A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes...A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.展开更多
A chromosome segment substitution line (CSSL) is a powerful tool for combining quantitative trait locus (QTL) mapping with the pyramiding of desirable alleles. The rice CSSL Z1364 with increased kernel number was iden...A chromosome segment substitution line (CSSL) is a powerful tool for combining quantitative trait locus (QTL) mapping with the pyramiding of desirable alleles. The rice CSSL Z1364 with increased kernel number was identified in a BC3F8 population derived from a cross of Nipponbare as the recipient with Xihui 18 as the donor parent. Z1364 carried three substitution segments distributed on chromosomes 1, 6, and 8. The mean substitution length was 1.19 Mb. Of 17 QTL identified on the substitution segments, qSP1 for spikelets per panicle, qSSD1 for seed-set density, and qNSB1 for number of secondary branches explained respectively 57.34%, 87.7%, and 49.44% of the corresponding phenotypic variance and were all linked to RM6777. Chi-square analysis showed that the increased kernel number in Z1364 was inherited recessively by a single gene. By fine mapping, qSP1 was delimited to a 50-kb region on the short arm of chromosome 1. Based on DNA sequence, a previously uncharacterized rice homolog of Arabidopsis thaliana AT4G32551 was identified as a candidate gene for qSP1 in which mutation increases the number of spikelets and kernels in Z1364. qSP1 was expressed in all tissues, but particularly in 1-cm panicles. The expression levels of OsMADS22, GN1A, and DST were upregulated and those of LAX2, GNP1, and GHD7 were downregulated in Nipponbare. These results provide a foundation for functional research on qSP1.展开更多
The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation...The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation.However,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs.Thus,the interpretability of CNNs has come into the spotlight.Since medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning method.Unfortunately,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these models.In this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac MRI.Our enhanced GPU training system implemented interpretable global average pooling for graphics using deep learning.The deep learning tasks were simplified.Simplification included data management,neural network architecture,and training.Our system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment model.Our results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning architectures.This model is lightweight and more convenient to deploy on mobile devices than transfer learning models.展开更多
Medical diagnosis software and computer-assisted surgical systems often use segmented image data to help clinicians make decisions. The segmentation extracts the region of interest from the background, which makes the...Medical diagnosis software and computer-assisted surgical systems often use segmented image data to help clinicians make decisions. The segmentation extracts the region of interest from the background, which makes the visualization clearer. However, no segmentation method can guarantee accurate results under all circumstances. As a result, the clinicians need a solution that enables them to check and validate the segmentation accuracy as well as displaying the segmented area without ambiguities. With the method presented in this paper, the real CT or MR image is displayed within the segmented region and the segmented boundaries can be expanded or contracted interactively. By this way, the clinicians are able to check and validate the segmentation visually and make more reliable decisions. After experiments with real data from a hospital, the presented method is proved to be suitable for efficiently detecting segmentation errors. The new algorithm uses new graphic processing uint （GPU） shading functions recently introduced in graphic cards and is fast enough to interact oil the segmented area, which was not possible with previous methods.展开更多
Due to the frequency of occlusion, cluttering and lowcontrast edges, gray intensity based active contour models oftenfail to segment meaningful objects. Prior shape information is usuallyutilized to segment desirable ...Due to the frequency of occlusion, cluttering and lowcontrast edges, gray intensity based active contour models oftenfail to segment meaningful objects. Prior shape information is usuallyutilized to segment desirable objects. A parametric shape priormodel is proposed. Firstly, principal component analysis is employedto train object shape and transformation is added to shaperepresentation. Then the energy function is constructed througha combination of shape prior energy, gray intensity energy andshape constraint energy of the kernel density function. The objectboundary extraction process is converted into the parameters solvingprocess of object shape. Besides, two new shape prior energyfunctions are defined when desirable objects are occluded by otherobjects or some parts of them are missing. Finally, an alternatingdecent iteration solving scheme is proposed for numerical implementation.Experiments on synthetic and real images demonstratethe robustness and accuracy of the proposed method.展开更多
