanta et al. 2018) proposed the Mini Unmanned Aerial Vehicle (MUAV) system for capturing the low contrast /quality image. The firefly algorithm-based image enhancement method for gray level is used to enhance the image contrast. Xie et al. (Xie et al. 2019) developed two Types of Firefly algorithms like inward intensified exploration Firefly Algorithm and compound intensified exploration Firefly Algorithm. The first variant was found by the replacement of the attractiveness coefficient with a randomized control matrix. In the compound intensified exploration, firefly employs a dispensing mechanism. The Bat algorithm, firefly algorithm, and particle swarm optimization algorithm are used to solve the optimization problem.
Various image removal techniques are also used filters. Narendra et al. (Narendra Kumar, Dahiya, and Kumar 2020b), (Narendra Kumar et al. 2019), (N. Kumar, Dahiya, and Kumar 2020), (Narendra Kumar, Dahiya, and Kumar 2020a) Experimental results show that these more efficient for removing multilevel noise.