In this paper,a new approach is proposed to determine whether the content of an image is authentic or modified with a focus on detecting complex image tampering.Detecting image tampering without any prior information ...In this paper,a new approach is proposed to determine whether the content of an image is authentic or modified with a focus on detecting complex image tampering.Detecting image tampering without any prior information of the original image is a challenging problem since unknown diverse manipulations may have different characteristics and so do various formats of images.Our principle is that image processing,no matter how complex,may affect image quality,so image quality metrics can be used to distinguish tampered images.In particular,based on the alteration of image quality in modified blocks,the proposed method can locate the tampered areas.Referring to four types of effective no-reference image quality metrics,we obtain 13 features to present an image.The experimental results show that the proposed method is very promising on detecting image tampering and locating the locally tampered areas especially in realistic scenarios.展开更多
Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality...Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality assessment(IQA) study on omnidirectional images. We first build an omnidirectional IQA(OIQA) database, including 16 source images with their corresponding 320 distorted images. We add four commonly encountered distortions. These distortions are JPEG compression, JPEG2000 compression, Gaussian blur, and Gaussian noise. Then we conduct a subjective quality evaluation study in the VR environment based on the OIQA database. Considering that visual attention is more important in VR environment, head and eye movement data are also tracked and collected during the quality rating experiments. The 16 raw and their corresponding distorted images,subjective quality assessment scores, and the head-orientation data and eye-gaze data together constitute the OIQA database. Based on the OIQA database, we test some state-of-the-art full-reference IQA(FR-IQA) measures on equirectangular format or cubic formatomnidirectional images. The results show that applying FR-IQA metrics on cubic format omnidirectional images could improve their performance. The performance of some FR-IQA metrics combining the saliency weight of three different types are also tested based on our database. Some new phenomena different from traditional IQA are observed.展开更多
In order to apply the deep learning to the stereo image quality evaluation,two problems need to be solved:The first one is that we have a bit of training samples,another is how to input the dimensional image’s left v...In order to apply the deep learning to the stereo image quality evaluation,two problems need to be solved:The first one is that we have a bit of training samples,another is how to input the dimensional image’s left view or right view.In this paper,we transfer the 2D image quality evaluation model to the stereo image quality evaluation,and this method solves the first problem;use the method of principal component analysis is used to fuse the left and right views into an input image in order to solve the second problem.At the same time,the input image is preprocessed by phase congruency transformation,which further improves the performance of the algorithm.The structure of the deep convolution neural network consists of four convolution layers and three maximum pooling layers and two fully connected layers.The experimental results on LIVE3D image database show that the prediction quality score of the model is in good agreement with the subjective evaluation value.展开更多
Image segmentation is a critical step of image analysis. Segmentation evaluation is an effective procedure for studying the performance of segmentation techniques, in which quality measure plays an important role. Thi...Image segmentation is a critical step of image analysis. Segmentation evaluation is an effective procedure for studying the performance of segmentation techniques, in which quality measure plays an important role. This paper presents a group of new objective quality measures for segmentation evaluation and compares their performances. In addition, to verify the effectiveness of these new measures, an appropriate classification of segmentation is proposed. According to this classification, several representative algorithms from different categories are selected for comparison testing. Some valuable results are obtained and presented.展开更多
Image enhancement is a popular technique,which is widely used to improve the visual quality of images.While image enhancement has been extensively investigated,the relevant quality assessment of enhanced images remain...Image enhancement is a popular technique,which is widely used to improve the visual quality of images.While image enhancement has been extensively investigated,the relevant quality assessment of enhanced images remains an open problem,which may hinder further development of enhancement techniques.In this paper,a no-reference quality metric for digitally enhanced images is proposed.Three kinds of features are extracted for characterizing the quality of enhanced images,including non-structural information,sharpness and naturalness.Specifically,a total of 42 perceptual features are extracted and used to train a support vector regression(SVR) model.Finally,the trained SVR model is used for predicting the quality of enhanced images.The performance of the proposed method is evaluated on several enhancement-related databases,including a new enhanced image database built by the authors.The experimental results demonstrate the efficiency and advantage of the proposed metric.展开更多
