1. Introduction
Common and frequently serious disagreements exist between recorded natural color images and the direct observation of natural scenes. The human perception is very excels in constructing a visual representation with vibrant color and detail across the wide range of photometric levels due to variations in the light. In addition to the human vision computers color are to be relatively independent of spectral variations in illumination [1]. When we want to display a color image on a display device, either the low intensity as well as medium intensity areas, which are underexposed, or the high intensity areas, which are overexposed, cannot be seen by observer. In order to avoid this problem, a number of color contrast enhancement techniques have been developed during the past decades. The color contrast enhancement techniques are commonly used in various applications where subjective quality of the image is very important. The objective of image enhancement is to improve visual quality of image depending on the application conditions. Contrast is an important factor for any individual estimation of image quality. It can be used as controlling tool for documenting and presenting information collection during examination. The contrast enhancement of image refers to the amount of color differentiation that exists between various features in digital images. It is the range of the brightness present in the digital image. The images having a higher contrast level usually display a larger degree of color scale difference as compared to lower contrast level. The contrast enhancement is a process that allows image features to show up more visibly by making best use of the color presented on the display devices. During the last decade a large number of contrast enhancement algorithms have been developed for color contrast enhancement of images for various applications. These are histogram equalization [2], global histogram equalization [3], local histogram equalization [4], adaptive histogram equalization and Contrast Limited Adaptive histogram equalization [5, 6], and other techniques and algorithms [7-38]. One of the most widely used algorithms is global histogram equalization, the basic idea of which is to adjust the intensity histogram to approximate a uniform distribution. It treats all regions of the image equally and, thus often yields poor local performance in terms of detail preservation of image.
The outline of this paper is as follows. Section 2 describes literature review. Section 3 describes proposed method for contrast enhancement of natural color images. Section 4 gives simulation results and discussions to demonstrate the performance of the proposed method. Finally, conclusion is drawn in section 5.
2. Literature Review
The existing contrast enhancement techniques for mobile communication and other real time applications is fall under two broad categories mainly contrast shaping based methods and histogram equalization based methods [2]. These methods are derived from digital image processing. These methods may lead to over-enhancement and other artifacts such as flickering, and contouring. The contrast shaping based methods are worked on by calculating an input-output luminance curve defined at every luminance level. The shape of the curve must depend on the statistics of the image frame being processed. For example, dark images would have a dark stretch curve applied to them. Although contrasts shaping based methods are the most popular methods used in the consumer electronics industry but they cannot provide a localized contrast enhancement which is desirable. For example, when a dark stretch is performed, bright pixels become brighter. However, a better way to enhance darker images is to stretch and enhance the dark regions, while leaving brighter pixels untouched [2, 38]. A very popular technique for contrast enhancement of image is histogram equalization technique [2-4]. A histogram equalization is a technique that generates gray map which change the histogram of image and redistributing all pixel values to be as close as possible to user specified desired histogram. This technique is useful for processing images that have little contrast with equal number of pixels to each the output gray levels. The histogram equalization (HE) is a method to obtain a unique input to output contrast transfer function based on the histogram of the input image which results in a contrast transfer curve that stretches the peaks of the histogram (where more information is present) and compresses the troughs of the histogram (where less information is present) [2]. Therefore it is a special case of contrast shaping technique. As a standalone technique, histogram equalization is used extensively in medical imaging, satellite images and other applications where the emphasis is on pattern recognition and bringing out of hidden details. Thus histogram equalization results in too much enhancement and artifacts like contouring which is unacceptable in consumer electronics [5-6].
