An image contrast enhancement method based on genetic algorithm Sara Hashemi, Soheila Kiani, Navid Noroozi, Mohsen Ebrahimi Moghaddam * Electrical and Computer Engineering Department, Shaid Beheshti University, G.C, Tehran, Iran article info Article history: Available online 11 December 2009 Keywords: Contrast enhancement Genetic algorithm Natural looking images abstract Contrast enhancement plays a fundamental role in image/video processing. Histogram Equalization (HE) is one of the most commonly used methods for image contrast enhancement. However, HE and most other contrast enhancement methods may produce un-natural looking images and the images obtained by these methods are not desirable in applications such as consumer electronic products where bright- ness preservation is necessary to avoid annoying artifacts. To solve such problems, we proposed an effi- cient contrast enhancement method based on genetic algorithm in this paper. The proposed method uses a simple and novel chromosome representation together with corresponding operators. Experimental results showed that this method makes natural looking images especially when the dynamic range of input image is high. Also, it has been shown by simulation results that the proposed genetic method had better results than related ones in terms of contrast and detail enhancement and the resulted images were suitable for consumer electronic products. Ó 2009 Elsevier B.V. All rights reserved. 1. Introduction Contrast enhancement is a process that is applied on images or videos to increase their dynamic range. Since now, many algo- rithms have been proposed for such an aim. Histogram Equaliza- tion (HE) is one of the most commonly used method for contrast enhancement (Gonzalez and Woods, 2008; Jain, 1989; Zimmerman et al., 1988; Kim, 1997; Kim et al., 1998). It is a simple method and has been used in various fields such as medical image processing and texture analysis (Pei et al., 2004; Wahab et al., 1998; de la Torre et al., 2005; Pizer, 2003). The main objective of this method is to achieve a uniform distributed histogram by using the cumula- tive density function of the input image (Chen and Ramli, 2003). It has been shown that the mean brightness of the histogram-equal- ized image is the middle gray level of the input image regardless of its mean (Chen and Ramli, 2003). This is not a suitable property in some applications such as consumer electronic products, where brightness preservation is necessary to avoid annoying artifacts (Chen and Ramli, 2003). To overcome brightness preservation problem, different meth- ods that were based on Histogram Equalization have been pro- posed. Mean preserving Bi-Histogram Equalization (BBHE) (Kim, 1997), equal area Dualistic Sub-Image Histogram Equalization (DSIHE) (Wan et al., 1999), Minimum Mean Brightness Error Bi- Histogram Equalization (MMBEBHE) (Chen and Ramli, 2003), and Recursive Mean-Spread Histogram Equalization (RMSHE) (Chen and Ramli, 2003) are HE based methods which tend to preserve the image brightness with a significant contrast enhancement. In BBHE, histogram of the input image is separated into two parts according to the mean of gray levels and each part is equalized independently. DSIHE is similar to BBHE except that it separates the histogram at the median of gray levels instead of the mean. MMBEBHE is an extension of BBHE and provides maximal bright- ness preservation. In RMSHE, scalable brightness preservation is achieved by partitioning the histogram recursively more than once. This technique is a generation of BBHE. Although these methods preserve the input image brightness on output, they may fail to produce images with natural looks (Menotti et al., 2007). In order to overcome this drawback, two Multi Histogram Equalization (MHE) methods, i.e. Minimum Middle Level Squared Error MHE (MMLSEMHE) and Minimum Within-Class Variance MHE (MWCVMHE), have been proposed (Menotti et al., 2007). These methods work by dividing the input image into several sub-images and applying the classic HE to each of them. In these methods, number of sub-images is determined by a cost function. The main difference between proposed methods is the way of in- put image decomposing. Nevertheless, they usually perform a less intensive image contrast enhancement (Menotti et al., 2007). This is the cost that is paid for achieving contrast enhancement, bright- ness preservation and natural looking images at the same time (Menotti et al., 2007). The Histogram Equalization based methods is divided into two major categories: global and local methods (Abdullah-Al-Wadud et al., 2007). In Global Histogram Equalization (GHE) (Gonzalez and Woods, 2008), the histogram of the entire image is used for 0167-8655/$ - see front matter Ó 2009 Elsevier B.V. All rights reserved. doi:10.1016/j.patrec.2009.12.006 * Corresponding author. Tel.: +98 2129902268; fax: +98 2122431804. E-mail addresses: s.hashemi@mail.sbu.ac.ir (S. Hashemi), So.Kiani@mail.sbu.ac.ir (S. Kiani), Na.noroozi@mail.sbu.ac.ir (N. Noroozi), m_moghadam@sbu.ac.ir (M.E. Moghaddam). Pattern Recognition Letters 31 (2010) 1816–1824 Contents lists available at ScienceDirect Pattern Recognition Letters journal homepage: www.elsevier.com/locate/patrec