Recent studies on no-reference image quality assessment (NR-IQA) methods usually learn to evaluate the image quality by regressing from human subjective scores of the training samples. This study presented an NR-IQA m...Recent studies on no-reference image quality assessment (NR-IQA) methods usually learn to evaluate the image quality by regressing from human subjective scores of the training samples. This study presented an NR-IQA method based on the basic image visual parameters without using human scored image databases in learning. We demonstrated that these features comprised the most basic characteristics for constructing an image and influencing the visual quality of an image. In this paper, the definitions, computational method, and relationships among these visual metrics were described. We subsequently proposed a no-reference assessment function, which was referred to as a visual parameter measurement index (VPMI), based on the integration of these visual metrics to assess image quality. It is established that the maximum of VPMI corresponds to the best quality of the color image. We verified this method using the popular assessment database—image quality assessment database (LIVE), and the results indicated that the proposed method matched better with the subjective assessment of human vision. Compared with other image quality assessment models, it is highly competitive. VPMI has low computational complexity, which makes it promising to implement in real-time image assessment systems.展开更多
Image segmentation is an important stage in many applications such as image, video and computer processing. Generally image interpretation depends on it. The materials and methods used to demonstrate are described. Th...Image segmentation is an important stage in many applications such as image, video and computer processing. Generally image interpretation depends on it. The materials and methods used to demonstrate are described. The results are presented and analyzed. Several approaches and algorithms for image segmentation have been developed, but it is difficult to evaluate the efficiency and to make an objective comparison of different segmentation methods. This general problem has been addressed for the evaluation of a segmentation result and the results are available in the literature. In this work, we first presented some criteria of evaluation of segmentation commonly used in image processing with reviews of their models. Then multicomponent synthetic images of known composition are applied to these criteria to explore the operation and evaluate its relevance. The results show that choosing an assessment method depends on the purpose, however the criterion of Zeboudj appears powerful for the evaluation of region segmentations for properly separated classes, on the contrary the criteria of Levine-Nazif and Borsotti are adapted to the methods of classification and permit to build homogeneous regions or classes. The values of the Rosenbeger criterion are generally low and similar, so hard to make a comparison of segmentations with this criterion.展开更多
The identification and quality evaluation of Flos carthami were studied using tunable liquid spectral imaging instrument, to discuss the application range and advantages of spectral imaging technology in Chinese medic...The identification and quality evaluation of Flos carthami were studied using tunable liquid spectral imaging instrument, to discuss the application range and advantages of spectral imaging technology in Chinese medicine identification and quality control field. The Flos carthami was indentified by extracting the normalized characteristic spectral curves of Flos carthami, Crocus sativus and Dendranthema morifolium, which were standard samples supplied by National Institute for Drug Control. The qualities of Flos carthamies collecting from different pharmacies were evaluated by extracting their normalized characteristic spectral curves. The imaging spectrum testing system was designed independently. The spectral resolution was 5 nm, and the spectral range was from 400 nm to 680 nm. The results showed that the normalized characteristic spectral curve of Flos carthami was significantly different from those of Crocus sativus’ and Dendranthema morifolium’s, and the fluorescence intensity of Flos carthami from different commercial sources were different. Spectral imaging technology could be used to identify and evaluate Flos carthami, and operation method was rapid, convenient and non-destructive.展开更多
Traditional image quality assessment methods use the hand-crafted features to predict the image quality score,which cannot perform well in many scenes.Since deep learning promotes the development of many computer visi...Traditional image quality assessment methods use the hand-crafted features to predict the image quality score,which cannot perform well in many scenes.Since deep learning promotes the development of many computer vision tasks,many IQA methods start to utilize the deep convolutional neural networks(CNN)for IQA task.In this paper,a CNN-based multi-scale blind image quality predictor is proposed to extract more effectivity multi-scale distortion features through the pyramidal convolution,which consists of two tasks:A distortion recognition task and a quality regression task.For the first task,image distortion type is obtained by the fully connected layer.For the second task,the image quality score is predicted during the distortion recognition progress.Experimental results on three famous IQA datasets show that the proposed method has better performance than the previous traditional algorithms for quality prediction and distortion recognition.展开更多
