dengyueyun666 / image-contrast-enhancement

C++ implementation of several image contrast enhancement techniques.

Image-Contrast-Enhancement

C++ implementation of several image contrast enhancement techniques.

Techniques

• AINDANE
  • Adaptive and integrated neighborhood-dependent approach for nonlinear enhancement of color images (2005), Tao et al.
  • Accepted input image : Color(√) Grayscale(×)
  • Only OpenCV3 is needed.
• WTHE
  • Fast image/video contrast enhancement based on weighted thresholded histogram equalization (2007), Wang et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• GCEHistMod
  • A histogram modification framework and its application for image contrast enhancement (TIP 2009), Arici et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• LDR
  • Contrast Enhancement based on Layered Difference Representation of 2D Histograms (TIP 2013), Lee et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• AGCWD
  • Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution (TIP 2013), Huang et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• AGCIE
  • An adaptive gamma correction for image enhancement (2016), Rahman et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• IAGCWD
  • Contrast enhancement of brightness-distorted images by improved adaptive gamma correction (2017), Cao et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• Ying_2017_CAIP
  • A New Image Contrast Enhancement Algorithm Using Exposure Fusion Framework (CAIP 2017), Ying et al.
  • Accepted input image : Color(√) Grayscale(√)
  • All requirements are needed.
• CEusingLuminanceAdaptation
  • Retinex-based perceptual contrast enhancement in images using luminance adaptation (2018), Fu et al.
  • Accepted input image : Color(√) Grayscale(×)
  • Only OpenCV3 is needed.
• adaptiveImageEnhancement
  • Adaptive image enhancement method for correcting low-illumination images (2019), Wang et al.
  • Accepted input image : Color(√) Grayscale(×)
  • Only OpenCV3 is needed.
• JHE
  • A novel joint histogram equalization based image contrast enhancement (2019), Agrawal et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.
• SEF
  • An Extended Exposure Fusion and its Application to Single Image Contrast Enhancement (WACV 2020), Hessel et al.
  • Accepted input image : Color(√) Grayscale(√)
  • Only OpenCV3 is needed.

Requirements

• Ubuntu-16.04
• Cmake
• OpenCV-3.4.6+
• Dlib-19.18+
• SuperLU-5.2.1+
• Armadillo-9.800.3+
  • Before install Armadillo, SuperLU 5 must be installed.

Usage

cd Image-Contrast-Enhancement
cmake .
make
./main <input_image>

Citations

@article{tao2005adaptive,
  title={Adaptive and integrated neighborhood-dependent approach for nonlinear enhancement of color images},
  author={Tao, Li and Asari, Vijayan K},
  journal={Journal of Electronic Imaging},
  volume={14},
  number={4},
  pages={043006},
  year={2005},
  publisher={International Society for Optics and Photonics}
}

@article{wang2007fast,
  title={Fast image/video contrast enhancement based on weighted thresholded histogram equalization},
  author={Wang, Qing and Ward, Rabab K},
  journal={IEEE transactions on Consumer Electronics},
  volume={53},
  number={2},
  pages={757--764},
  year={2007},
  publisher={IEEE}
}

@article{arici2009histogram,
  title={A histogram modification framework and its application for image contrast enhancement},
  author={Arici, Tarik and Dikbas, Salih and Altunbasak, Yucel},
  journal={IEEE Transactions on image processing},
  volume={18},
  number={9},
  pages={1921--1935},
  year={2009},
  publisher={IEEE}
}

@article{lee2013contrast,
  title={Contrast enhancement based on layered difference representation of 2D histograms},
  author={Lee, Chulwoo and Lee, Chul and Kim, Chang-Su},
  journal={IEEE transactions on image processing},
  volume={22},
  number={12},
  pages={5372--5384},
  year={2013},
  publisher={IEEE}
}

@article{huang2013efficient,
  title={Efficient Contrast Enhancement Using Adaptive Gamma Correction With Weighting Distribution},
  author={Huang, Shihchia and Cheng, Fanchieh and Chiu, Yisheng},
  journal={IEEE Transactions on Image Processing},
  volume={22},
  number={3},
  pages={1032--1041},
  year={2013}
}

@article{rahman2016an,
  title={An adaptive gamma correction for image enhancement},
  author={Rahman, Shanto and Rahman, Mostafijur and Abdullahalwadud, M and Alquaderi, Golam Dastegir and Shoyaib, Mohammad},
  journal={Eurasip Journal on Image and Video Processing},
  volume={2016},
  number={1},
  pages={35},
  year={2016}
}

@article{cao2017contrast,
  title={Contrast enhancement of brightness-distorted images by improved adaptive gamma correction},
  author={Cao, Gang and Huang, Lihui and Tian, Huawei and Huang, Xianglin and Wang, Yongbin and Zhi, Ruicong},
  journal={Computers & Electrical Engineering},
  volume={66},
  pages={569--582},
  year={2017}
}

@inproceedings{ying2017new,
  title={A New Image Contrast Enhancement Algorithm Using Exposure Fusion Framework},
  author={Ying, Zhenqiang and Li, Ge and Ren, Yurui and Wang, Ronggang and Wang, Wenmin},
  booktitle={International Conference on Computer Analysis of Images and Patterns},
  pages={36--46},
  year={2017},
  organization={Springer}
}

