scholarly journals Low-Light Image Enhancement Based on Quasi-Symmetric Correction Functions by Fusion

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1561
Author(s):  
Changli Li ◽  
Shiqiang Tang ◽  
Jingwen Yan ◽  
Teng Zhou
Keyword(s):  
Image Enhancement ◽  
State Of The Art ◽  
Histogram Equalization ◽  
Local Contrast ◽  
Low Light ◽  
Adaptive Histogram Equalization ◽  
Light Image ◽  
Image Capturing ◽  
Enhancement Method ◽  
Image Details

Sometimes it is very difficult to obtain high-quality images because of the limitations of image-capturing devices and the environment. Gamma correction (GC) is widely used for image enhancement. However, traditional GC perhaps cannot preserve image details and may even reduce local contrast within high-illuminance regions. Therefore, we first define two couples of quasi-symmetric correction functions (QCFs) to solve these problems. Moreover, we propose a novel low-light image enhancement method based on proposed QCFs by fusion, which combines a globally-enhanced image by QCFs and a locally-enhanced image by contrast-limited adaptive histogram equalization (CLAHE). A large number of experimental results showed that our method could significantly enhance the detail and improve the contrast of low-light images. Our method also has a better performance than other state-of-the-art methods in both subjective and objective assessments.

Perbandingan Performa Histogram Equalization untuk Peningkatan Kualitas Gambar Minim Cahaya pada Android

2020 ◽  
Vol 12 (2) ◽  
pp. 80-88
Author(s):  
Claudia Kenyta ◽  
Daniel Martomanggolo Wonohadidjojo
Keyword(s):  
Image Enhancement ◽  
Light Condition ◽  
Histogram Equalization ◽  
Low Light ◽  
Adaptive Histogram Equalization ◽  
Enhancement Method ◽  
Better Than

When the photos are taken in low light condition, the quality of the results will not meet their expectation. Image Enhancement method can be used to enhance the quality of the photos taken in low light condition. One of the algorithms used is called Histogram Equalization (HE), that works using Histogram basis. The superiority of HE algorithm in enhancing the quality of the photos taken in low light condition is the simplicity of the algorithm itself and it does not need a high specification device for the algorithm to run. One variant of HE algorithm is Contrast Limited Adaptive Histogram Equalization (CLAHE). This paper shows the implementation of HE algorithm and its performance in enhancing the quality of photos taken in low light condition on Android based application and the comparison with CLAHE algorithm. The results show that, HE algorithm is better than CLAHE algorithm.

Perceptual Quality Assessment of Low-light Image Enhancement

2021 ◽  
Vol 17 (4) ◽  
pp. 1-24
Author(s):  
Guangtao Zhai ◽  
Wei Sun ◽  
Xiongkuo Min ◽  
Jiantao Zhou
Keyword(s):  
Image Quality ◽  
Quality Assessment ◽  
Image Enhancement ◽  
Dynamic Range ◽  
State Of The Art ◽  
Perceptual Quality ◽  
Low Light ◽  
Light Image ◽  
Light Enhancement

Low-light image enhancement algorithms (LIEA) can light up images captured in dark or back-lighting conditions. However, LIEA may introduce various distortions such as structure damage, color shift, and noise into the enhanced images. Despite various LIEAs proposed in the literature, few efforts have been made to study the quality evaluation of low-light enhancement. In this article, we make one of the first attempts to investigate the quality assessment problem of low-light image enhancement. To facilitate the study of objective image quality assessment (IQA), we first build a large-scale low-light image enhancement quality (LIEQ) database. The LIEQ database includes 1,000 light-enhanced images, which are generated from 100 low-light images using 10 LIEAs. Rather than evaluating the quality of light-enhanced images directly, which is more difficult, we propose to use the multi-exposure fused (MEF) image and stack-based high dynamic range (HDR) image as a reference and evaluate the quality of low-light enhancement following a full-reference (FR) quality assessment routine. We observe that distortions introduced in low-light enhancement are significantly different from distortions considered in traditional image IQA databases that are well-studied, and the current state-of-the-art FR IQA models are also not suitable for evaluating their quality. Therefore, we propose a new FR low-light image enhancement quality assessment (LIEQA) index by evaluating the image quality from four aspects: luminance enhancement, color rendition, noise evaluation, and structure preserving, which have captured the most key aspects of low-light enhancement. Experimental results on the LIEQ database show that the proposed LIEQA index outperforms the state-of-the-art FR IQA models. LIEQA can act as an evaluator for various low-light enhancement algorithms and systems. To the best of our knowledge, this article is the first of its kind comprehensive low-light image enhancement quality assessment study.

