Fusion based approach for Underwater Image Enhancement

The implementation of computer vision in the field of underwater image is currently very popular. However, Indonesia's vision system for breakwater work has not yet been implemented. The work of the vision system is still manual using divers [1]. In addition, the application of computer vision in underwater images has a big obstacle because the resulting image in an underwater environment has poor color and contrast. This poor color and contrast are due to a density nearly 1000 times denser than air. This density directly affects the light transmission, which affects the resulting image, which has less color and contrast than the image taken through the air. So it takes image processing such as Image Enhancement and Image Color Restoration [2]. Another issue is building a real-time system. If the system that is built is not real-time, this makes the possibility of data reading errors being significant, and the movement of information is slow [3]. This research presents methods regarding image enhancement and color restoration built in the Graphical User Interface (GUI). The methods applied in this research are Histogram Equalization (HE), Contrast Limited Adaptive Histogram Equalization (CLAHE), and Multi-Scale Retinex with Color Restoration (MSRCR). Those methods are applied to the images produced by the two cameras and run on the single board processor and laptop for the comparison. The result by using 71 underwater images shows that for Underwater Color Image Quality Evaluation (UCIQE) value of the Histogram Equalization (HE) Method yields 20%, meanwhile for Contrast Limited Adaptive Histogram Equalization (CLAHE) yields 8%, and the Multi-Scale Retinex with Color Restoration (MSRCR) method yields 72%.

Due to the complex and varying underwater environment, the optical images obtained are low resolution and full of noise, which ultimately make it difficult to register and stich the optical images. To solve the above problems, we propose an improved image registration method based on MSRCR and SIFT. First, multi-scale retinex with color restoration (MSRCR) is applied to improve the underwater low-quality image, and the image contrast is improved by contrast limited adaptive histogram equalization (CLAHE). After that, the scale-invariant feature transform (SIFT) algorithm is adopted to extract feature points of the reference image and sensed image. Then coarsely match the feature points based on the K nearest neighbor (KNN)-based Ratio Matching algorithm, and the random sample consensus (RANSAC) is used to eliminate mismatched feature points and improve matching accuracy. Finally, the mosaic image is output after the transformation matrix is calculated. The experiment results show a better effect of underwater image registration and stitching, demonstrating that the algorithm can improve the accuracy of underwater image registration through image enhancement.

Enhancing aerial images plays an important role in many remote sensing applications; aerial images are often affected by dust, smoke and fog. In this paper, a new algorithm was proposed to improve aerial images. The proposed algorithm using Dark Channel Prior (DCP) to enhance the color compounds only in HSV space and a Multiscale Retinex (MSR) using to enhance the lightness component in the same space. To know the efficiency of enhancement aerial images, the no-reference quality measures as Natural Image Quality Evaluator (NIQE) and Wavelet Quality Evaluator (WQE) Have been calculated, which are used to see the quality of the proposed method in comparison with DCP, Histogram equalization (HE), Image Entropy and Information Fidelity (IEIF) and Multiscale Retinex with color restoration (MSRCR). Through the analysis of the results, it is found that the proposed method has succeeded in improving aerial images better than other methods.

The retinex is a human perception based image processing algorithm which provides color constancy and dynamic range compression. The multi scale retinex with color restoration (MSRCR) has shown itself to be a very versatile automatic image enhancement algorithm that simultaneously provides dynamic range compression, color constancy, and color rendition. But the MSRCR results suffer from lower global brightness and partial color distortion. In order to improve the MSRCR method, this paper presents a modified MSRCR algorithm to Landsat-5 image enhancement considering percent liner stretch and histogram adjustment. Finally, the effect of modified MSRCR method on Landsat-5 image enhancement is analyzed and the comparison with other color adjustment methods such as gamma correction and histogram equalization is reported in the experimental results.

