Multi-scale Retinex Image Enhancement Research Articles

A novel coal-gangue recognition method in underground coal mine based on image processing

ABSTRACT This study proposes a coal-gangue recognition method based on Retinex and extreme learning machine. The traditional Retinex has many limitations, including halo artifacts, excessive enhancement, and noise amplification in dark areas. To handle these, first, a modified multi-scale Retinex image enhancement algorithm based on hue, saturation, value color space, and bidimensional empirical mode decomposition named modified multi-scale Retinex algorithm with color restoration (MMSRCR) is proposed herein. On-site images are used to verify the effectiveness of the MMSRCR. Second, a preliminary segmentation method for coal-gangue images based on the optimal entropy threshold optimized by the improved quantum genetic algorithm is designed. The proposed segmentation method performs excellent stability compared with other traditional methods. Third, the adhesion part of the ore is further segmented based on the morphology opening operation and watershed algorithm. Then, the feature space of each enclosed area is extracted using the chain code and line segment tables. The improved extreme learning machine completes the classification of these areas, and the coal-gangue visual ratio recognition method is proposed. Finally, an experimental platform for visual ratio recognition is built to verify the proposed method. The experimental results show that the proposed method can accurately identify the visual ratio of coal-gangue.

Mask Wearing Detection Based on Inceptionv4 and Multi-Scale Retinex Image Enhancement Algorithm

The novel coronavirus is a contagious virus with a high mortality rate, and the international health emergency due to COVID-19 has never stopped since the outbreak, due to this situation, wearing masks has become a basic recommended public epidemic prevention approach for many countries. In the current shortage of medical human resources, we urgently need a non-artificial mask-wearing detection method. In this paper, the multi-scale Retinex algorithm is involved as the preprocessing step of the input image. The mask-wearing detection is based on the InceptionV4 convolutional neural network model. During the experiment, we compared and verified the superiority of the Inception part of the InceptionV4 model compared with the Stem structure of the GoogLenet model, and from LFW (Labeled Faces in the Wild), RMFD (Real-World-Masked-Face-Dataset) more than 10,000 samples were selected from the public datasets for model training. Finally, the precise rate reaches 97.3 %.

Forest 3D Reconstruction and Individual Tree Parameter Extraction Combining Close-Range Photo Enhancement and Feature Matching

An efficient and accurate forest sample plot survey is of great significance to understand the current status of forest resources at the stand or regional scale and the basis of scientific forest management. Close-range photogrammetry (CRP) technology can easily and quickly collect sequence images with high overlapping to reconstruct the 3D model of forest scenes and extract the individual tree parameters automatically and, therefore, can greatly improve the efficiency of forest investigation and has great application potential in forestry visualization management. However, it has some issues in practical forestry applications. First, the imaging quality is affected by the illumination in the forest, resulting in difficulty in feature matching and low accuracy of parameter extraction. Second, the efficiency of 3D forest model reconstruction is limited under complex understory vegetation or the topographic situation in the forest. In addition, the density of point clouds by dense matching directly affects the accuracy of individual tree parameter extraction. This research collected the sequence images of sample plots of four tree species by smartphones in Gaofeng Forest Farm in Guangxi and Wangyedian Forest Farm in Mongolia to analyze the effects of image enhancement, feature detection and dense point cloud algorithms on the efficiency of 3D forest reconstruction and accuracy of individual tree parameter extraction, then proposed a strategy of 3D reconstruction and parameter extraction suitable for different forest scenes. First, we compared the image enhancement effects of median–Gaussian (MG) filtering, single-scale retinex (SSR) and multi-scale retinex (MSR) filtering algorithms. Then, an improved algorithm combining Harris corner detection with speeded-up robust features (SURF) feature detection (Harris+SURF) is proposed, and the feature matching effect is compared with that of a scale invariant feature transform (SIFT) operator. Third, according to the morphological characteristics of the trees in the sequence images, we used the iterative interpolation algorithm of a planar triangulation network based on geometric constraints (GC-based IIPTN) to increase the density of point clouds and reconstruct the 3D forest model, and then extract the position and DBH of the individual trees. The results show that MSR image enhancement can significantly increase the number of matched point pairs. The improved Harris+SURF method can reduce the reconstruction time of the 3D forest model, and the GC-based IIPTN algorithm can improve the accuracy of individual tree parameter extraction. The extracted position of the individual tree is the same as the measured position with the bias within 0.2 m. The accuracy of extracted DBH of Eucalyptus grandis, Taxus chinensis, Larix gmelinii and Pinus tabuliformis is 94%, 95%, 96% and 90%, respectively, which proves that the proposed 3D model reconstruction method based on image enhancement has great potential for tree position and DBH extraction, and also provides effective support for forest resource investigation and visualization management in the future.