Based on the raw data of spaceborne dispersive and interferometry imaging spectrometer,a set of quality evaluation metrics for compressed hyperspectral data is initially established in this paper.These quality evaluat...Based on the raw data of spaceborne dispersive and interferometry imaging spectrometer,a set of quality evaluation metrics for compressed hyperspectral data is initially established in this paper.These quality evaluation metrics,which consist of four aspects including compression statistical distortion,sensor performance evaluation,data application performance and image quality,are suited to the comprehensive and systematical analysis of the impact of lossy compression in spaceborne hyperspectral remote sensing data quality.Furthermore,the evaluation results would be helpful to the selection and optimization of satellite data compression scheme.展开更多
To evaluate the quality of blurred images effectively,this study proposes a no-reference blur assessment method based on gradient distortion measurement and salient region maps.First,a Gaussian low-pass filter is used...To evaluate the quality of blurred images effectively,this study proposes a no-reference blur assessment method based on gradient distortion measurement and salient region maps.First,a Gaussian low-pass filter is used to construct a reference image by blurring a given image.Gradient similarity is included to obtain the gradient distortion measurement map,which can finely reflect the smallest possible changes in textures and details.Second,a saliency model is utilized to calculate image saliency.Specifically,an adaptive method is used to calculate the specific salient threshold of the blurred image,and the blurred image is binarized to yield the salient region map.Block-wise visual saliency serves as the weight to obtain the final image quality.Experimental results based on the image and video engineering database,categorial image quality database,and camera image database demonstrate that the proposed method correlates well with human judgment.Its computational complexity is also relatively low.展开更多
Image segmentation denotes a process for partitioning an image into distinct regions, it plays an important role in interpretation and decision making. A large variety of segmentation methods has been developed;among ...Image segmentation denotes a process for partitioning an image into distinct regions, it plays an important role in interpretation and decision making. A large variety of segmentation methods has been developed;among them, multidimensional histogram methods have been investigated but their implementation stays difficult due to the big size of histograms. We present an original method for segmenting n-D (where n is the number of components in image) images or multidimensional images in an unsupervised way using a fuzzy neighbourhood model. It is based on the hierarchical analysis of full n-D compact histograms integrating a fuzzy connected components labelling algorithm that we have realized in this work. Each peak of the histo- gram constitutes a class kernel, as soon as it encloses a number of pixels greater than or equal to a secondary arbitrary threshold knowing that a first threshold was set to define the degree of binary fuzzy similarity be- tween pixels. The use of a lossless compact n-D histogram allows a drastic reduction of the memory space necessary for coding it. As a consequence, the segmentation can be achieved without reducing the colors population of images in the classification step. It is shown that using n-D compact histograms, instead of 1-D and 2-D ones, leads to better segmentation results. Various images were segmented;the evaluation of the quality of segmentation in supervised and unsupervised of segmentation method proposed compare to the classification method k-means gives better results. It thus highlights the relevance of our approach, which can be used for solving many problems of segmentation.展开更多
In recent years,many medical image fusion methods had been exploited to derive useful information from multimodality medical image data,but,not an appropriate fusion algorithm for anatomical and functional medical ima...In recent years,many medical image fusion methods had been exploited to derive useful information from multimodality medical image data,but,not an appropriate fusion algorithm for anatomical and functional medical images.In this paper,the traditional method of wavelet fusion is improved and a new fusion algorithm of anatomical and functional medical images,in which high-frequency and low-frequency coefficients are studied respectively.When choosing high-frequency coefficients,the global gradient of each sub-image is calculated to realize adaptive fusion,so that the fused image can reserve the functional information;while choosing the low coefficients is based on the analysis of the neighborbood region energy,so that the fused image can reserve the anatomical image's edge and texture feature.Experimental results and the quality evaluation parameters show that the improved fusion algorithm can enhance the edge and texture feature and retain the function information and anatomical information effectively.展开更多
Objective evaluations of fused images are important in comparing the performance of different image fusion algorithms. This paper describes a structural similarity metric that does not use a reference image for image ...Objective evaluations of fused images are important in comparing the performance of different image fusion algorithms. This paper describes a structural similarity metric that does not use a reference image for image fusion evaluations. The metric is based on the universal image quality index and addresses not only the similarities between the input images and the fused image, but also the similarities among the input images. The evaluation process distinguishes between complementary information and redundant information using similarities among the input images. The metric uses the information classification to estimate how much structural similarity is preserved in the fused image. Tests demonstrate that the metric correlates well with subjective evaluations of the fused images.展开更多