During the last decade a number of techniques have been proposed by various researchers to deal with these problems. In [8], the histogram is divided into two parts based on the input mean, and each part is equalized separately. This preserves the mean value of image to a certain extent. In [9], each peak of the histogram is equalized separately. An adaptation of HE, termed as contrast limited adaptive histogram equalization (CLAHE) [6] divides the input image into a number of equal sized blocks and then performs contrast limited histogram equalization on each block. The contrast limiting is done by clipping the histogram before histogram equalization. This tends to tone down the over enhancement effect of histogram equalization and gives a more localized enhancement. However it is much more computationally intensive than histogram equalization. If the blocks are non-overlapping, an interpolation scheme is needed to prevent blocky artifacts in the output picture. Therefore overlapping blocks can solve this problem (every pixel is replaced by the histogram equalization output using a neighborhood) but it is more computationally intensive than using non-overlapping blocks. So the CLAHE also requires a field store. Finally one more contrast enhancement method that is homomorphic filter is proposed in spatial domain [2]. In this filter images normally consist of light reflected from objects. The basic nature of the image may be characterized by two components: (1) the amount of source light incident on the scene being viewed, and (2) the amount of light reflected by the objects in the scene but this method does not provide good image quality [5]. Another method is histogram specification which takes a desired histogram by which the expected output image histogram can be controlled [2]. However specifying the output histogram is not a smooth task as it varies from image to image. In [10] D. J. Jobson, Z. Rahman, and G. A. Woodell introduced new algorithm to improve the brightness, contrast and sharpness of an image. This algorithm performs a non-linear spatial transform that provides simultaneous dynamic range compression [11]. The performance of this method is compared with other existing enhancement techniques such as histogram equalization and homomorphic filtering [12]. In [13] B. V. Funt, K. Barnard, M. Brockington, and V. Cardei have investigated the Multi Scale Retinex algorithm approach for image enhancement purpose, they explored the effect of processing from theoretical standpoint [13] and in the same year they modified the multi-scale retinex approach to image enhancement such that the processing is more justified from a theoretical standpoint they suggested a new algorithm with fewer arbitrary parameters and prove it is more flexible [14]. In [15] A. A. Bayaty has suggested a new method to calculate image contrast and evaluate image quality depending on computing the image contrast in edge regions. Author has introduced robust quantitative measures to determine image quality, and after that estimated the efficiency of the various techniques in image processing applications. In [16] L. Tao, M. J. Seow and V. K. Asari have proposed image contrast enhancement method to improve the visual quality of digital images that exhibit dark shadows due to the limited dynamic ranges of imaging and display devices which are incapable of handling high dynamic range scenes. The proposed technique processes images by applying two separate steps: dynamic range compression and local contrast enhancement. Dynamic range compression is a neighborhood dependent intensity transformation which is able to enhance the luminance in dark shadows while keeping the overall tonality consistent with that of the input image. In [17] A. J. A. Dalawy has studied the TV satellite images. These images were the same with respect to the type on the three satellites. The analyzing these images was done statistically by finding the statistics distribution and studying the relations between the mean and the standard deviation of the color compound (RGB) and light component (L) for the image as whole and for the extracted homogeneous regions. Also author studied the contrast of image edges depending on sobel operator in neighbor area to the edges and studied the contrast as function for edge finding threshold and found that the Hotbird has the best results.
In [18] N. Hassan and N. Akamastu have proposed new approach for contrast enhancement using sigmoid function. The objective of this new contrast enhancer is to scale the input image by using sigmoid function. However this method is also have some side effects. In order to improve the performance of above mentioned technique another algorithm that is exact histogram specification (EHS) is proposed for contrast enhancement of images [19]. However this method is also have some side effects. In order to provide better result another technique that is brightness preserving dynamic fuzzy histogram equalization (BPDFHE) is proposed [20]. This technique is the modification of the brightness preserving dynamic histogram equalization technique to improve its brightness preserving and contrast enhancement abilities while reducing its computational complexity. This technique uses fuzzy statistics of digital images for their representation and processing. Therefore, representation and processing of images in the fuzzy domain enables the technique to handle the inexactness of gray level values in a better way which results provide improved performance. However this technique is also having some side effects. In [21] Celik and Jahjadi proposed contextual and variational contrast enhancement for image. This algorithm enhances the contrast of an input image using interpixel contextual information. This algorithm uses a 2-D histogram of the input image constructed using a mutual relationship between each pixel and its neighboring pixels. A smooth 2-D target histogram is obtained by minimizing the sum of frobenius norms of the differences from the input histogram and the uniformly distributed histogram. The enhancement is achieved by mapping the diagonal elements of the input histogram to the diagonal elements of the target histogram. This algorithm produces better enhanced images results as compared to other existing state-of-the-art algorithms but this method is also have some side effects.
