Retinex-Based Perceptual Contrast Enhancement in Images Using Luminance Adaptation

Images captured under varying light conditions have deficient contrast, low brightness, latent colors, and high noise. Numerous methods have been developed for image enhancement. However, these methods are only suitable for enhancing specific type of images (e.g., overexposed or underexposed), and also fail to restore artifact-free results for various other types of images. Therefore, to meet this goal, in this paper, we present an automatic image enhancement method, which is capable of producing quality results for all types of images captured under uneven exposure conditions (e.g., backlit, non-uniform, overexposed , one-sided illumination and night-time images). Firstly, images are categorized using a convolutional neural network (CNN) to determine their class, and different values of weight coefficients are achieved for further processing. Then, images are converted into photonegative form to obtain an initial transmission map using a bright channel prior. Next, L1-norm regularization is adopted to refine scene transmission. Besides, environmental light is estimated based on an effective filter. Finally, the image degradation model is applied to achieve enhanced results. Furthermore, post-processing of the images is comprised of two steps, such as denoising and details enhancement. The denoised model is only applied when the images are captured in extreme low-light conditions. Whereas, a smooth layer is obtained using L1-norm regularization to enhance details in partially over-and underexposed images. Extensive experiments reveal the effectives of the proposed approach as compared to other state-of-the-art algorithms. INDEX TERMS Exposure correction, low-light conditions, details enhancement, image degradation model.

Section: B Results and Discussionmentioning

confidence: 88%

Efficient Image Enhancement Model for Correcting Uneven Illumination Images

Rahman

Aamir

et al. 2020

“…Thus to decrease the negative effect of environment light, a lighting compensation method is designed. Both a standard color card and a Light Emitting Diode (LED) light source are used to provide a reference and make the light compensation [30] for our system. The distributed surface light source or the ringing shape light source can be used.…”

Section: B Environment Lighting Control Methodsmentioning

confidence: 99%

Automatic Process Parameters Tuning and Surface Roughness Estimation for Laser Cleaning

Liu

Yang

et al. 2020

An image analysis-based two-stage process parameters tuning and Surface Roughness (SR) estimation algorithm is proposed for the laser cleaning application. A Cartesian coordinate robot is utilized to collect image and implement cleaning. Before cleaning, in order to tune the proper laser parameters, first, the environment lighting is controlled for the metal image collection. Second, lots of classification features are computed for the images above. The Gray-Level Co-occurrence Matrix (GLCM) texture features, the concavo-convex region features, the histogram symmetry difference feature, and the imaging thermophysical property features are computed. Third, the initial laser parameters are created randomly and an iteration computation is performed: a Support Vector Machine (SVM) is used to forecast the cleaning effect; its inputs include the classification features and the initial laser parameters; its output is the cleaning effect degree. If the SVM output cannot fulfill user's demand, the laser parameters will be updated randomly. This iteration will be implemented constantly until the SVM output becomes valid. Then the laser cleaning will be performed. When estimating SR for the cleaned metal, multiple image features are calculated for the images after cleaning. The features include the Tamura coarseness, some GLCM features, and the convex region feature. To improve the prediction precision, different feature combinations are used for different cleaning effects. The linear function and the 3-order polynomial function are considered for the SR estimation. After tests, the accuracies of SVM, the SR prediction function, and the integrated SR control and estimation algorithm can be 90.0%, 80.0% and 80.0% approximately.

“…High-frequency detail images need to be quantitatively stretched to conform to human vision. Similar to the method of high-frequency detail processing in GIMP [21], [22], we use the standard deviation and mean of the detail image and add adjustment factors D to linearly quantize the image. (8) where α and β are the standard deviation and mean of an image block, L ij is a small detail map of I ij after multilayer decomposition and non-linear mapping.…”

Section: Transmittance Estimationmentioning

confidence: 99%

Multilayer Fusion and Chunk-Based Transmittance Estimation for Natural Hazy Image Enhancement

Mei

Yuan

2019

Aiming at the uneven distribution of haze concentration and color imbalance in haze weather images, a natural hazy image enhancement method which combines with multilayer fusion and chunk-based is proposed. Based on the atmospheric physical model, the detail and base layers of scene images can be extracted using multilayer decomposition and nonlinear mapping function. Iterative Box Filter can improve the accuracy of ambient light selection and avoid the imbalance of ambient light estimation. The image is segmented into blocks, and the block images are processed by the same operations which are multilayer decomposition and nonlinear mapping function to obtain the detail maps of block images. By splicing these detail maps into the whole detail maps and combining with the dark channel priori, a good transmittance estimation map can be obtained. Throughout the experiment, the guide image filter is utilized to preserve the edges of the image and color correction is added to the model. The experiment results demonstrate that our proposed method can outperform state-of-the-art methods in both qualitative and quantitative comparisons. INDEX TERMS Image enhancement, multilayer decomposition, nonlinear mapping function, box filter, chunk-based.