Due to light being absorbed by water and scattered by suspended particles, color distortion, low image contrast, and detail loss are the common problems found in underwater images. We present an underwater image processing method, which based on an underwater imaging model, makes initial image restoration with the improved red channel prior combining transmission reduction, background light correction, and color compensation to acquire clearer underwater images, and then combines multiscale retinex (MSR) enhancement and hue saturation value to enhance image color contrast and saturation. Results indicate that, compared with the original images, the method proposed in this paper is capable of significantly enhancing image definition, saturation, contrast, and luminance. In comparison with dark channel prior, single-scale retinex (SSR), MSR, and multiscale retinex with color restoration (MSRCR), this method greatly improved the average gradient of images while keeping the information entropy of images unchanged. The average gradient calculated with the proposed method increased by 239%, 199%, 200%, and 220% for the three given images, respectively, compared with the other methods above.

The multi-scale retinex with color restoration (MSRCR) was developed as a general-purpose image enhancement algorithm that provides simultaneous dynamic range compression, local lightness/contrast enhancement, and good color rendition, and has been successfully used for a wide variety of imagery from diverse fields. While the MSRCR performs good enhancement in most images, the output image can sometimes be further visually optimized during our experiments. An improved MSRCR+Autolevels (AL) algorithm is presented, which can eliminate the impact of a small number of outliers in the histogram of the image and further improve the contrast of an image. New extension significantly improves the visual performance of the MSRCR algorithm. However, the MSRCR+AL containing a large number of complex calculations is computationally expensive, limiting real-time applications. In this paper, a parallel application of the MSRCR+AL algorithm on a graphics processing unit (GPU) is presented. For the various configurations in our test, the GPU-accelerated MSRCR+AL shows a scalable speedup as the resolution of an image increases. The up to 45× speedup (1,024 × 1,024) over the single-threaded CPU counterpart shows a promising direction of using the GPU-based MSRCR+AL in large-scale, time-critical applications. We also achieved 17 frames per second in video processing (1,280 × 720).

One of the crucial issue in image quality enhancement is the fidelity issue. There are three fidelity issues to must be studied. The 1st fidelity issue can be called that the information entropy of the enhanced image can not be increase. The 2nd fidelity issue can be called that the constituents of the enhanced image can not be increased. The 3rd fidelity issue can be called that the color relation of the enhanced image can not be changed. MSRCR will be used as an example of an image enhancement method based on the retinex series method. As an example, the three fidelity brought by multi-scale retinex with color restoration (MSRCR), which is one of series methods based on retinex, will be studied in this paper. The study will point out that the MSRCR will result in the three obvious distortions above mentioned.

Aiming at the matter of seed overlapping and adhesion within the actual quality detection of soybean, a soybean image segmentation based on multi-scale Retinex with color restoration (MSRCR) was proposed. Firstly, original images of soybean were obtained by the industrial camera. secondly, these images were enhanced by MSRCR. Thirdly, these images after MSRCR were segmented by Otsu. Finally, soybean seed images were extracted by mask and minimum bounding rectangle from soybean images after MSRCR. The image acquisition system was constructed and the algorithm was verified. The experiment showed that the segmentation accuracy of the proposed algorithm was 98.05%, which can meet the requirement of soybean image segmentation. Additionally, the proposed algorithm can also provide an image preprocessing method for agricultural seed classification in similar scenes.

Summary form only given. In the field of image contrast enhancement, the Retinex algorithm is the most frequently used one. MSRCR(Multi Scale Retinex with Color Restoration) and IMSR (Integrated Multi Scale Retinex) are the two most popular Retinex algorithms in the literature. In this talk, a new algorithm "FH-IMSR" is presented to solve the problems existing in the MSRCR and IMSR algorithms. These problems include distortion of grey out due to the individual treatment of RGB channel, color noise due to log function, and halo effect occurred by the use of the Gaussian filter. The original IMSR algorithm is based on a RGB color model. The separate treatment for each channel in RGB space brings a phenomenon to change the rate of RGB, which causes grey out problem in the restored image. To solve this problem, FH-IMSR proposed to transform RGB color model into HSV color model, and apply the Retinex treatment on the luminance channel V. To remove color noise occurred by the use of log function, the Hue differences in the original image and restored image are minimized. To reduce Halo-artifact, FH-IMSR proposed to use Fuzzy C-means Clustering algorithm to cluster image pixels into dark area, middle area, and bright area, and different strategies are proposed to deal with brightness restoration on the three types of areas. Experiments on a wide variety of images are conducted, and comparisons with MSRCR and IMSR algorithms are made. The results showed that the proposed FM-IMSR algorithm has better performance than MSRCT and IMSR algorithms.