In [22] H. Hu and G. Ni proposed an improved retinex algorithm for image enhancement purpose. This algorithm has provides very good performance for specific color images in terms of color constancy, contrast enhancement and computational cost. However, this algorithm is done in HSV color space rather than RGB space. Therefore an additional step is necessary to convert an image from RGB to HSV color space and vice-versa. However this algorithm is also have some side effects. In [23] Y. Terai et al. proposed a retinex model for color image contrast enhancement purpose. In this algorithm, the luminance signal is processed in order to reduce the computation time without changing color components from one format to other format. But the computation time of this algorithm is still large due to large scale Gaussian filtering. The algorithm is only suitable for gray images. However this algorithm is also have some side effects. In [24] L. He et al. proposed image enhancement algorithm based on retinex theory. This algorithm replaces brightness value of each pixel by the ratio of brightness value to the average values of the neighboring pixels. The main drawbacks of this algorithm are complexity, weakly illuminated, enlarged dynamic range. In [25] X. Ding et al. proposed a new enhancement algorithm for color image based on human visual system based on adaptive filter. This algorithm utilizes color space conversion to obtain a much better visibility. This algorithm has provides better effectiveness in reducing halo and color distortion. However, the main drawback of this algorithm is computational slow algorithm. On the other hand various researchers also proposed many algorithms for contrast enhancement in DCT based compressed domain such as alpha rooting (AR) [7], multi contrast enhancement (MCE) [26], modified histogram Equalization (MHE) [27], Adaptive Contrast Enhancement Based on modified Sigmoid Function (ACEBSF) [28], Multicontrast Enhancement with Dynamic Range Compression (MCEDRC) [29], Contrast Enhancement by Scaling (CES) [30], RGB retinex theory [31] and other methods for contrast enhancement [32-35]. In order to determine image quality metric, many existing image quality assessment algorithms use only limited image features.
During the past years various algorithms have been developed by various researchers, each algorithm has its own advantages and disadvantages. The main drawback of many existing image algorithms are the visual quality of the enhanced image is not good. In order to overcome this drawback of many existing contrast enhancement algorithms, a new method is proposed for contrast enhancement of different types of the natural color images. The proposed algorithm provide better contrast enhancement results as compared to other many existing contrast enhancement algorithms for different types of the natural color images such as NASA images, Hperspectral images and other types of images.
3. Proposed Algorithm
The proposed algorithm consists of two stages: in first stage lightness component in YIQ color space is transformed using sigmoid function, after the adaptive histogram equalization (AHE) method [6] is applied on Y component and in the second stage automatic color enhancement algorithm is applied. The proposed algorithm is abbreviated as Automatic Color Contrast Enhancement (ACCE) Algorithm. The model of proposed method is shown in Fig. 1.
Fig. 1.Block diagram of proposed algorithm
Stage-I: In the first stage the input color image is converted to YIQ Color space by RGB to YIQ color space transformation because it is used in the NSTC and PAL televisions of different countries. First advantages of this format is that grayscale information is separated from color data, so the same signal can be used for both color and black and white sets. In the NTSC format, image data consists of three components: luminance (Y), hue (I ), and saturation (Q). The first component, luminance, represents grayscale information, while the last two components make up chrominance (color information). Second advantage is that it takes advantage of human color-response characteristics. The eye is more sensitive to changes in the orange-blue (I) range than in the purplegreen range (Q), therefore less bandwidth is required for Q than for I. The color space transformation is given as:
After the color space transformation, the luminance component (Y) is normalized as follows:
Consider I (x, y) = Y = 0.299R + 0.587G + 0.114B, then the normalized Intensity is given by
After this the normalized lightness value is transformed by using sigmoid function is given by [35]
The plot between Sn and In is shown in Fig. 2.