为实现星载数字时间延迟积分(Digital Time Integration Delay,DTDI)系统的有效设计与成像质量分析,文章提出星载DTDI系统全链路成像质量影响因素分析方法。首先,分析了技术的原理和影响因素,在此基础上构建了场景-大气-星载系统-处理...为实现星载数字时间延迟积分(Digital Time Integration Delay,DTDI)系统的有效设计与成像质量分析,文章提出星载DTDI系统全链路成像质量影响因素分析方法。首先,分析了技术的原理和影响因素,在此基础上构建了场景-大气-星载系统-处理的全链路DTDI成像系统仿真模型,开展了多要素影响下的DTDI成像仿真试验与分析评价。结果表明:0.9 m分辨率下,积分时间0.063 ms、量化位数12 bit、TDI级数6级可以获得较好的成像质量,利用DTDI技术可将平台稳定度要求降至0.1(°)/s。文章研究成果可为星载DTDI系统设计分析提供参考。展开更多
A way of embedded learning convolution neural network(ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale dat...A way of embedded learning convolution neural network(ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also score the image aesthetic quality. First, we chose Alexnet and VGG_S to compare for confirming which is more suitable for this image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tuning cannot make full use of the small-scale data set. Third, to solve the problem in second step, a way of using twice fine-tuning continually based on the aesthetic quality label and content label respective is proposed, the classification probability of the trained CNN models is used to evaluate the image aesthetic quality. The experiments are carried on the small-scale data set of Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.展开更多
Objective image quality assessment(IQA)plays an important role in various visual communication systems,which can automatically and efficiently predict the perceived quality of images.The human eye is the ultimate eval...Objective image quality assessment(IQA)plays an important role in various visual communication systems,which can automatically and efficiently predict the perceived quality of images.The human eye is the ultimate evaluator for visual experience,thus the modeling of human visual system(HVS)is a core issue for objective IQA and visual experience optimization.The traditional model based on black box fitting has low interpretability and it is difficult to guide the experience optimization effectively,while the model based on physiological simulation is hard to integrate into practical visual communication services due to its high computational complexity.For bridging the gap between signal distortion and visual experience,in this paper,we propose a novel perceptual no-reference(NR)IQA algorithm based on structural computational modeling of HVS.According to the mechanism of the human brain,we divide the visual signal processing into a low-level visual layer,a middle-level visual layer and a high-level visual layer,which conduct pixel information processing,primitive information processing and global image information processing,respectively.The natural scene statistics(NSS)based features,deep features and free-energy based features are extracted from these three layers.The support vector regression(SVR)is employed to aggregate features to the final quality prediction.Extensive experimental comparisons on three widely used benchmark IQA databases(LIVE,CSIQ and TID2013)demonstrate that our proposed metric is highly competitive with or outperforms the state-of-the-art NR IQA measures.展开更多
基金Sponsored by the National Natural Science Foundation of China(Grant No.60971095 and No.61172109)Artificial Intelligence Key Laboratory of Sichuan Province(Grant No.2012RZJ01)the Fundamental Research Funds for the Central Universities(Grant No.DUT13RC201)
文摘In this paper,a new approach is proposed to determine whether the content of an image is authentic or modified with a focus on detecting complex image tampering.Detecting image tampering without any prior information of the original image is a challenging problem since unknown diverse manipulations may have different characteristics and so do various formats of images.Our principle is that image processing,no matter how complex,may affect image quality,so image quality metrics can be used to distinguish tampered images.In particular,based on the alteration of image quality in modified blocks,the proposed method can locate the tampered areas.Referring to four types of effective no-reference image quality metrics,we obtain 13 features to present an image.The experimental results show that the proposed method is very promising on detecting image tampering and locating the locally tampered areas especially in realistic scenarios.
文摘Virtual reality(VR) environment can provide immersive experience to viewers.Under the VR environment, providing a good quality of experience is extremely important.Therefore, in this paper, we present an image quality assessment(IQA) study on omnidirectional images. We first build an omnidirectional IQA(OIQA) database, including 16 source images with their corresponding 320 distorted images. We add four commonly encountered distortions. These distortions are JPEG compression, JPEG2000 compression, Gaussian blur, and Gaussian noise. Then we conduct a subjective quality evaluation study in the VR environment based on the OIQA database. Considering that visual attention is more important in VR environment, head and eye movement data are also tracked and collected during the quality rating experiments. The 16 raw and their corresponding distorted images,subjective quality assessment scores, and the head-orientation data and eye-gaze data together constitute the OIQA database. Based on the OIQA database, we test some state-of-the-art full-reference IQA(FR-IQA) measures on equirectangular format or cubic formatomnidirectional images. The results show that applying FR-IQA metrics on cubic format omnidirectional images could improve their performance. The performance of some FR-IQA metrics combining the saliency weight of three different types are also tested based on our database. Some new phenomena different from traditional IQA are observed.