In this paper, a Particle Swarm Optimization (PSO) method for tuning the parameters of multiscale retinex based color image enhancement is presented. The image enhancement using multiscale retinex scheme heavily depends on parameters such as Gaussian surround space constants, number of scales, gain and offset etc. Due to hard selection of these parameters, PSO has been used in order to investigate the optimal parameters for the best image enhancement. The PSO method of parameter tuning adopted for multiscale retinex with modified color restoration (MSRMCR) algorithm achieves very good quality of reconstructed images, far better than that possible with the other existing methods. The presented algorithm is compared with other promising enhancement schemes such as histogram equalization, NASA's multiscale retinex with color restoration (MSRCR), Improved MSRCR (IMSRCR), and Photoflair software. The quality of the enhanced image is validated iteratively using an efficient objective criterion which is based on entropy and edge information of an image. Finally, the quality of the reconstructed images obtained by the proposed method is evaluated using Wavelet Energy (WE) metric. The experimental results presented shows that color image enhanced by the proposed algorithm are clearer, vivid and efficient.

The underwater environment has high complexity, which naturally arises due to the absorption and scattering of light waves by water and other particles suspended in it. This results in underwater images with low contrast, blurriness, and unclear details, necessitating the use of image enhancement methods. The Retinex method aims to maintain color constancy, where the color of an object appears relatively the same even under different lighting conditions. Preliminary research indicates that the SSR and MSR methods still produce halo effects. Therefore, this study modifies and enhances the MSR method by adding color restoration to correct the color distortion caused by water. This research begins with test images of 5 x 5 dimensions. The image enhancement process is conducted using the proposed MSRCR method and then analyzed mathematically on digital images. Subsequently, it is applied to underwater images with different sigma (

The <i>Journal of Electronic Imaging</i> (JEI), copublished bimonthly with the Society for Imaging Science and Technology, publishes peer-reviewed papers that cover research and applications in all areas of electronic imaging science and technology.

Image enhancement is one of the key concerns pertaining to better quality image photography captured through modern digital cameras. Probability of digital images getting compromised through lightning and weather conditions remains high. Due to these environmental limitations, many a time loss of information from images is reported. Major role of image amplification is to bring out hidden details of an image from the sample. It provides multiple options for enhancing the visual quality of images. This paper addresses problem of early skin cancer detection using image enhancement techniques and presents a multi-scale retinex with color restoration (MSR-CR) technique for skin cancer detection. The actual skin portion suffering from cancer is identified by comparing enhanced image with available ground truth image. Experimental result shows significant improvement over previously available techniques.

In order to restore image color and enhance contrast of remote sensing image without suffering from color cast and insufficient detail enhancement, a novel improved multi-scale retinex with color restoration (MSRCR) image enhancement algorithm based on Gaussian filtering and guided filtering was proposed in this paper. Firstly, multi-scale Gaussian filtering functions were used to deal with the original image to obtain the rough illumination components. Secondly, accurate illumination components were acquired by using the guided filtering functions. Then, combining with four-direction Sobel edge detector, a self-adaptive weight selection nonlinear image enhancement was carried out. Finally, a series of evaluate metrics such as mean, MSE, PSNR, contrast and information entropy were used to assess the enhancement algorithm. The results showed that the proposed algorithm can suppress effectively noise interference, enhance the image quality and restore image color effectively.

Image fusion is a technique of combining two or more images so that the combined image is better enhanced than all these images. We propose that a fusion based approach on Multi Scale Retinex with Color Restoration(MSRCR) would give better image enhancement. Lower dynamic range of a camera as compared to human visual system causes images taken to be extremely dependent on illuminant conditions. MSRCR algorithm enhances images taken under a wide range of nonlinear illumination conditions to the level that a user would have perceived it in real time.