Fig. 2.Relationship between input lightness In versus output lightness Sn
The processed lightness component is obtained by applying adaptive histogram equalization (AHE) [6] on the lightness component and the processed lightness component is denoted as YP for further reference. The YIQ to RGB color space transformation of the first stage is defined as follows
Stage - II: The automatic color contrast enhancement algorithm is given bellow:
Step(1) Convert R'G'B' to Y 'I 'Q'
Step(2) Set the following parameters
my _ Limit = 0.5, lower _ Limit = 0.008 upper_Limit = 0.092: my_Limit2 = 0.04; my_Limit3 = −0.04
Step(3) Calculate Y _ Adjust, I _ Adjust, Q _ Adjust and find Yn, In and Qn components
Step(4) Convert image YnInQn to RnGnBn (F1), the inverse color space transformation from YnInQn to RnGnBn color space is given as
Step(5) Normalized image intensity which is given below
F = F 1*255
Step(6) Final output image can be calculated as
Where Vmin= max {minimum value of RnGnBn with impact of lower limit (0.008) }
Vmax = max {maximum value of RnGnBn with impact of upper limit (0.992)}
4. Simulation Results and Discussions
In order to demonstrate the performance of proposed ACCE algorithm, it is tested on different natural color images such NASA color images, hyperspectral color images and other types of natural color images. The proposed ACCE algorithm and other existing algorithms are implemented using MATLAB software (MATLAB 7.6, release 2008a), and 4GB RAM with I3 Processor. Two experiments are conducted on different natural color images: in the first experiment the image quality metrics is evaluated and in the second experiment visual enhancement quality of image is obtained. In order to judge the performance of proposed ACCE algorithm the color image quality parameters such as colorfulness metric (CM), color enhancement factor (CEF) and CPU time are the automatic choice for the researchers. The higher values of CM and CEF imply that the visual quality of the enhanced image is good and a lower value of CPU time is good. The colorfulness metric (CM) and color enhancement factor (CEF) are defined in Eq. (7) and Eq. (8) respectively for natural color images. These non-reference image quality metrics are used to compare the performance of proposed ACCE algorithm and other existing contrast enhancement techniques such adaptive histogram equalization (AHE) [6], alpha rooting (AR) [7], multi contrast enhancement (MCE) [26], modified histogram Equalization (MHE) [27], Adaptive Contrast Enhancement Based on modified Sigmoid Function (ACEBSF) [28], Multi-contrast Enhancement with Dynamic Range Compression (MCEDRC) [29], Contrast Enhancement by Scaling (CES)[30], RGB retinex theory [31].
The test natural color images used for the experiment are available on the websites http://dragon.larc.nasa.govt/retinex/pao/news and http://vision.seas.harvard.edu/hyperspec/explorei.html
The colorfulness metric (CM) is no-reference image quality metric (CM). It is suggested by Susstrunk and Winkler [38]. The definition for this metric in the color space is as given below. Let the red, green and blue components of an image be denoted by R, G and B, respectively [30]. Consider α=R-G and β=(R+G)/2-B, then the colorfulness of the image is defined as
Where σα and σβ are standard deviations of α and β respectively. Similarly, μα and μβ are their means.
The color enhancement factor (CEF) between output image and input image is defined as:
4.1 Experiment 1
In this experiment the performance of proposed ACCE algorithm is tested on different natural color images such NASA color images (image11.jpg, image22.jpg, image99. jpg, and image110.jpg), Hyperspectral color images (image33.jpg, image44.jpg, and image55.jpg) and other natural color images (image66.jpg). The performance of proposed ACCE algorithm has been evaluated and compared with many existing contrast enhancement techniques such adaptive histogram equalization (AHE) [6], alpha rooting (AR) [7], multi contrast enhancement (MCE) [26], modified histogram Equalization (MHE) [27], Adaptive Contrast Enhancement Based on modified Sigmoid Function (ACEBSF) [28], Multi-contrast Enhancement with Dynamic Range Compression (MCEDRC) [29], Contrast Enhancement by Scaling (CES)[30], RGB retinex theory [31] for hyperspectral color images and other natural color images and for NASA color images. The performance of proposed ACCE algorithm and many other existing contrast enhancement techniques have been evaluated and compared in terms color fullness metric (CM), color enhancement factor (CEF) and CPU time which are given in Table 1 and Table 2. From Table 1 and Table 2, it is observed that the proposed ACCE algorithm provides higher values of CM) and (CEF) as compared to other many existing contrast enhancement techniques. And also proposed ACCE algorithm provides lower CPU time and litter more CPU time as compared to other existing algorithm as given in Table 1 and Table 2.