文摘In order to apply the deep learning to the stereo image quality evaluation,two problems need to be solved:The first one is that we have a bit of training samples,another is how to input the dimensional image’s left view or right view.In this paper,we transfer the 2D image quality evaluation model to the stereo image quality evaluation,and this method solves the first problem;use the method of principal component analysis is used to fuse the left and right views into an input image in order to solve the second problem.At the same time,the input image is preprocessed by phase congruency transformation,which further improves the performance of the algorithm.The structure of the deep convolution neural network consists of four convolution layers and three maximum pooling layers and two fully connected layers.The experimental results on LIVE3D image database show that the prediction quality score of the model is in good agreement with the subjective evaluation value.
基金Supported under grants CEC-F1994660 and CEC-TM199416
文摘Image segmentation is a critical step of image analysis. Segmentation evaluation is an effective procedure for studying the performance of segmentation techniques, in which quality measure plays an important role. This paper presents a group of new objective quality measures for segmentation evaluation and compares their performances. In addition, to verify the effectiveness of these new measures, an appropriate classification of segmentation is proposed. According to this classification, several representative algorithms from different categories are selected for comparison testing. Some valuable results are obtained and presented.
基金supported in part by the National Natural Science Foundation of China under Grant 61379143in part by the Fundamental Research Funds for the Central Universities under Grant 2015QNA66in part by the Qing Lan Project of Jiangsu Province
文摘Image enhancement is a popular technique,which is widely used to improve the visual quality of images.While image enhancement has been extensively investigated,the relevant quality assessment of enhanced images remains an open problem,which may hinder further development of enhancement techniques.In this paper,a no-reference quality metric for digitally enhanced images is proposed.Three kinds of features are extracted for characterizing the quality of enhanced images,including non-structural information,sharpness and naturalness.Specifically,a total of 42 perceptual features are extracted and used to train a support vector regression(SVR) model.Finally,the trained SVR model is used for predicting the quality of enhanced images.The performance of the proposed method is evaluated on several enhancement-related databases,including a new enhanced image database built by the authors.The experimental results demonstrate the efficiency and advantage of the proposed metric.
基金supported by the National Natural Science Foundation of China under Grants No.61773094,No.61573080,No.91420105,and No.61375115National Program on Key Basic Research Project(973 Program)under Grant No.2013CB329401+1 种基金National High-Tech R&D Program of China(863 Program)under Grant No.2015AA020505Sichuan Province Science and Technology Project under Grants No.2015SZ0141 and No.2018ZA0138
文摘Recent studies on no-reference image quality assessment (NR-IQA) methods usually learn to evaluate the image quality by regressing from human subjective scores of the training samples. This study presented an NR-IQA method based on the basic image visual parameters without using human scored image databases in learning. We demonstrated that these features comprised the most basic characteristics for constructing an image and influencing the visual quality of an image. In this paper, the definitions, computational method, and relationships among these visual metrics were described. We subsequently proposed a no-reference assessment function, which was referred to as a visual parameter measurement index (VPMI), based on the integration of these visual metrics to assess image quality. It is established that the maximum of VPMI corresponds to the best quality of the color image. We verified this method using the popular assessment database—image quality assessment database (LIVE), and the results indicated that the proposed method matched better with the subjective assessment of human vision. Compared with other image quality assessment models, it is highly competitive. VPMI has low computational complexity, which makes it promising to implement in real-time image assessment systems.
文摘Image segmentation is an important stage in many applications such as image, video and computer processing. Generally image interpretation depends on it. The materials and methods used to demonstrate are described. The results are presented and analyzed. Several approaches and algorithms for image segmentation have been developed, but it is difficult to evaluate the efficiency and to make an objective comparison of different segmentation methods. This general problem has been addressed for the evaluation of a segmentation result and the results are available in the literature. In this work, we first presented some criteria of evaluation of segmentation commonly used in image processing with reviews of their models. Then multicomponent synthetic images of known composition are applied to these criteria to explore the operation and evaluate its relevance. The results show that choosing an assessment method depends on the purpose, however the criterion of Zeboudj appears powerful for the evaluation of region segmentations for properly separated classes, on the contrary the criteria of Levine-Nazif and Borsotti are adapted to the methods of classification and permit to build homogeneous regions or classes. The values of the Rosenbeger criterion are generally low and similar, so hard to make a comparison of segmentations with this criterion.