@article{fu2018retinex,
  title={Retinex-based perceptual contrast enhancement in images using luminance adaptation},
  author={Fu, Qingtao and Jung, Cheolkon and Xu, Kaiqiang},
  journal={IEEE Access},
  volume={6},
  pages={61277--61286},
  year={2018},
  publisher={IEEE}
}

@article{wang2019adaptive,
  title={Adaptive image enhancement method for correcting low-illumination images},
  author={Wang, Wencheng and Chen, Zhenxue and Yuan, Xiaohui and Wu, Xiaojin},
  journal={Information Sciences},
  volume={496},
  pages={25--41},
  year={2019},
  publisher={Elsevier}
}

@article{agrawal2019novel,
  title={A novel joint histogram equalization based image contrast enhancement},
  author={Agrawal, Sanjay and Panda, Rutuparna and Mishro, PK and Abraham, Ajith},
  journal={Journal of King Saud University-Computer and Information Sciences},
  year={2019},
  publisher={Elsevier}
}

@inproceedings{hessel2020extended,
  title={An extended exposure fusion and its application to single image contrast enhancement},
  author={Hessel, Charles and Morel, Jean-Michel},
  booktitle={The IEEE Winter Conference on Applications of Computer Vision},
  pages={137--146},
  year={2020}
}

License

Copyright © 2022 dengyueyun666

This project is under the MIT License. See the LICENSE file for the full license text.

image-contrast-enhancement's Issues

Does SEF also work for multiple images?

Hi,

awesome repository - I'm actually trying to port the https://github.com/chlsl/extended-exposure-fusion-ipol implementation to OpenCV and just found your implementation of the single file variant. Do you think it's doable to make your version accept one or more (bracketed) images ?

Image-Contrast-Enhancement/src/SEF.cpp

Line 160 in cd2b1eb

void SEF(const cv::Mat & src, cv::Mat & dst, double alpha, double beta, double lambda)

This would be amazing to incorporate the EEF version into OpenCV as it addresses some Mertens Merge shortcomings.

Licensing of this repo

Hi,

Could you specify which license this repo is under?

I would like to compare some of my own image enhancement work against other algorithms and your library is a convenient repo for this. My work would fall under commercial use, although I would only use your code for image comparisons - I would not modify/expand on your code.

armadillo version

which armadillo version should be work? I found no 'spdiags' function in armadillo-10.1.2

感觉挺不错的总结

感觉挺不错的总结

python implementation do not work

opencv-python==3.4.2.17
numpy==1.19.1

function output image is black image

def CELA(img):
HSV = cv2.cvtColor(img, cv2.COLOR_BGR2HSV_FULL)
HSV_channels = cv2.split(HSV)
V = HSV_channels[2]

ksize = 5
gauker1 = cv2.getGaussianKernel(ksize, 15)
gauker2 = cv2.getGaussianKernel(ksize, 80)
gauker3 = cv2.getGaussianKernel(ksize, 250)

gauV1 = cv2.filter2D(V, cv2.CV_8U, gauker1, anchor=(-1, -1), delta=0, borderType=cv2.BORDER_CONSTANT)
gauV2 = cv2.filter2D(V, cv2.CV_8U, gauker2, anchor=(-1, -1), delta=0, borderType=cv2.BORDER_CONSTANT)
gauV3 = cv2.filter2D(V, cv2.CV_8U, gauker3, anchor=(-1, -1), delta=0, borderType=cv2.BORDER_CONSTANT)

lut = np.zeros(256, np.uint8)
for i in range(256):
    lut[i] = 17.0 * (1. - math.sqrt(i/127.)) + 3. if i <= 127 else 3. / 128. *(i - 127.) + 3.
    lut[i] = (-lut[i] + 20.)/17.

beta1 = cv2.LUT(gauV1, lut)
beta2 = cv2.LUT(gauV2, lut)
beta3 = cv2.LUT(gauV3, lut)

gauV1 = np.float64(gauV1/255.)
gauV2 = np.float64(gauV2/255.)
gauV3 = np.float64(gauV3/255.)
V = np.float64(V/255.)

V = cv2.log(V)
gauV1 = cv2.log(gauV1)
gauV2 = cv2.log(gauV2)
gauV3 = cv2.log(gauV3)

r = (3. * V - beta1 * gauV1 - beta2 * gauV2 - beta3 * gauV3) / 3.0

R = cv2.exp(r)
R_min, R_max = np.min(R), np.max(R)
V_w = (R - R_min)/ (R_max - R_min)
V_w = np.uint8(V_w*255)

histsize = 256
hist = cv2.calcHist([V_w], [0], None, [histsize], [0, 255], accumulate=False)

pdf = hist / img.size
pdf_min, pdf_max = np.min(pdf), np.max(pdf)
for i in range(histsize):
    pdf[i] = pdf_max * (pdf[i] - pdf_min) / (pdf_max - pdf_min)
    
cdf = [0] * 256
accum = 0
for i in range(255):
    accum += pdf[i]
    cdf[i] = accum
cdf[255] = 1. - accum

V_w_max = np.max(V_w)
for i in range(255):
    lut[i] = V_w_max * math.pow((i *1./V_w_max), 1. - cdf[i])

V_out = cv2.LUT(V_w, lut)
V_out = np.uint8(V_out)

HSV_channels[2] = V_out
HSV = cv2.merge(HSV_channels)
return cv2.cvtColor(HSV, cv2.COLOR_HSV2BGR_FULL)