Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by ...Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by human vision and by some outdoor computer vision systems.Therefore image dehazing is an important issue and has been widely researched in the field of computer vision.The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing.This paper reviews the main techniques of image dehazing that have been developed over the past decade.Firstly,we innovatively divide a number of approaches into three categories:image enhancement based methods,image fusion based methods and image restoration based methods.All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics.Various quality evaluation methods are then described,sorted and discussed in detail.Finally,research progress is summarized and future research directions are suggested.展开更多
Technological advancements continue to expand the communications industry’s potential.Images,which are an important component in strengthening communication,are widely available.Therefore,image quality assessment(IQA...Technological advancements continue to expand the communications industry’s potential.Images,which are an important component in strengthening communication,are widely available.Therefore,image quality assessment(IQA)is critical in improving content delivered to end users.Convolutional neural networks(CNNs)used in IQA face two common challenges.One issue is that these methods fail to provide the best representation of the image.The other issue is that the models have a large number of parameters,which easily leads to overfitting.To address these issues,the dense convolution network(DSC-Net),a deep learning model with fewer parameters,is proposed for no-reference image quality assessment(NR-IQA).Moreover,it is obvious that the use of multimodal data for deep learning has improved the performance of applications.As a result,multimodal dense convolution network(MDSC-Net)fuses the texture features extracted using the gray-level co-occurrence matrix(GLCM)method and spatial features extracted using DSC-Net and predicts the image quality.The performance of the proposed framework on the benchmark synthetic datasets LIVE,TID2013,and KADID-10k demonstrates that the MDSC-Net approach achieves good performance over state-of-the-art methods for the NR-IQA task.展开更多
Recently, device storage capacity and transmission bandwidth requirements are facing a heavy burden on account of massive internet images. Generally, to improve user experience and save costs as much as possible, a lo...Recently, device storage capacity and transmission bandwidth requirements are facing a heavy burden on account of massive internet images. Generally, to improve user experience and save costs as much as possible, a lot of internet applications always focus on how to achieve appropriate image reeompression. In this paper, we propose a novel framework to efficiently customize image recompression according to a variety of applications. First of all, we evaluate the input image's compression level and predict an initial compression level which is very close to the final output of our system using a prior learnt from massive images. Then, we iteratively recompress the input image to different levels and measure the perceptual similarity between the input image and the new result by a block-based coding quality method. According to the output of the quality assessment method, we can update the target compression level, or switch to the subjective evaluation, or return the final recompression result in our system pipeline control. We organize subjective evaluations based on different applications and obtain corresponding assessment report. At last, based on the assessment report, we set up a series of appropriate parameters for customizing image recompression. Moreover, our new framework has been successfully applied to many commercial applications, such as web portals, e-commerce, online game, and so on.展开更多
Depth-image-based rendering(DIBR) is widely used in 3 DTV, free-viewpoint video, and interactive 3 D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, ...Depth-image-based rendering(DIBR) is widely used in 3 DTV, free-viewpoint video, and interactive 3 D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, particularly geometric distortions induced by object dis-occlusion. Ensuring the quality of synthetic images is critical to maintaining adequate system service. However, traditional 2 D image quality metrics are ineffective for evaluating synthetic images as they are not sensitive to geometric distortion. In this paper, we propose a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights. Due to the lack of existing training data, we construct a new DIBR synthetic image dataset as part of our contribution. Experiments were conducted on both the public benchmark IRCCyN/IVC DIBR image dataset and our own dataset. Results demonstrate that our proposed metric outperforms traditional 2 D image quality metrics and state-of-the-art DIBR-related metrics.展开更多
A variety of existing image quality assessment (IQA) metrics share a similar two-stage framework: at the first stage, a quality map is constructed by comparison between local regions of reference and distorted imag...A variety of existing image quality assessment (IQA) metrics share a similar two-stage framework: at the first stage, a quality map is constructed by comparison between local regions of reference and distorted images; at the second stage, the spatial pooling is adopted to obtain overall quality score. In this work, we propose a novel spatial pooling strategy for image quality assessment through statistical analysis of the quality map. Our in-depth analysis indicates that the overall image quality is sensitive to the quality distribution. Based on the analysis, the quality histogram and statistical descriptors extracted from the quality map are used as input to the support vector regression to obtain the final objective quality score. Experimental results on three large public IQA databases have demonstrated that the proposed spatial pooling strategy can greatly improve the quality prediction performance of the original IQA metrics in terms of correlation with human subjective ratings.展开更多
基金supported by the National Natural Science Foundation of China(61403283)Shandong Provincial Natural Science Foundation(ZR2013FQ036.ZR2015PE025)+2 种基金the Spark Program of China(2013GA740053)the Spark Program of Shandong Province(2013XH06034)the Technology Development Plan of Weifang City(201301015)
文摘Images captured in hazy or foggy weather conditions can be seriously degraded by scattering of atmospheric particles,which reduces the contrast,changes the color,and makes the object features difficult to identify by human vision and by some outdoor computer vision systems.Therefore image dehazing is an important issue and has been widely researched in the field of computer vision.The role of image dehazing is to remove the influence of weather factors in order to improve the visual effects of the image and provide benefit to post-processing.This paper reviews the main techniques of image dehazing that have been developed over the past decade.Firstly,we innovatively divide a number of approaches into three categories:image enhancement based methods,image fusion based methods and image restoration based methods.All methods are analyzed and corresponding sub-categories are introduced according to principles and characteristics.Various quality evaluation methods are then described,sorted and discussed in detail.Finally,research progress is summarized and future research directions are suggested.