An Image Enhancement Method Based on the Coal Mine Monitoring System

2012 ◽  
Vol 468-471 ◽  
pp. 204-207
Author(s):  
Zhen Chong Wang ◽  
Yan Qin Zhao
Keyword(s):  
Image Enhancement ◽  
Coal Mine ◽  
Impulse Noise ◽  
Histogram Equalization ◽  
Video Monitor ◽  
Low Contrast ◽  
Adaptive Histogram Equalization ◽  
Enhancement Method ◽  
Special Environment

For the low illumination and low contrast in the coal mine, images captured from the video monitor system sometimes are not so clear to help the related personal monitoring the production and safety of the mine. According to the special environment of coal mine, an image enhancement method was presented. In this method the impulse noise which is the mainly noise in the coal mine was first reduced with median filtering, then the low contrast and illumination was greatly improved with the improved adaptive histogram equalization. Experiments show that this method can improve the quality of images underground effectively.

scholarly journals An image enhancement method based on gabor filtering in wavelet domain and adaptive histogram equalization

2021 ◽  
Vol 21 (1) ◽  
pp. 146
Author(s):  
Jeevan K M ◽  
Anne Gowda A B ◽  
Padmaja Vijay Kumar
Keyword(s):  
Image Enhancement ◽  
Histogram Equalization ◽  
Median Filtering ◽  
Wavelet Domain ◽  
Gabor Filtering ◽  
Low Contrast ◽  
Enhancement Technique ◽  
Adaptive Histogram Equalization ◽  
Enhancement Method ◽  
Two Parameters

<p><span>The images are not always good enough to convey the proper information. The image may be very bright or very dark sometime or it may be low contrast or high contrast. Because of these reasons image enhancement plays important role in digital image processing. In this paper we proposed an image enhancement technique in which Gabor and median filtering is performed in wavelet domain and Adaptive Histogram Equalization is performed in spatial domain. Brightness and contrast are the two parameters used for analyzing the performance of the proposed method</span></p>

scholarly journals A Comparative Study of Semantic Segmentation Models for Identification of Grape with Different Varieties

Agriculture ◽  
2021 ◽  
Vol 11 (10) ◽  
pp. 997
Author(s):  
Yun Peng ◽  
Aichen Wang ◽  
Jizhan Liu ◽  
Muhammad Faheem
Keyword(s):  
Image Enhancement ◽  
Precision Agriculture ◽  
State Of The Art ◽  
Semantic Segmentation ◽  
Histogram Equalization ◽  
Performance Difference ◽  
Convolutional Network ◽  
Enhancement Method ◽  
The Impact ◽  
Segmentation Models

Accurate fruit segmentation in images is the prerequisite and key step for precision agriculture. In this article, aiming at the segmentation of grape cluster with different varieties, 3 state-of-the-art semantic segmentation networks, i.e., Fully Convolutional Network (FCN), U-Net, and DeepLabv3+ applied on six different datasets were studied. We investigated: (1) the segmentation performance difference of the 3 studied networks; (2) The impact of different input representations on segmentation performance; (3) The effect of image enhancement method to improve the poor illumination of images and further improve the segmentation performance; (4) The impact of the distance between grape clusters and camera on segmentation performance. The experiment results show that compared with FCN and U-Net the DeepLabv3+ combined with transfer learning is more suitable for the task with an intersection over union (IoU) of 84.26%. Five different input representations, namely RGB, HSV, L*a*b, HHH, and YCrCb obtained different IoU, ranging from 81.5% to 88.44%. Among them, the L*a*b got the highest IoU. Besides, the adopted Histogram Equalization (HE) image enhancement method could improve the model’s robustness against poor illumination conditions. Through the HE preprocessing, the IoU of the enhanced dataset increased by 3.88%, from 84.26% to 88.14%. The distance between the target and camera also affects the segmentation performance, no matter in which dataset, the closer the distance, the better the segmentation performance was. In a word, the conclusion of this research provides some meaningful suggestions for the study of grape or other fruit segmentation.

