Comparative Study of Noise Removal and Image Enhancement Methods in Low Light Image
Capturing photos in low light conditions is a difficult situation for photographers to get optimal image results. Low light conditions can occur at night, in the forest or in a dark room. The image quality in low light conditions is not good because the objects in the picture are lack of light which makes some objects blur and hard to identify. Factors that affect low light conditions such as brightness, contrast and noise can cause poor image quality. Poor image quality can be improved by doing image enhancement and noise removal technique. Image enhancement is a way to improve image quality by using various methods. While noise removal is removing noise that can damage image quality.
Keywords— Image Enhancement, Noise Removal, Denoising, Low Light Image, Image Processing.
Digital images play an important role in the era of information and communication technology. Digital images make people easy to share information, but some problems usually occur to digital images like noise and lighting that can affect image quality. Noise removal and image enhancement technique are needed to improve image quality that affects image quality.
Image enhancement is one of the initial processes in image processing. Image enhancement is a process to improve the appearance of an image or to convert the image to a form better suited for analysis by a machine or human. Some of the processes in the image enhancement section include image brightness change, contrast enhancement, contrast stretching, image histogram conversion, image softening, sharpening, edge detection, histogram equalization, and geometric alteration.
Enhancement of images in low light environment is a very challenging problem in in various research case studies of improve image quality. Images that take in low-light environment usually have low visibility, unwanted noise, poor image sharpness, and various other issues. In the most recent decade, various techniques and methods have been proposed to improve the quality of low light images such as histogram-based methods , , , Retinex-based methods , , Logarithmic Image Processing methods , , ﬁltering-based methods , , and neural network-based methods , , , , . In this paper, we compare several methods and techniques to improve images with low light conditions.
Various techniques or methods used for image enhancement and noise removal in a low light image are given below
Pixel-wise inversion histograms of low-light images or HDR images is very similar to the histogram of hazy images. That can make de-hazing techniques can enhance low-light images. For low light image input (I), invert it to make hazy condition using :
where c is the color channel (RGB). is the intensity of a color channel of pixel x of the low light image input I. is the same intensity of inverted image R. Apply the haze removal algorithm to the inverted image using :
where A is the global atmospheric light. R(x) is the intensity of pixel x the camera catches. J(x) is the intensity of the original objects or scene. t(x) describes how much percent of the light emitted from the objects or scene reaches the camera. After applying the haze removal algorithm, invert again to obtain the enhanced image .
NPE propose an enhancement algorithm for non-uniform illumination images. In general, NPE makes the following three major contributions. First, a lightness-order-error (LOE) measure is proposed to access naturalness preservation objectively. Second, a bright-pass ﬁlter is proposed to decompose an image into reﬂectance and illumination, which, respectively, determine the details and the naturalness of the image. Third, NPE propose a bi-log transformation, which is utilized to map the illumination to make a balance between details and naturalness .
BIMEF propose a multi-exposure fusion framework inspired by the human visual system (HVS). There are two stages in this framework: Eye Exposure Adjustment and Eye Exposure Adjustment. The ﬁrst stage simulates the human eye to adjust the exposure, generating an multi-exposure image set. The second stage simulates the human brain to fuse the generated images into the ﬁnal enhanced result. Based on this framework, BIMEF propose a dual-exposure fusion method. First employ the illumination estimation techniques to build the weight matrix for image fusion. Then derives camera response model based on observation. Next, ﬁnd the optimal exposure for camera response model to generate the synthetic image that is well-exposed in the regions where the original image is under-exposed. Finally, obtain the enhanced results by fusing the input image with the synthetic image using the weight matrix .
SRIE propose a weighted variational model to estimate both the reﬂectance and the illumination from an observed image. SRIE goal is to develop an objective function that outputs a usable illumination and reﬂectance. To this end, SRIE observe that conventional methods use an objective function along the following lines:
In this objective function, the logarithmic illumination l uses a squared penalty to enforce spatial smoothness and the logarithmic reﬂectance r is encouraged to be piece-wise constant using L1-norm. The ﬁdelity term is the squared error term between the log-transformed image and its breakdown in illumination and reﬂectance .