In this paper,we consider the Chan–Vese(C-V)model for image segmentation and obtain its numerical solution accurately and efficiently.For this purpose,we present a local radial basis function method based on a Gaussi...In this paper,we consider the Chan–Vese(C-V)model for image segmentation and obtain its numerical solution accurately and efficiently.For this purpose,we present a local radial basis function method based on a Gaussian kernel(GA-LRBF)for spatial discretization.Compared to the standard radial basis functionmethod,this approach consumes less CPU time and maintains good stability because it uses only a small subset of points in the whole computational domain.Additionally,since the Gaussian function has the property of dimensional separation,the GA-LRBF method is suitable for dealing with isotropic images.Finally,a numerical scheme that couples GA-LRBF with the fourth-order Runge–Kutta method is applied to the C-V model,and a comparison of some numerical results demonstrates that this scheme achieves much more reliable image segmentation.展开更多
The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape infor...The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape information. We propose a fully automatic brain tumor segmentation method based on kernel sparse coding. It is validated with 3D multiple-modality magnetic resonance imaging(MRI). In this method, MRI images are pre-processed first to reduce the noise, and then kernel dictionary learning is used to extract the nonlinear features to construct five adaptive dictionaries for healthy tissues, necrosis, edema, non-enhancing tumor, and enhancing tumor tissues. Sparse coding is performed on the feature vectors extracted from the original MRI images, which are a patch of m×m×m around the voxel. A kernel-clustering algorithm based on dictionary learning is developed to code the voxels. In the end, morphological filtering is used to fill in the area among multiple connected components to improve the segmentation quality. To assess the segmentation performance, the segmentation results are uploaded to the online evaluation system where the evaluation metrics dice score, positive predictive value(PPV), sensitivity, and kappa are used. The results demonstrate that the proposed method has good performance on the complete tumor region(dice: 0.83; PPV: 0.84; sensitivity: 0.82), while slightly worse performance on the tumor core(dice: 0.69; PPV: 0.76; sensitivity: 0.80) and enhancing tumor(dice: 0.58; PPV: 0.60; sensitivity: 0.65). It is competitive to the other groups in the brain tumor segmentation challenge. Therefore, it is a potential method in differentiation of healthy and pathological tissues.展开更多
We propose a novel clustering algorithm using fast global kernel fuzzy c-means-F(FGKFCM-F), where F refers to kernelized feature space. This algorithm proceeds in an incremental way to derive the near-optimal solution...We propose a novel clustering algorithm using fast global kernel fuzzy c-means-F(FGKFCM-F), where F refers to kernelized feature space. This algorithm proceeds in an incremental way to derive the near-optimal solution by solving all intermediate problems using kernel-based fuzzy c-means-F(KFCM-F) as a local search procedure. Due to the incremental nature and the nonlinear properties inherited from KFCM-F, this algorithm overcomes the two shortcomings of fuzzy c-means(FCM): sen- sitivity to initialization and inability to use nonlinear separable data. An accelerating scheme is developed to reduce the compu-tational complexity without significantly affecting the solution quality. Experiments are carried out to test the proposed algorithm on a nonlinear artificial dataset and a real-world dataset of speech signals for consonant/vowel segmentation. Simulation results demonstrate the effectiveness of the proposed algorithm in improving clustering performance on both types of datasets.展开更多
It remains a challenging task to segment images that are distorted by noise and intensity inhomogeneity.To overcome these problems, in this paper, we present a novel region-based active contour model based on local in...It remains a challenging task to segment images that are distorted by noise and intensity inhomogeneity.To overcome these problems, in this paper, we present a novel region-based active contour model based on local intensity information and a kernel metric. By introducing intensity information about the local region, the proposed model can accurately segment images with intensity inhomogeneity. To enhance the model＇s robustness to noise and outliers, we introduce a kernel metric as its objective functional. To more accurately detect boundaries, we apply convex optimization to this new model, which uses a weighted total-variation norm given by an edge indicator function. Lastly, we use the split Bregman iteration method to obtain the numerical solution. We conducted an extensive series of experiments on both synthetic and real images to evaluate our proposed method, and the results demonstrate significant improvements in terms of efficiency and accuracy, compared with the performance of currently popular methods.展开更多
Rice kernel shape affects kernel quality(appearance) and yield(1000-kernel weight) and therefore is an important agronomic trait, but its inheritance is complicated. We identified a long-kernel rice chromosome segment...Rice kernel shape affects kernel quality(appearance) and yield(1000-kernel weight) and therefore is an important agronomic trait, but its inheritance is complicated. We identified a long-kernel rice chromosome segment substitution line(CSSL), Z741, derived from Nipponbare as a recipient and Xihui 18 as a donor parent. Z741 has six substitution segments distributed on rice chromosomes 3, 6, 7, 8 and 12 with an average replacement length of 5.82 Mb. Analysis of a secondary F2 population from a cross between Nipponbare and Z741 identified 20 QTLs for important agronomic traits. The kernel length of Z741 is controlled by a major QTL(qKL3) and a minor QTL(qKL7). Candidate gene prediction and sequencing indicated that qKL3 may be an allele of OsPPKL1, which encodes a protein phosphatase implicated in brassinosteroid signaling, and qKL7 is an unreported QTL. Finally, we validated eight QTLs(qKL3, qKL7, qRLW3-1, qRLW7, qPH3-1, qKWT3, qKWT7 and qNPB6) using three selected singlesegment substitution lines(SSSLs), S1, S2 and S3. Also, we detected five QTLs(qKL6, qKW3, qKW7, qKW6 and qRLW6) in S1, S2 and S3, which were not found in the Nipponbare/Z741 F2 population. However, qNPB3, qNPB7 and qPL3 QTLs were not validated by the three SSSLs in 2019, suggesting that minor QTLs are susceptible to environmental factors. These results lay the foundation for studying the biodiversity of kernal length and molecular breeding of different kernel types.展开更多