文摘The identification and quality evaluation of Flos carthami were studied using tunable liquid spectral imaging instrument, to discuss the application range and advantages of spectral imaging technology in Chinese medicine identification and quality control field. The Flos carthami was indentified by extracting the normalized characteristic spectral curves of Flos carthami, Crocus sativus and Dendranthema morifolium, which were standard samples supplied by National Institute for Drug Control. The qualities of Flos carthamies collecting from different pharmacies were evaluated by extracting their normalized characteristic spectral curves. The imaging spectrum testing system was designed independently. The spectral resolution was 5 nm, and the spectral range was from 400 nm to 680 nm. The results showed that the normalized characteristic spectral curve of Flos carthami was significantly different from those of Crocus sativus’ and Dendranthema morifolium’s, and the fluorescence intensity of Flos carthami from different commercial sources were different. Spectral imaging technology could be used to identify and evaluate Flos carthami, and operation method was rapid, convenient and non-destructive.
文摘Traditional image quality assessment methods use the hand-crafted features to predict the image quality score,which cannot perform well in many scenes.Since deep learning promotes the development of many computer vision tasks,many IQA methods start to utilize the deep convolutional neural networks(CNN)for IQA task.In this paper,a CNN-based multi-scale blind image quality predictor is proposed to extract more effectivity multi-scale distortion features through the pyramidal convolution,which consists of two tasks:A distortion recognition task and a quality regression task.For the first task,image distortion type is obtained by the fully connected layer.For the second task,the image quality score is predicted during the distortion recognition progress.Experimental results on three famous IQA datasets show that the proposed method has better performance than the previous traditional algorithms for quality prediction and distortion recognition.
基金supported by the Chinese 863 Plan Program under Grant 2012AA121504
文摘Based on the raw data of spaceborne dispersive and interferometry imaging spectrometer,a set of quality evaluation metrics for compressed hyperspectral data is initially established in this paper.These quality evaluation metrics,which consist of four aspects including compression statistical distortion,sensor performance evaluation,data application performance and image quality,are suited to the comprehensive and systematical analysis of the impact of lossy compression in spaceborne hyperspectral remote sensing data quality.Furthermore,the evaluation results would be helpful to the selection and optimization of satellite data compression scheme.
基金The National Natural Science Foundation of China(No.61762004,61762005)the National Key Research and Development Program(No.2018YFB1702700)+1 种基金the Science and Technology Project Founded by the Education Department of Jiangxi Province,China(No.GJJ200702,GJJ200746)the Open Fund Project of Jiangxi Engineering Laboratory on Radioactive Geoscience and Big Data Technology(No.JETRCNGDSS201901,JELRGBDT202001,JELRGBDT202003).
文摘To evaluate the quality of blurred images effectively,this study proposes a no-reference blur assessment method based on gradient distortion measurement and salient region maps.First,a Gaussian low-pass filter is used to construct a reference image by blurring a given image.Gradient similarity is included to obtain the gradient distortion measurement map,which can finely reflect the smallest possible changes in textures and details.Second,a saliency model is utilized to calculate image saliency.Specifically,an adaptive method is used to calculate the specific salient threshold of the blurred image,and the blurred image is binarized to yield the salient region map.Block-wise visual saliency serves as the weight to obtain the final image quality.Experimental results based on the image and video engineering database,categorial image quality database,and camera image database demonstrate that the proposed method correlates well with human judgment.Its computational complexity is also relatively low.
文摘Image segmentation denotes a process for partitioning an image into distinct regions, it plays an important role in interpretation and decision making. A large variety of segmentation methods has been developed;among them, multidimensional histogram methods have been investigated but their implementation stays difficult due to the big size of histograms. We present an original method for segmenting n-D (where n is the number of components in image) images or multidimensional images in an unsupervised way using a fuzzy neighbourhood model. It is based on the hierarchical analysis of full n-D compact histograms integrating a fuzzy connected components labelling algorithm that we have realized in this work. Each peak of the histo- gram constitutes a class kernel, as soon as it encloses a number of pixels greater than or equal to a secondary arbitrary threshold knowing that a first threshold was set to define the degree of binary fuzzy similarity be- tween pixels. The use of a lossless compact n-D histogram allows a drastic reduction of the memory space necessary for coding it. As a consequence, the segmentation can be achieved without reducing the colors population of images in the classification step. It is shown that using n-D compact histograms, instead of 1-D and 2-D ones, leads to better segmentation results. Various images were segmented;the evaluation of the quality of segmentation in supervised and unsupervised of segmentation method proposed compare to the classification method k-means gives better results. It thus highlights the relevance of our approach, which can be used for solving many problems of segmentation.