Table 1.Comparative performance of different methods for Hyperspectral images & other natural image
Table 2.Comparative performance of different methods for NASA images
4.2 Experiment 2
This experiment visualizes subjective image enhancement performance. The enhanced contrast of NASA images, Hyperspectral images and other natural color images have been compared with result of proposed ACCE algorithm and many other existing contrast enhancement techniques. The visual contrast enhancement results of proposed ACCE algorithm and many existing contrast enhancement techniques have been given from Fig. 3 to Fig. 8. Therefore, it can be noticed from Fig. 3(B) to Fig. 3(J), Fig. 4(B) to Fig. 4(J), Fig. 5(B) to Fig. 5(J), Fig. 6(B) to Fig. 6(J) Fig. 7(B) to Fig. 7(J) and Fig. 8(B) to Fig. 8(J) that proposed ACCE algorithm gives better color contrast enhancement results as compared to other existing contrast enhancement techniques.
Fig. 3.Visual Enhancement results of different algorithms for image11.jpg
Fig. 4.Visual Enhancement results of different algorithms for image22.jpg
Fig. 5.Visual Enhancement results of different algorithms for image99.jpg
Fig. 6.Visual Enhancement results of different algorithms for image33.jpg
Fig. 7.Visual Enhancement results of different algorithms for image44.jpg
Fig. 8.Visual Enhancement results of different algorithms for image66.jpg
5. Conclusion
In this paper, an automatic color contrast enhancement algorithm has been proposed for image enhancement purpose for various applications. The proposed method has been tested on different types of natural color images such as NASA images, Hyperspectral images and other types of natural images. The subjective enhancement performance of proposed ACCE algorithm has been evaluated and compared with other state-of-art contrast enhancement techniques for different natural color images in terms of colorfulness metric (CM) and Color enhancement factor (CEF). The simulation results demonstrated that the proposed ACCE algorithm provides better color enhancement quality parameters such as Colorfulness metric (CM) and Color enhancement factor (CEF) and also provided better visual enhancement results as compared to other state-of-art contrast enhancement techniques for different natural color images. Therefore, the proposed ACCE algorithm performs very effectively for the contrast enhancement of different natural color images. The proposed ACCE algorithm can also be used for many other images such as remote sensing images and even real life photographic pictures suffer from poor contrast as well as medium contrast problems during its acquisition.
References
- D. Jabson, Z. Rahman and G. A. Woodel, “A Multi- Scale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes,” IEEE Trans. Image Processing, vol. 6, pp. 965-976, July 1997. https://doi.org/10.1109/83.597272
- R. C. Gonzalez and R. E Woods, “Digital Image Processing,” Addison-Wesley Publishing Company, 2nd edition, 1992.
- J. A Stark, “Adaptive Contrast Enhancement using Generalization of Histogram Equalization,” IEEE Trans. on Image Processing, vol. 9, no. 5, pp. 889-906, 2000. https://doi.org/10.1109/83.841534
- V. Caselles, J. L. Lisani, J. M. Morel and G. Sapiro, “Shape Preserving Local Histogram Modification,” IEEE Trans. on Image Processing, vol. 8, no. 2, pp. 220-230, 1998.