Efficient parameterization of point-sampled surfaces is a fundamental problem in the field of digital geometry processing. In order to parameterize a given point-sampled surface for minimal distance distortion, a diff...Efficient parameterization of point-sampled surfaces is a fundamental problem in the field of digital geometry processing. In order to parameterize a given point-sampled surface for minimal distance distortion, a differentialslbased segmentation and parameterization approach is proposed in this paper. Our approach partitions the point-sampled geometry based on two criteria： variation of Euclidean distance between sample points, and angular difference between surface differential directions. According to the analysis of normal curvatures for some specified directions, a new projection approach is adopted to estimate the local surface differentials. Then a k-means clustering （k-MC） algorithm is used for partitioning the model into a set of charts based on the estimated local surface attributes. Finally, each chart is parameterized with a statistical method -- multidimensional scaling （MDS） approach, and the parameterization results of all charts form an atlas for compact storage.展开更多
Polyurethane (PU) was prepared from palm kernel oil-based monoester polyol (PKO-p) via prepolymerization method at NCO/OH ratio of 200/100, 150/100, 100/100, and 75/100 at ambient temperature under nitrogen gas atmosp...Polyurethane (PU) was prepared from palm kernel oil-based monoester polyol (PKO-p) via prepolymerization method at NCO/OH ratio of 200/100, 150/100, 100/100, and 75/100 at ambient temperature under nitrogen gas atmosphere. The structure of the synthesized prepolymerized PKO-p PU was determined using FTIR and 13C NMR. The disapperance of NCO peak in the FTIR spectrum at 2270 cm–1 - 2250 cm–1 cm showed that MDI has completely reacted to form PU. The appearance of C=O peak at 1700 cm–1 indicated that hydrogen bonding was formed between the soft segmented chain of the PKO-p and the hard segmented MDI. Hence, urethane bond was the main polymeric chain in the PU.展开更多
Determination of an age in a particular tree species can be considered as a vital factor in forest management.In this research we have introduced a novel scheme to determine the accurate age of the tree species in Sri...Determination of an age in a particular tree species can be considered as a vital factor in forest management.In this research we have introduced a novel scheme to determine the accurate age of the tree species in Sri Lanka.This is initially developed for the tree species called‘Hora’(Dipterocarpus zeylanicus)in wet zone of Sri Lanka.Here the core samples are extracted and further analyzed by means of the different image processing techniques such as Gaussian kernel blurring,use of Sobel filters,double threshold analysis,Hough line tran sformation and etc.The operations such as rescaling,slicing and measuring are also used in line with image processing techniques to achieve the desired results.Ultimately a Graphical user interface(GUI)is developed to cater for the user requirements in a user friendly environment.It has been found that the average growth ring identification accuracy of the proposed system is 93%and the overall average accuracy of detecting the age is 81%.Ultimately the proposed system will provide an insight and contributes to the forestry related activities and researches in Sri Lanka.展开更多
Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the ana...Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the analysis and interpretation of hyperspectral images a challenge.Feature extraction is a very important step for hyperspectral image processing.Feature extraction methods aim at reducing the dimension of data,while preserving as much information as possible.Particularly,nonlinear feature extraction methods (e.g.kernel minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing,due to their good preservation of high-order structures of the original data.However,conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction,and this leads to poor performances for post-applications.This paper proposes a novel nonlinear feature extraction method for hyperspectral images.Instead of estimating noise fraction by the nearest neighborhood information (within a sliding window),the proposed method explores the use of image segmentation.The approach benefits both noise fraction estimation and information preservation,and enables a significant improvement for classification.Experimental results on two real hyperspectral images demonstrate the efficiency of the proposed method.Compared to conventional KMNF,the improvements of the method on two hyperspectral image classification are 8 and 11％.This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required.展开更多
基金supported by National Natural Science Foundation of China[grant numbers 61573233]Natural Science Foundation of Guangdong,China[grant numbers 2021A1515010661]+1 种基金Special projects in key fields of colleges and universities in Guangdong Province[grant numbers 2020ZDZX2005]Innovation Team Project of University in Guangdong Province[grant numbers 2015KCXTD018].