基金The National High Technology Research and Development Program of China(‘863’Program)grant number:2007AA02Z4A9+1 种基金National Natural Science Foundation of Chinagrant number:30671997
文摘In recent years,many medical image fusion methods had been exploited to derive useful information from multimodality medical image data,but,not an appropriate fusion algorithm for anatomical and functional medical images.In this paper,the traditional method of wavelet fusion is improved and a new fusion algorithm of anatomical and functional medical images,in which high-frequency and low-frequency coefficients are studied respectively.When choosing high-frequency coefficients,the global gradient of each sub-image is calculated to realize adaptive fusion,so that the fused image can reserve the functional information;while choosing the low coefficients is based on the analysis of the neighborbood region energy,so that the fused image can reserve the anatomical image's edge and texture feature.Experimental results and the quality evaluation parameters show that the improved fusion algorithm can enhance the edge and texture feature and retain the function information and anatomical information effectively.
基金Supported by the National Natural Science Foundation of China (No.60673024)
文摘Objective evaluations of fused images are important in comparing the performance of different image fusion algorithms. This paper describes a structural similarity metric that does not use a reference image for image fusion evaluations. The metric is based on the universal image quality index and addresses not only the similarities between the input images and the fused image, but also the similarities among the input images. The evaluation process distinguishes between complementary information and redundant information using similarities among the input images. The metric uses the information classification to estimate how much structural similarity is preserved in the fused image. Tests demonstrate that the metric correlates well with subjective evaluations of the fused images.
基金supported by the National Natural Science Foundation of China(Nos.61271361,61163019,61462093 and 61761046)the Research Foundation of Yunnan Province(Nos.2014FA021 and 2014FB113)the Digital Media Technology Key Laboratory of Universities in Yunnan Province
文摘A way of embedded learning convolution neural network(ELCNN) based on the image content is proposed to evaluate the image aesthetic quality in this paper. Our approach can not only solve the problem of small-scale data but also score the image aesthetic quality. First, we chose Alexnet and VGG_S to compare for confirming which is more suitable for this image aesthetic quality evaluation task. Second, to further boost the image aesthetic quality classification performance, we employ the image content to train aesthetic quality classification models. But the training samples become smaller and only using once fine-tuning cannot make full use of the small-scale data set. Third, to solve the problem in second step, a way of using twice fine-tuning continually based on the aesthetic quality label and content label respective is proposed, the classification probability of the trained CNN models is used to evaluate the image aesthetic quality. The experiments are carried on the small-scale data set of Photo Quality. The experiment results show that the classification accuracy rates of our approach are higher than the existing image aesthetic quality evaluation approaches.
基金This work was supported by National Natural Science Foundation of China(Nos.61831015 and 61901260)Key Research and Development Program of China(No.2019YFB1405902).
文摘Objective image quality assessment(IQA)plays an important role in various visual communication systems,which can automatically and efficiently predict the perceived quality of images.The human eye is the ultimate evaluator for visual experience,thus the modeling of human visual system(HVS)is a core issue for objective IQA and visual experience optimization.The traditional model based on black box fitting has low interpretability and it is difficult to guide the experience optimization effectively,while the model based on physiological simulation is hard to integrate into practical visual communication services due to its high computational complexity.For bridging the gap between signal distortion and visual experience,in this paper,we propose a novel perceptual no-reference(NR)IQA algorithm based on structural computational modeling of HVS.According to the mechanism of the human brain,we divide the visual signal processing into a low-level visual layer,a middle-level visual layer and a high-level visual layer,which conduct pixel information processing,primitive information processing and global image information processing,respectively.The natural scene statistics(NSS)based features,deep features and free-energy based features are extracted from these three layers.The support vector regression(SVR)is employed to aggregate features to the final quality prediction.Extensive experimental comparisons on three widely used benchmark IQA databases(LIVE,CSIQ and TID2013)demonstrate that our proposed metric is highly competitive with or outperforms the state-of-the-art NR IQA measures.