- S. M. Pizer, E. P. Amburn, J. D. Austin, R. Cromartie, A. Geselowitz, T. Greer, B. T. H Romeny, J. B Zimmerman and K. Zuiderveld, “Adaptive Histogram Equalization and its Variations,” Computer Vision, Graphics and Image Processing, vol. 39, no. 3, pp.355-368, 1987. https://doi.org/10.1016/S0734-189X(87)80186-X
- D. J. Jobson, Z. Rahman, and G. A. Woodell, “A Multiscale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes”, IEEE Trans. on Image Processing, vol. 6,no.7, pp. 965-976, 1997. https://doi.org/10.1109/83.597272
- S. Aghagolzadeh and O. K. Ersoy, “Transform Image Enhancement,” Optical Engineering, vol. 31, pp. 614- 626, 1992. https://doi.org/10.1117/12.56095
- Y. T Kim, “Contrast Enhancement using Brightness Preserving Bi-histogram Equalization,” IEEE Trans. on Consumer Electronics, vol. 43, no. 1, pp. 1-8, 1997. https://doi.org/10.1109/30.580378
- S. D. Chen and A. R. Ramli, “Preserving Brightness in Histogram Equalization Based Contrast Enhancement Techniques,” Digital Signal Processing, vol. 14, no. 5, pp. 413-428, 2004. https://doi.org/10.1016/j.dsp.2004.04.001
- Z. Rahman, G. A. Woodell, and D. J. Jobson, “A Comparison of the Multiscale Retinex with Other Image Enhancement Techniques,” In Proceedings of the IS &T 50th Anniversary Conference, May 1997.
- D. J. Jobson, Z. Rahman, and G. A. Woodell, “A Multiscale Retinex for Bridging the Gap Between Color Images and the Human Observation of Scenes”, IEEE Trans. on Image Processing, vol. 6,no.7, pp. 965-976, 1997. https://doi.org/10.1109/83.597272
- D. J. Jobson, Z. Rahman and G. A. Woodell, “Properties and Performance of a Center / Surround Retinex,” IEEE Trans. on Image Processing, vol. 6, pp. 451-462, 1996.
- B. V. Funt, K. Barnard, M. Brockington and V. Cardei, “Luminance-Based Multi-scale Retinex”, In Proceedings of 9th Congress of the International Colour Association (AIC Color 97), Kyoto, Japan, 1997.
- K. Barnard and B. Funt, “Analysis and Improvement of Multi-Scale Retinex,” In Proceedings of the IS &T/ SID, Fifth Color Imaging Conference: Color Science, Systems and Applications, Scottsdale, Arizona, pp. 221-226, November 17-20, 1997.
- A. Bayaty, “Adaptive Techniques for Image Con-trast Estimation Based on Edge Detection,” Master Degree Thesis, Physics Dep., Al-Mustansiriya Univ., 2005.
- L. Tao, M. J. Seow and V. K. Asari, “Nonlinear Image Enhancement to Improve Face,” International Journal of Computational Intelligence Research, vol. 2, no. 4, pp. 327-336, 2006.
- J. A. Dalawy, “A Study of TV Images Quality for Channels Broadcast Television Satellite,” Master of Science in Physics, Physics Department, Al- Mustansiriya University, 2008.
- N. Hassan and N. Akamatsu, “A New Approach For Contrast Enhancement Using Sigmoid Function,” The International Arab Journal of Information Tech-nology, vol. 1, no. 2, pp. 221-225, 2004.
- D. Coltuc, P. Bolon and J. M. Chasserym, “Exact Histogram Specification,” IEEE Trans. on Image Processing, vol. 15, no. 5, pp. 1143-1151, 2006. https://doi.org/10.1109/TIP.2005.864170
- D. Sheet, H. Garud, A. Suveer, A. M. Mahadevappa and J. Chatterjee, “Brightness Preserving Dynamic Fuzzy Histogram Equalization,” IEEE Trans. on Consumer Electronics, vol. 56, no. 4, pp. 2475-2480, 2010. https://doi.org/10.1109/TCE.2010.5681130
- T. Celik and T. Tjahjad, “Contextual and Variational Contrast Enhancement,” IEEE Trans. on Image Processing, vol. 20, no. 12, pp. 3431-3441, 2011. https://doi.org/10.1109/TIP.2011.2157513
- H. Hu and G. Ni, “The Improved Algorithm for the Defect of the Retinex Image Enhancement”, In Proceedings of International Conference on Anti- Counterfeiting Security and Identification in Communication, pp. 257-260, July, 2010.