文摘A fast image segmentation algorithm based on salient features model and spatial-frequency domain adaptive kernel is proposed to solve the accurate discriminate objects problem of online visual detection in such scenes of variable sample morphological characteristics,low contrast and complex background texture.Firstly,by analyzing the spectral component distribution and spatial contour feature of the image,a salient feature model is established in spatial-frequency domain.Then,the salient object detection method based on Gaussian band-pass filter and the design criterion of adaptive convolution kernel are proposed to extract the salient contour feature of the target in spatial and frequency domain.Finally,the selection and growth rules of seed points are improved by integrating the gray level and contour features of the target,and the target is segmented by seeded region growing.Experiments have been performed on Berkeley Segmentation Data Set,as well as sample images of online detection,to verify the effectiveness of the algorithm.The experimental results show that the Jaccard Similarity Coefficient of the segmentation is more than 90%,which indicates that the proposed algorithm can availably extract the target feature information,suppress the background texture and resist noise interference.Besides,the Hausdorff Distance of the segmentation is less than 10,which infers that the proposed algorithm obtains a high evaluation on the target contour preservation.The experimental results also show that the proposed algorithm significantly improves the operation efficiency while obtaining comparable segmentation performance over other algorithms.
基金supported by the National Key Research Plan Project (2017YFD0101107)the Chongqing Science and Technology Commission Special Project (cstc2016shmsztzx0032)the Southwest University Innovation Team Project (XDJK2017A004)
文摘A chromosome segment substitution line (CSSL) is a powerful tool for combining quantitative trait locus (QTL) mapping with the pyramiding of desirable alleles. The rice CSSL Z1364 with increased kernel number was identified in a BC3F8 population derived from a cross of Nipponbare as the recipient with Xihui 18 as the donor parent. Z1364 carried three substitution segments distributed on chromosomes 1, 6, and 8. The mean substitution length was 1.19 Mb. Of 17 QTL identified on the substitution segments, qSP1 for spikelets per panicle, qSSD1 for seed-set density, and qNSB1 for number of secondary branches explained respectively 57.34%, 87.7%, and 49.44% of the corresponding phenotypic variance and were all linked to RM6777. Chi-square analysis showed that the increased kernel number in Z1364 was inherited recessively by a single gene. By fine mapping, qSP1 was delimited to a 50-kb region on the short arm of chromosome 1. Based on DNA sequence, a previously uncharacterized rice homolog of Arabidopsis thaliana AT4G32551 was identified as a candidate gene for qSP1 in which mutation increases the number of spikelets and kernels in Z1364. qSP1 was expressed in all tissues, but particularly in 1-cm panicles. The expression levels of OsMADS22, GN1A, and DST were upregulated and those of LAX2, GNP1, and GHD7 were downregulated in Nipponbare. These results provide a foundation for functional research on qSP1.
基金The National Natural Science Foundation of China (62176048)provided funding for this research.