LIME is built based on retinex teory and using the following (Retinex) model , , which explains the formation of a low-light image :
where L and R are the captured image and the desired recovery, respectively. Furthermore, T represents the illumination map, and the operator ◦ means element-wise multiplication. LIME assume that, for color images, three channels share the same illumination map and use T () to represent one-channel and threechannel illumination maps interchangeably. LIME propose to simultaneously preserve the over-all structure and smooth the textural details based on the initial illumination map with the following optimization problem :
where α is the coefﬁcient to balance the involved two terms and, and designate the Frobenious and norms, respectively. Further, W is the weight matrix, and ∇T is the ﬁrst order derivative ﬁlter. In this work, it only contains ∇hT (horizontal) and ∇vT (vertical). The ﬁrst term takes care of the ﬁdelity between the initial map and the reﬁned one T, while the second term considers the (structure-aware) smoothness  .
RetinexNet construct a deep-learning image decomposition based on Retinex model. The enhancement process is divided into three steps: decomposition, adjustment and reconstruction. In the decomposition step, a subnetwork Decom-Net decomposes the input image into reﬂectance and illumination. In the following adjustment step, an encoder-decoder based Enhance-Net brightens up the illumination. Multiscale concatenation is introduced to adjust the illumination from multi-scale perspectives. Noise on the reﬂectance is also removed at this step. Finally, RetinexNet reconstruct the adjusted illumination and reﬂectance to get the enhanced result .
LLNet proposes a deep autoencoder-based approach to identify signal features from lowlight images and adaptively brighten images without over-amplifying/saturating the lighter parts in images with a high dynamic range. LLNet propose a training data generation method by synthetically modifying images available on Internet databases to simulate low-light environments. Two types of deep architecture are explored : (i) for simultaneous learning of contrast-enhancement and denoising and (ii) sequential learning of contrast-enhancement and denoising using two modules .
LLCNN propose a CNN-based method to enhance low-light images. LLCNN learns to adaptively enhance image contrast and increase image brightness. In LLCNN, a special module is designed to help training and improve the performance. The architecture of LLCNN is described as follows: one convolutional layer is used to do pre-processing to produce uniform input, and another convolutional layer is used to generate enhanced image, several special-designed convolutional modules are placed between those two layers. The network takes low-light images as input and do processing to make the output image appear to be captured in normal light conditions. All input images are generated using nonlinear method to simulate low light condition .
This method proposed fully convolutional neural network, namely the multi-branch low-light enhancement network (MBLLEN). The MBLLEN consists of three types of modules, i.e., the feature extraction module (FEM), the enhancement module (EM) and the fusion module (FM). The idea is to learn to 1) extract rich features up to different levels via FEM, 2) enhance the multi-level features respectively via EM and 3) obtain the ﬁnal output by multi-branch fusion via FM .
Chen et al. introduce See-in-the-Dark (SID) dataset of raw short-exposure low-light images, with corresponding long-exposure reference images. Using the presented dataset, Chen et al. develop a pipeline for processing low-light images, based on end-to-end training of a fully convolutional network. The network operates directly on raw sensor data and replaces much of the traditional image processing pipeline, which tends to perform poorly on such data. Chen et al. use BM3D  as the reference denoising algorithm .
The method is simple and fast enhancement algorithm
The quality of image and brightness is still not good
Preserves the naturalness and increase brightness
Image sharpness is lacking and there is still noise
Slight image distortion and less noise
Image brightness still lacking
Image clarity is more satisfying
There is still noise and slow computing time
Brightness and object clarity in the image is better
There is still noise and image sharpness still lacking
High-quality restored result with reduce halo effect and color distortion
Image contrast is bad and slow computing time
Less noise and better brightness
Cannot process the entire high resolution image due to its MLP structure
Less noise and good image brightness
High image distortion and less sharpness
Less noise and better image clarity
High image distortion and less sharpness
Chen et al.
