Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all d...Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all day and weather unattended bird monitoring becomes possible.However,the current mainstream bird recognition methods are mostly based on deep learning.These will be appropriate for big data applications,but the training sample size for rare bird is usually very short.Therefore,this paper presents a new sparse recognition model via improved part detection and our previous dictionary learning.There are two achievements in our work:(1)after the part localization with selective search,the gist feature of all bird image parts will be fused as data description;(2)the fused gist feature needs to be learned through our proposed intraclass dictionary learning with regularized K-singular value decomposition.According to above two innovations,the rare bird sparse recognition will be implemented by solving one l1-norm optimization.In the experiment with Caltech-UCSD Birds-200-2011 dataset,results show the proposed method can have better recognition performance than other SR methods for rare bird task with small sample size.展开更多
The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This ...The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This paper investigates impulsive signals detection of a single-point defect rolling bearing and presents a novel data-driven detection approach based on dictionary learning.To overcome the effects harmonic and noise components,we propose an autoregressive-minimum entropy deconvolution model to separate harmonic and deconvolve the effect of the transmission path.To address the shortcomings of conventional sparse representation under the changeable operation environment,we propose an approach that combines K-clustering with singular value decomposition(K-SVD)and split-Bregman to extract impulsive components precisely.Via experiments on synthetic signals and real run-to-failure signals,the excellent performance for different impulsive signals detection verifies the effectiveness and robustness of the proposed approach.Meanwhile,a comparison with the state-of-the-art methods is illustrated,which shows that the proposed approach can provide more accurate detected impulsive signals.展开更多
Dictionary learning has been applied to face recognition and gets good results. However few works applied dictionary learning in facial expression recognition. This paper investigates the application of K-SVD in facia...Dictionary learning has been applied to face recognition and gets good results. However few works applied dictionary learning in facial expression recognition. This paper investigates the application of K-SVD in facial expression recognition. Since K-SVD focuses on reconstruction and lacks discriminant capability. It has similar classification performance with image pixel values. To address this problem, this paper proposes a Combined Dictionary Scheme, which uses combination of separate dictionaries. This yields better performance than the original single dictionary scheme in terms of both recognition rate and computation complexity.展开更多
In this paper, a two-level Bregman method is presented with graph regularized sparse coding for highly undersampled magnetic resonance image reconstruction. The graph regularized sparse coding is incorporated with the...In this paper, a two-level Bregman method is presented with graph regularized sparse coding for highly undersampled magnetic resonance image reconstruction. The graph regularized sparse coding is incorporated with the two-level Bregman iterative procedure which enforces the sampled data constraints in the outer level and updates dictionary and sparse representation in the inner level. Graph regularized sparse coding and simple dictionary updating applied in the inner minimization make the proposed algorithm converge with a relatively small number of iterations. Experimental results demonstrate that the proposed algorithm can consistently reconstruct both simulated MR images and real MR data efficiently, and outperforms the current state-of-the-art approaches in terms of visual comparisons and quantitative measures.展开更多
Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In t...Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection results.In order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.展开更多
Electrical capacitance tomography(ECT)has great application potential inmultiphase processmonitoring,and its visualization results are of great significance for studying the changes in two-phase flow in closed environ...Electrical capacitance tomography(ECT)has great application potential inmultiphase processmonitoring,and its visualization results are of great significance for studying the changes in two-phase flow in closed environments.In this paper,compressed sensing(CS)theory based on dictionary learning is introduced to the inverse problem of ECT,and the K-SVD algorithm is used to learn the overcomplete dictionary to establish a nonlinear mapping between observed capacitance and sparse space.Because the trained overcomplete dictionary has the property to match few features of interest in the reconstructed image of ECT,it is not necessary to rely on the sparsity of coefficient vector to solve the nonlinear mapping as most algorithms based on CS theory.Two-phase flow distribution in a cylindrical pipe was modeled and simulated,and three variations without sparse constraint based on Landweber,Tikhonov,and Newton-Raphson algorithms were used to rapidly reconstruct a 2-D image.展开更多