Low light image enhancement method based on guided filtering

2021 ◽  
Author(s):  
Bin Yao ◽  
Zhen Han ◽  
Shiying Kang ◽  
Xuanying Wei ◽  
Lifeng He ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Low Light ◽  
Light Image ◽  
Guided Filtering ◽  
Enhancement Method

Research on the Image Enhancement Algorithm of Pointer Instrument under Inadequate Light

2014 ◽  
Vol 615 ◽  
pp. 248-254 ◽  
Author(s):  
Lu Zhang ◽  
Jin Lin Zhang ◽  
Ting Rui ◽  
Yue Wang ◽  
Yan Nan Wang
Keyword(s):  
Image Processing ◽  
Image Enhancement ◽  
Traditional Method ◽  
Histogram Equalization ◽  
Light Conditions ◽  
Low Light ◽  
Homomorphic Filtering ◽  
The Impact ◽  
Image Details ◽  
Enhancement Algorithm

For image processing, the recognition of pointer instrument’s reading by computer vision highly depends on brightness. An image enhancement algorithm based on homomorphic filtering and histogram equalization is proposed in order to reduce the impact of low-light conditions on images of pointer instrument. It combines the methods of spatial with frequency domain, which enhances the image contrast and highlights the image details as well. Compared with the traditional method, the experiments show that the proposed method can eliminate the effect of inadequate light and also perform well in enhancing the image quality.

scholarly journals A low‐light image enhancement method based on bright channel prior and maximum colour channel

2021 ◽  
Author(s):  
Ghada Sandoub ◽  
Randa Atta ◽  
Hesham Arafat Ali ◽  
Rabab Farouk Abdel‐Kader
Keyword(s):  
Image Enhancement ◽  
Low Light ◽  
Light Image ◽  
Colour Channel ◽  
Enhancement Method ◽  
Bright Channel Prior

scholarly journals Cotton-wool spots, red-lesions and hard-exudates distinction using CNN enhancement and transfer learning

2021 ◽  
Vol 23 (2) ◽  
pp. 1170
Author(s):  
Tian-Swee Tan ◽  
M. A. As'ari ◽  
Wan Hazabbah Wan Hitam ◽  
Qi Zhe Ngoo ◽  
Matthias Tiong Foh thye ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Retinal Disease ◽  
Histogram Equalization ◽  
Disease Diagnosis ◽  
Training Dataset ◽  
Cotton Wool ◽  
Hard Exudates ◽  
Adaptive Histogram Equalization ◽  
Cotton Wool Spots ◽  
Enhancement Method

<div>The automatic retinal disease diagnosis by artificial intelligent is an interesting and challenging topic in the medical field. It requires an appropriate image enhancement technique and a sufficient training dataset for the specific retina conditions. The aim of this study was to design an automatic diagnosis convolutional neural network (CNN) model which does not require a large training dataset to specifically identify diabetic retinopathy symptoms, which are cotton wool, exudates spots and red lesionin colour fundus pictures. A novel framework comprised image enhancement method by using upgraded contrast limited adaptive histogram equalization (UCLAHE) filter and transferred pre-trained networks was developed to classify the retinal diseases regarding to the symptoms. The performance of the proposed framework was evaluated based on accuracy, sensitivity and specificity metrics. The collected results have proven the robustness of the proposed framework in offering good accuracy in retina diseases diagnosis. </div>

Sign in / Sign up

Export Citation Format

Share Document