Image clarity with good brightness and sharpness also less noise
Slow computing time
Improving the quality of low light images has several methods. Each method has advantages and disadvantages. A good method is one that can enhance images by increasing brightness, sharpness, clarity and minimizing distortion also eliminating existing noise. Based on this research, the best technique or method for enhancement low-light images is Chen et al. where this method can increase the brightness and sharpness of low light images to be of good quality.
Introduction What is the speed of light and what affects? This question has been asked for hundreds of years and the answer is simple. The speed of light is approximately 299,792,458 m/s (Las Cumbres Observatory, 2019). This answers the first part of the question, but what about the second part? What affects the speed of light? The purpose of this experiment is going to be answering that question “What affects the speed of light?”. And in particular, does the density...
Many people in this world really underestimate how physics contributes to our daily lives whether be walking, talking, or any other action. Many equations, graphs, and a little bit of math help us understand what goes on behind the curtain. Physics also have shared relations with science and combining those physics to other types of studies. To understand physics, we need to discuss the laws of motion which are called the Newton’s Laws of Motion, there are only three. According...
1. Introduction As a fundamental constant, the exact value of the speed of light has been disputed for centuries. The measurement of the speed of light brought arise to new areas of Physics such as Einstein’s Theory of Relativity. This Theory of Relativity was based entirely on the relativistic effects caused by objects moving near the speed of light. This brought arise to an exclusively new area of Physics, furthermore it is no wonder why the velocity of light in...
Abstract – Active street lighting has emerged as an essential factor in strategies for a resource-efficient economy and realization of sustainable growth. In the outdoor area, lights represent approximately 40 % of the total energy consumption at night and have much energy saving potential. If passers-by or vehicles, summarized as traffic elements, are not located near street lamps, it is not energy-efficient to turn them on. The idea is to activate street lights only when they will be used to...
Human beings have been trying to understand how light works since the time of the Ancient Greeks. In roughly 300 BC Euclid studied the properties of light, he thought light travelled in straight lines and described the laws of reflection. In 1690 Sir Isaac Newton came out with the corpuscular theory of light, he believed that light was shot out of a source in small particles. Also, in the 17th century the Dutch astronomer Huygens suggested a wave theory of...
Albert Einstein was born March 14, 1879, in Germany and was a physicist who developed the special and general theories of relativity, considered to be his most famous piece of work. His research spanned from quantum mechanics to theories about gravity and motion. After publishing some papers that changed how the world knew space, time and gravity, he toured the world giving speeches about his discoveries. Since a very young age, Einstein was extremely interested in science and was influenced...
Blue light is a spectrum of light that can be seen by humans’ eyes. Blue light produces a high amount of energy due to its short wavelength of 400-450 nm. Phones, computers and other electronic products with screen emit blue light and ever since phones became mainstream more people have started using their devices longer with many people having the habit of checking their phones at night. This may seem like a harmless habit but this could be harmful to...
Abstract: Advance illumination instruments have changed the scenario in distribution and intensity of lighting systems in this world. Development from fluorescent to white LED (light emitting diode) opens the door of illumination, pest control application and eco-friendly lighting. Color sensitivity in UV spectrum plays crucial role in navigation; meet selection, excitation in terrestrial invertebrate animals. This review shows the importance of each wavelength while selecting any lighting system for environmental applications. All major scientific studies are scanned as per the...
Abstract The main aim of the project is to design a circuit which would allow the detection of light by using a photodiode and to critically assess in details how a light sensing circuit using a photodiode works to obtain a desired output. This is achieved by using a transistor Darlington pair, four resistors (2*330, 1k, 4.7k), one LED and a photodiode. In all processes of design all simulations, breadboard design and printed circuit board yielded the results that were...
01 / 09
Fair Use Policy
EduBirdie considers academic integrity to be the essential part of the learning process and does not support any violation of the academic standards. Should you have any questions regarding our Fair Use Policy or become aware of any violations, please do not hesitate to contact us via email@example.com.
We are here 24/7 to write your paper in as fast as 3 hours.