- Y. Terai, T. Goto, S. Hirano and M. Sakurai, “Color Image Contrast Enhancement by Retinex Model,” In Proceedings of IEEE 13th International Symposium on Consumer Electronics, pp. 392-393, May, 2009.
- L. He, L. Luo, and J. Shang, “An Image Enhancement Algorithm based on Retinex Theory,” Proceedings of First International Workshop on Education Technology and Computer Science, pp. 350-352, March, 2009.
- X. Ding, X. Wang and Q. Xiao, “Color Image Enhancement with a Human Visual System based Adaptive Filter,” In Proceedings of International Conference on Image Analysis and Signal Processing, April, 2010.
- J. Tang, E. Peli and S. Acton, “Image Enhancement using A Contrast Measure in the Compressed Domain,” IEEE Signal Processing Letter, vol. 10, no. 10, pp. 289-292, 2003. https://doi.org/10.1109/LSP.2003.817178
- H. H. Kareem, “Color image with Dim regions Enhancement Using Modified Histogram Equalization Algorithm,” Journal of Al-Nahrain University, vol. 15, no. 3, pp. 101-111, 2012. https://doi.org/10.22401/JNUS.15.3.15
- S. Lal, and M. Chandra, “Efficient Algorithm for Contrast Enhancement of Natural Images,” The International Arab Journal of Information Technology, vol. 11, no. 1, pp. 96-103, 2014.
- S. Lee, “An Efficient Content Based Image Enhancement in the Compressed Domain Using Retinex Theory,” IEEE Trans. Circuits Syst. Video Technol., vol. 17, no. 2, pp. 199-213, February 2007. https://doi.org/10.1109/TCSVT.2006.887078
- J. Mukherjee and S. K Mitra, “Enhancement of Color Images by Scaling the DCT Coefficients,” IEEE Trans. on Image Processing, vol. 17, no. 10, October 2008.
- R. Kimmel, M. Elad, D. Shaked, R. Keshet, and I. Sobel, “A Variational Framework for Retinex,” In Proceedings of SPIE Electronic Imaging, vol. 4672, 2002.
- M. C. Hanumantharaju, M. Ravishankar, D. R. Rameshbabu and S. Ramachandran,” Color Image Enhancement Using Multiscale Retinex with Modified Color Restoration Technique,” In Proceedings of International Conference on Emerging Applications of Information Technology (EAIT-2011) , pp. 93-97, 2011.
- Loza, D. Bull and A. Achim, “Automatic Contrast Enhancement of Low-Light Images Based on Local Statistics of Wavelet Coe cients,” In Proceedings of 17th IEEE International Conference on Image Processing, September 26-29, 2010.
- S. C. Huang, F. C. Cheng, and Y. S. Chiu,” Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution” IEEE Trans. on Image Processing, vol. 22, no. 3, pp.1032-104, March 2013. https://doi.org/10.1109/TIP.2012.2226047
- E. Provenzi and V. Caselles, “A Wavelet Perspective on Variational Perceptually-Inspired Color Enhancement”, International Journal of Computer Vision, vol. 106, no.2, pp. 153-171, 2014. https://doi.org/10.1007/s11263-013-0651-y
- Menon, K. Mehrotra, C. Mohan and S. Ranka, “Characterization of a class of Sigmoid Functions with applications to Neural Networks, Neural Networks, vol. 9, no. 5, pp. 819-8351, 1996. https://doi.org/10.1016/0893-6080(95)00107-7
- S. J. Sangwine and R. E. N. Horne, “The Color Image Processing, Hand Book,” international Thomson, 1998.
- S. Susstrunk and S. Winkler, “Color Image Quality on the Internet,” In Proceedings of IS & T/SPIE Electronic Imaging: Internet Imaging V, vol. 5304, pp. 118-131, 2004.
Cited by
- Contrast Limited Adaptive Histogram Equalization-Based Fusion in YIQ and HSI Color Spaces for Underwater Image Enhancement 2017, https://doi.org/10.1142/S0218001418540186
- Modified Visibility Restoration-Based Contrast Enhancement Algorithm for Colour Foggy Images 2018, https://doi.org/10.1080/02564602.2016.1276868