文摘Technological advancements continue to expand the communications industry’s potential.Images,which are an important component in strengthening communication,are widely available.Therefore,image quality assessment(IQA)is critical in improving content delivered to end users.Convolutional neural networks(CNNs)used in IQA face two common challenges.One issue is that these methods fail to provide the best representation of the image.The other issue is that the models have a large number of parameters,which easily leads to overfitting.To address these issues,the dense convolution network(DSC-Net),a deep learning model with fewer parameters,is proposed for no-reference image quality assessment(NR-IQA).Moreover,it is obvious that the use of multimodal data for deep learning has improved the performance of applications.As a result,multimodal dense convolution network(MDSC-Net)fuses the texture features extracted using the gray-level co-occurrence matrix(GLCM)method and spatial features extracted using DSC-Net and predicts the image quality.The performance of the proposed framework on the benchmark synthetic datasets LIVE,TID2013,and KADID-10k demonstrates that the MDSC-Net approach achieves good performance over state-of-the-art methods for the NR-IQA task.
基金supported by a joint project of Tencent Research and Shanghai Jiao Tong Universitysupported by the National Basic Research 973 Program of China under Grant No.2011CB302203+2 种基金the National Natural Science Foundation of China under Grant Nos.61073089,61133009the Open Projects Program of National Laboratory of Pattern Recognition of Chinathe Open Project Program of the State Key Lab of CAD&CG of Zhejiang University of China under Grant No.A1206
文摘Recently, device storage capacity and transmission bandwidth requirements are facing a heavy burden on account of massive internet images. Generally, to improve user experience and save costs as much as possible, a lot of internet applications always focus on how to achieve appropriate image reeompression. In this paper, we propose a novel framework to efficiently customize image recompression according to a variety of applications. First of all, we evaluate the input image's compression level and predict an initial compression level which is very close to the final output of our system using a prior learnt from massive images. Then, we iteratively recompress the input image to different levels and measure the perceptual similarity between the input image and the new result by a block-based coding quality method. According to the output of the quality assessment method, we can update the target compression level, or switch to the subjective evaluation, or return the final recompression result in our system pipeline control. We organize subjective evaluations based on different applications and obtain corresponding assessment report. At last, based on the assessment report, we set up a series of appropriate parameters for customizing image recompression. Moreover, our new framework has been successfully applied to many commercial applications, such as web portals, e-commerce, online game, and so on.
基金sponsored by the National Key R&D Program of China (No. 2017YFB1002702)the National Natural Science Foundation of China (Nos. 61572058, 61472363)
文摘Depth-image-based rendering(DIBR) is widely used in 3 DTV, free-viewpoint video, and interactive 3 D graphics applications. Typically, synthetic images generated by DIBR-based systems incorporate various distortions, particularly geometric distortions induced by object dis-occlusion. Ensuring the quality of synthetic images is critical to maintaining adequate system service. However, traditional 2 D image quality metrics are ineffective for evaluating synthetic images as they are not sensitive to geometric distortion. In this paper, we propose a novel no-reference image quality assessment method for synthetic images based on convolutional neural networks, introducing local image saliency as prediction weights. Due to the lack of existing training data, we construct a new DIBR synthetic image dataset as part of our contribution. Experiments were conducted on both the public benchmark IRCCyN/IVC DIBR image dataset and our own dataset. Results demonstrate that our proposed metric outperforms traditional 2 D image quality metrics and state-of-the-art DIBR-related metrics.
基金This work was supported by the National Natural Science Foundation of China under Grant No. 61571212 and the Natural Science Foundation of Jiangxi Province of China under Grant No. 20151BDH80003.
文摘A variety of existing image quality assessment (IQA) metrics share a similar two-stage framework: at the first stage, a quality map is constructed by comparison between local regions of reference and distorted images; at the second stage, the spatial pooling is adopted to obtain overall quality score. In this work, we propose a novel spatial pooling strategy for image quality assessment through statistical analysis of the quality map. Our in-depth analysis indicates that the overall image quality is sensitive to the quality distribution. Based on the analysis, the quality histogram and statistical descriptors extracted from the quality map are used as input to the support vector regression to obtain the final objective quality score. Experimental results on three large public IQA databases have demonstrated that the proposed spatial pooling strategy can greatly improve the quality prediction performance of the original IQA metrics in terms of correlation with human subjective ratings.