文摘The interpretability of deep learning models has emerged as a compelling area in artificial intelligence research.The safety criteria for medical imaging are highly stringent,and models are required for an explanation.However,existing convolutional neural network solutions for left ventricular segmentation are viewed in terms of inputs and outputs.Thus,the interpretability of CNNs has come into the spotlight.Since medical imaging data are limited,many methods to fine-tune medical imaging models that are popular in transfer models have been built using massive public Image Net datasets by the transfer learning method.Unfortunately,this generates many unreliable parameters and makes it difficult to generate plausible explanations from these models.In this study,we trained from scratch rather than relying on transfer learning,creating a novel interpretable approach for autonomously segmenting the left ventricle with a cardiac MRI.Our enhanced GPU training system implemented interpretable global average pooling for graphics using deep learning.The deep learning tasks were simplified.Simplification included data management,neural network architecture,and training.Our system monitored and analyzed the gradient changes of different layers with dynamic visualizations in real-time and selected the optimal deployment model.Our results demonstrated that the proposed method was feasible and efficient:the Dice coefficient reached 94.48%,and the accuracy reached 99.7%.It was found that no current transfer learning models could perform comparably to the ImageNet transfer learning architectures.This model is lightweight and more convenient to deploy on mobile devices than transfer learning models.
基金Project supported by the National Natural Science Foundation of China （Grant No.60572154）, and the National Basic Research Program of China （Grant No.2003CB716104）Acknowledgment I would like to thank YANG Xin, my tutor, SHANG Yan- feng, SUN Kun of Shanghai Children＇s Medical Center, and all the people in 3D Visualization Laboratory of Shanghai Jiaotong University for their help during my research.
文摘Medical diagnosis software and computer-assisted surgical systems often use segmented image data to help clinicians make decisions. The segmentation extracts the region of interest from the background, which makes the visualization clearer. However, no segmentation method can guarantee accurate results under all circumstances. As a result, the clinicians need a solution that enables them to check and validate the segmentation accuracy as well as displaying the segmented area without ambiguities. With the method presented in this paper, the real CT or MR image is displayed within the segmented region and the segmented boundaries can be expanded or contracted interactively. By this way, the clinicians are able to check and validate the segmentation visually and make more reliable decisions. After experiments with real data from a hospital, the presented method is proved to be suitable for efficiently detecting segmentation errors. The new algorithm uses new graphic processing uint （GPU） shading functions recently introduced in graphic cards and is fast enough to interact oil the segmented area, which was not possible with previous methods.
基金supported by the National Natural Science Foundation of China(6137214261571005U1401252)
文摘Due to the frequency of occlusion, cluttering and lowcontrast edges, gray intensity based active contour models oftenfail to segment meaningful objects. Prior shape information is usuallyutilized to segment desirable objects. A parametric shape priormodel is proposed. Firstly, principal component analysis is employedto train object shape and transformation is added to shaperepresentation. Then the energy function is constructed througha combination of shape prior energy, gray intensity energy andshape constraint energy of the kernel density function. The objectboundary extraction process is converted into the parameters solvingprocess of object shape. Besides, two new shape prior energyfunctions are defined when desirable objects are occluded by otherobjects or some parts of them are missing. Finally, an alternatingdecent iteration solving scheme is proposed for numerical implementation.Experiments on synthetic and real images demonstratethe robustness and accuracy of the proposed method.
基金sponsored by Guangdong Basic and Applied Basic Research Foundation under Grant No.2021A1515110680Guangzhou Basic and Applied Basic Research under Grant No.202102020340.
文摘In this paper,we consider the Chan–Vese(C-V)model for image segmentation and obtain its numerical solution accurately and efficiently.For this purpose,we present a local radial basis function method based on a Gaussian kernel(GA-LRBF)for spatial discretization.Compared to the standard radial basis functionmethod,this approach consumes less CPU time and maintains good stability because it uses only a small subset of points in the whole computational domain.Additionally,since the Gaussian function has the property of dimensional separation,the GA-LRBF method is suitable for dealing with isotropic images.Finally,a numerical scheme that couples GA-LRBF with the fourth-order Runge–Kutta method is applied to the C-V model,and a comparison of some numerical results demonstrates that this scheme achieves much more reliable image segmentation.