Research on Pedestrian Detection Technology Based on MSR and Faster R-CNN

In order to avoid the problem of poor illumination characteristics and inaccurate positioning accuracy, this paper proposed a pedestrian detection algorithm suitable for low-light environments. The algorithm first applied the multi-scale Retinex image enhancement algorithm to the sample pre-processing of deep learning to improve the image resolution. Then the paper used the faster regional convolutional neural network to train the pedestrian detection model, extracted the pedestrian characteristics, and obtained the bounding boxes through classification and position regression. Finally, the pedestrian detection process was carried out by introducing the Soft-NMS algorithm, and the redundant bounding box was eliminated to obtain the best pedestrian detection position. The experimental results showed that the proposed detection algorithm achieves an average accuracy of 89.74% on the low-light dataset, and the pedestrian detection effect was more significant.

基于HSI空间的Retinex低照度图像增强算法

低照度环境下拍摄的图像往往会出现细节模糊不清的情况，传统的Retinex算法可以有效提高图像质量，然而当图像亮度整体较低时可能会出现过增强现象。为了改善低照度环境下拍摄图像的质量，本文提出了一种基于HSI颜色空间的改进的多尺度Retinex图像增强算法，采用引导图像滤波消除应用Retinex算法所产生的“光晕伪影”现象，并利用原图像的亮度信息对多尺度Retinex算法增强后的图像进行了亮度重构，有效地抑制了过增强等失真现象，进一步提高了图像增强质量。实验结果表明，本文算法与传统的多尺度Retinex算法相比在低照度图像亮度增强、对比度增强和图像细节信息保护方面具有更好的表现效果。 The images which are captured in low brightness environment are often blurred. The traditional Retinex algorithm can improve the quality of image; however enhancement phenomenon may occur when the image brightness is low. In order to improve the quality of captured images in brightness environment, an improved multi-scale Retinex image enhancement algorithm based on HSI color space is proposed in this paper. In this algorithm, the guide image filtering is used to eliminate the “halo artifact”. The intensity of enhanced image based on multi-scale Retinex algorithm, is reconstructed by applying the intensity of original image. This effectively suppresses the distortion such as over-enhancement, and further enhances the image quality. Experimental results show that for low-luminance image the proposed algorithm has better performance than the traditional multi-scale Retinex algorithm in brightness enhancement, contrast enhancement and image detail information protection.

IR and Multi Scale Retinex image Enhancement for Concealed Weapon Detection

A Concealed Weapon Detection (CWD) had been developed by a large number of researchers and technologies. As a result of the weakness of the infrared images in unique altogether graphic items, infrared and MMW images become inaccurate and insufficient to obviously detectand deal withweaponry objectsin an invisible setting. This article uses Multi Scale Retinex and contrast stretching image processing enhancement techniques to improve the recognition of weapons concealed below attire. Specifically, the focus of the study is on detecting weapons and ammos by enhancing the IR pictures based on image processing techniques. Evaluation techniques were empirically proved to be able to show the enhancement percentage progress.

Improved multi-scale retinex image enhancement algorithm

For the existing problems of expensive calculation in the process of image enhancement with multi-scale Retinex this paper presented an improved algorithm on the basis of fast two-dimensional convolution and multi-scale continuous estimation.Compared with the original algorithm the new one was simpler for its superiority of making full use of the separability of the image Gaussian convolution and the feasibility of multi-scale continuous illumination estimation.Meanwhile a histogram clipping method with removing extremum was proposed to deal with the color distortion of enhanced image which could restore image color information and enhance image contrast.The experimental results demonstrate that the proposed method can efficiently increase the running speed while improving image quality.

Resiliency of the Multiscale Retinex Image Enhancement Algorithm

Resiliency of the Multiscale Retinex Image Enhancement Algorithm