基金Project supported by the National Natural Science Foundation of China(No.31200746)the Zhejiang Provincial Key Research and Development Plan,China(No.2015C03023)the‘521’Talent Project of ZSTU,China
文摘The segmentation of brain tumor plays an important role in diagnosis, treatment planning, and surgical simulation. The precise segmentation of brain tumor can help clinicians obtain its location, size, and shape information. We propose a fully automatic brain tumor segmentation method based on kernel sparse coding. It is validated with 3D multiple-modality magnetic resonance imaging(MRI). In this method, MRI images are pre-processed first to reduce the noise, and then kernel dictionary learning is used to extract the nonlinear features to construct five adaptive dictionaries for healthy tissues, necrosis, edema, non-enhancing tumor, and enhancing tumor tissues. Sparse coding is performed on the feature vectors extracted from the original MRI images, which are a patch of m×m×m around the voxel. A kernel-clustering algorithm based on dictionary learning is developed to code the voxels. In the end, morphological filtering is used to fill in the area among multiple connected components to improve the segmentation quality. To assess the segmentation performance, the segmentation results are uploaded to the online evaluation system where the evaluation metrics dice score, positive predictive value(PPV), sensitivity, and kappa are used. The results demonstrate that the proposed method has good performance on the complete tumor region(dice: 0.83; PPV: 0.84; sensitivity: 0.82), while slightly worse performance on the tumor core(dice: 0.69; PPV: 0.76; sensitivity: 0.80) and enhancing tumor(dice: 0.58; PPV: 0.60; sensitivity: 0.65). It is competitive to the other groups in the brain tumor segmentation challenge. Therefore, it is a potential method in differentiation of healthy and pathological tissues.
基金Project supported by the National Research Foundation(NRF) of Korea(Nos.2013009458 and 2013068127)
文摘We propose a novel clustering algorithm using fast global kernel fuzzy c-means-F(FGKFCM-F), where F refers to kernelized feature space. This algorithm proceeds in an incremental way to derive the near-optimal solution by solving all intermediate problems using kernel-based fuzzy c-means-F(KFCM-F) as a local search procedure. Due to the incremental nature and the nonlinear properties inherited from KFCM-F, this algorithm overcomes the two shortcomings of fuzzy c-means(FCM): sen- sitivity to initialization and inability to use nonlinear separable data. An accelerating scheme is developed to reduce the compu-tational complexity without significantly affecting the solution quality. Experiments are carried out to test the proposed algorithm on a nonlinear artificial dataset and a real-world dataset of speech signals for consonant/vowel segmentation. Simulation results demonstrate the effectiveness of the proposed algorithm in improving clustering performance on both types of datasets.
基金supported by the National Natural Science Foundation of China(No.61472270)
文摘It remains a challenging task to segment images that are distorted by noise and intensity inhomogeneity.To overcome these problems, in this paper, we present a novel region-based active contour model based on local intensity information and a kernel metric. By introducing intensity information about the local region, the proposed model can accurately segment images with intensity inhomogeneity. To enhance the model＇s robustness to noise and outliers, we introduce a kernel metric as its objective functional. To more accurately detect boundaries, we apply convex optimization to this new model, which uses a weighted total-variation norm given by an edge indicator function. Lastly, we use the split Bregman iteration method to obtain the numerical solution. We conducted an extensive series of experiments on both synthetic and real images to evaluate our proposed method, and the results demonstrate significant improvements in terms of efficiency and accuracy, compared with the performance of currently popular methods.
基金supported by the National Key Research Plan Project of China(Grant No.2017YFD0101107)Chongqing Technical Innovation and Application Development Project(Grant No.cstc2019jscx-msxmX0392)。
文摘Rice kernel shape affects kernel quality(appearance) and yield(1000-kernel weight) and therefore is an important agronomic trait, but its inheritance is complicated. We identified a long-kernel rice chromosome segment substitution line(CSSL), Z741, derived from Nipponbare as a recipient and Xihui 18 as a donor parent. Z741 has six substitution segments distributed on rice chromosomes 3, 6, 7, 8 and 12 with an average replacement length of 5.82 Mb. Analysis of a secondary F2 population from a cross between Nipponbare and Z741 identified 20 QTLs for important agronomic traits. The kernel length of Z741 is controlled by a major QTL(qKL3) and a minor QTL(qKL7). Candidate gene prediction and sequencing indicated that qKL3 may be an allele of OsPPKL1, which encodes a protein phosphatase implicated in brassinosteroid signaling, and qKL7 is an unreported QTL. Finally, we validated eight QTLs(qKL3, qKL7, qRLW3-1, qRLW7, qPH3-1, qKWT3, qKWT7 and qNPB6) using three selected singlesegment substitution lines(SSSLs), S1, S2 and S3. Also, we detected five QTLs(qKL6, qKW3, qKW7, qKW6 and qRLW6) in S1, S2 and S3, which were not found in the Nipponbare/Z741 F2 population. However, qNPB3, qNPB7 and qPL3 QTLs were not validated by the three SSSLs in 2019, suggesting that minor QTLs are susceptible to environmental factors. These results lay the foundation for studying the biodiversity of kernal length and molecular breeding of different kernel types.
基金This work is supported by the National Grand Fundamental Research 973 Program of China under Grant No.2002CB312101National Natural Science Foundation of China(NSFC)under Grant Nos. 60503056,60333010the Natural Science Foundation of Zhejiang Province under Grant No.R106449.
文摘Efficient parameterization of point-sampled surfaces is a fundamental problem in the field of digital geometry processing. In order to parameterize a given point-sampled surface for minimal distance distortion, a differentialslbased segmentation and parameterization approach is proposed in this paper. Our approach partitions the point-sampled geometry based on two criteria： variation of Euclidean distance between sample points, and angular difference between surface differential directions. According to the analysis of normal curvatures for some specified directions, a new projection approach is adopted to estimate the local surface differentials. Then a k-means clustering （k-MC） algorithm is used for partitioning the model into a set of charts based on the estimated local surface attributes. Finally, each chart is parameterized with a statistical method -- multidimensional scaling （MDS） approach, and the parameterization results of all charts form an atlas for compact storage.
文摘Polyurethane (PU) was prepared from palm kernel oil-based monoester polyol (PKO-p) via prepolymerization method at NCO/OH ratio of 200/100, 150/100, 100/100, and 75/100 at ambient temperature under nitrogen gas atmosphere. The structure of the synthesized prepolymerized PKO-p PU was determined using FTIR and 13C NMR. The disapperance of NCO peak in the FTIR spectrum at 2270 cm–1 - 2250 cm–1 cm showed that MDI has completely reacted to form PU. The appearance of C=O peak at 1700 cm–1 indicated that hydrogen bonding was formed between the soft segmented chain of the PKO-p and the hard segmented MDI. Hence, urethane bond was the main polymeric chain in the PU.
基金Supported by National Natural Science Foundation of China(60675039)National High Technology Research and Development Program of China(863 Program)(2006AA04Z217)Hundred Talents Program of Chinese Academy of Sciences
文摘Determination of an age in a particular tree species can be considered as a vital factor in forest management.In this research we have introduced a novel scheme to determine the accurate age of the tree species in Sri Lanka.This is initially developed for the tree species called‘Hora’(Dipterocarpus zeylanicus)in wet zone of Sri Lanka.Here the core samples are extracted and further analyzed by means of the different image processing techniques such as Gaussian kernel blurring,use of Sobel filters,double threshold analysis,Hough line tran sformation and etc.The operations such as rescaling,slicing and measuring are also used in line with image processing techniques to achieve the desired results.Ultimately a Graphical user interface(GUI)is developed to cater for the user requirements in a user friendly environment.It has been found that the average growth ring identification accuracy of the proposed system is 93%and the overall average accuracy of detecting the age is 81%.Ultimately the proposed system will provide an insight and contributes to the forestry related activities and researches in Sri Lanka.
基金the National Natural Science Foundation of China [Grant Number 41722108],(Grant Number 91638201)%FWO project:data fusion for image analysis in remote sensing(Grant Number G037115N)
文摘Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the analysis and interpretation of hyperspectral images a challenge.Feature extraction is a very important step for hyperspectral image processing.Feature extraction methods aim at reducing the dimension of data,while preserving as much information as possible.Particularly,nonlinear feature extraction methods (e.g.kernel minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing,due to their good preservation of high-order structures of the original data.However,conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction,and this leads to poor performances for post-applications.This paper proposes a novel nonlinear feature extraction method for hyperspectral images.Instead of estimating noise fraction by the nearest neighborhood information (within a sliding window),the proposed method explores the use of image segmentation.The approach benefits both noise fraction estimation and information preservation,and enables a significant improvement for classification.Experimental results on two real hyperspectral images demonstrate the efficiency of the proposed method.Compared to conventional KMNF,the improvements of the method on two hyperspectral image classification are 8 and 11％.This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required.