Sparse representation is a mathematical model for data representation that has proved to be a powerful tool for solving problems in various fields such as pattern recognition, machine learning, and computer vision. As...Sparse representation is a mathematical model for data representation that has proved to be a powerful tool for solving problems in various fields such as pattern recognition, machine learning, and computer vision. As one of the building blocks of the sparse representation method, dictionary learning plays an important role in the minimization of the reconstruction error between the original signal and its sparse representation in the space of the learned dictionary. Although using training samples directly as dictionary bases can achieve good performance, the main drawback of this method is that it may result in a very large and inef- ficient dictionary due to noisy training instances. To obtain a smaller and more representative dictionary, in this paper, we propose an approach called Laplacian sparse dictionary （LSD） learning. Our method is based on manifold learning and double sparsity. We incorporate the Laplacian weighted graph in the sparse representation model and impose the 11-norm sparsity on the dictionary. An LSD is a sparse overcomplete dictionary that can preserve the intrinsic structure of the data and learn a smaller dictionary for each class. The learned LSD can be easily integrated into a classification framework based on sparse representation. We compare the proposed method with other methods using three benchmark-controlled face image databases, Extended Yale B, ORL, and AR, and one uncontrolled person image dataset, i-LIDS-MA. Results show the advantages of the proposed LSD algorithm over state-of-the-art sparse representation based classification methods.展开更多
In recent years,there has been a growing usage of sparse representations in signal processing.This paper revisits theK-SVD,an algorithm for designing overcomplete dictionaries for sparse and redundant representations....In recent years,there has been a growing usage of sparse representations in signal processing.This paper revisits theK-SVD,an algorithm for designing overcomplete dictionaries for sparse and redundant representations.We present a newapproach to solve dictionary learning models by combining the alternating direction method of multipliers and the orthogonal matching pursuit.The experimental results show that our approach can reliably obtain better learned dictionary elements and outperform other algorithms.展开更多
目的现实中采集到的人脸图像通常受到光照、遮挡等环境因素的影响,使得同一类的人脸图像具有不同程度的差异性,不同类的人脸图像又具有不同程度的相似性,这极大地影响了人脸识别的准确性。为了解决上述问题对人脸识别造成的影响,在低秩...目的现实中采集到的人脸图像通常受到光照、遮挡等环境因素的影响,使得同一类的人脸图像具有不同程度的差异性,不同类的人脸图像又具有不同程度的相似性,这极大地影响了人脸识别的准确性。为了解决上述问题对人脸识别造成的影响,在低秩矩阵恢复理论的基础上提出了具有识别力的结构化低秩字典学习的人脸识别算法。方法该算法基于训练样本的标签信息将低秩正则化以及结构化稀疏同时引入到学习的具有识别力的字典上。在字典学习过程中,首先利用样本的重建误差约束样本与字典之间的关系;其次将Fisher准则应用到稀疏编码过程中,使其编码系数具有识别能力;由于训练样本中的噪声信息会影响字典的识别力,所以在低秩矩阵恢复理论的基础上将低秩正则化应用到字典学习过程中;接着,在字典学习过程中加入了结构化稀疏使其不丢失结构信息以保证对样本进行最优分类;最后再利用误差重构法对测试样本进行分类识别。结果本文算法在AR以及ORL人脸数据库上分别进行了实验仿真。在AR人脸数据库中,为了分析样本不同维数对实验结果造成的影响,选取了第一时期拍摄的每人6幅图像,包括1幅围巾遮挡,2幅墨镜遮挡以及3幅脸部表情变化以及光照变化(未被遮挡)的图像作为训练样本,同时选取相同组合的样本图像作为测试样本,无论哪种方法,图像的维度越高识别率越高。对比SRC(sparse representation based on classification)算法与DKSVD(discriminative K-means singular value decomposition)算法的识别率可知,DKSVD算法通过字典学习减缓了训练样本中的不确定因素对识别结果的影响;对比DLRD_SR(discriminative low-rank dictionary learning for sparse representation)算法与FDDL(Fisher discriminative dictionary learning)算法的识别率可知,当图像有遮挡等噪声信息存在时,字典低秩化可以提高至少5.8%的识别率;对比本文算法与DLRD_SR算法可知,在字典学习的过程中加入Fisher准则后识别率显著提高,同时理想稀疏值能保证对样本进行最优的分类。当样本图像的维度达到500维时人脸图像在有围巾、墨镜遮挡的情况下识别率可达到85.2%;其中墨镜和围巾的遮挡程度分别可以看成是人脸图像的20%和40%,为了验证本文算法在不同脸部表情变化、光照改变以及遮挡情况下的有效性,根据训练样本的具体图像组合情况进行实验。无论哪种样本图像组合,本文算法在有遮挡存在的样本识别中具有显著优势。在训练样本只包含脸部表情变化、光照变化以及墨镜遮挡图像的情况下,本文算法的识别率高于其他算法至少2.7%,在训练样本只包含脸部表情变化、光照变化以及围巾遮挡图像的情况下,本文算法的识别率高于其他算法至少3.6%,在训练样本包含脸部表情变化、光照变化、围巾遮挡以及墨镜遮挡图像的情况下,其识别率高于其他算法至少1.9%。在ORL人脸数据库中,人脸图像在无遮挡的情况下识别率达到95.2%,稍低于FDDL算法的识别率;在随机块遮挡程度达到20%时,相比较于SRC算法、DKSVD算法、FDDL算法以及DLRD_SR算法,本文算法的识别率最高;当随机块遮挡程度达到50%时,以上算法的识别率均不高,但本文算法的其识别率仍然最高。结论本文算法在人脸图像受到遮挡等因素的影响时具有一定的鲁棒性,实验结果表明该算法在人脸识别方面具有可行性。展开更多
文摘Rare bird has long been considered an important in the field of airport security,biological conservation,environmental monitoring,and so on.With the development and popularization of IOT-based video surveillance,all day and weather unattended bird monitoring becomes possible.However,the current mainstream bird recognition methods are mostly based on deep learning.These will be appropriate for big data applications,but the training sample size for rare bird is usually very short.Therefore,this paper presents a new sparse recognition model via improved part detection and our previous dictionary learning.There are two achievements in our work:(1)after the part localization with selective search,the gist feature of all bird image parts will be fused as data description;(2)the fused gist feature needs to be learned through our proposed intraclass dictionary learning with regularized K-singular value decomposition.According to above two innovations,the rare bird sparse recognition will be implemented by solving one l1-norm optimization.In the experiment with Caltech-UCSD Birds-200-2011 dataset,results show the proposed method can have better recognition performance than other SR methods for rare bird task with small sample size.
基金This work was supported by the National Natural Science Foundation of China(61773080,61633005)the Fundamental Research Funds for the Central Universities(2019CDYGZD001)Scientific Reserve Talent Programs of Chongqing University(cqu2018CDHB1B04).
文摘The localized faults of rolling bearings can be diagnosed by its vibration impulsive signals.However,it is always a challenge to extract the impulsive feature under background noise and non-stationary conditions.This paper investigates impulsive signals detection of a single-point defect rolling bearing and presents a novel data-driven detection approach based on dictionary learning.To overcome the effects harmonic and noise components,we propose an autoregressive-minimum entropy deconvolution model to separate harmonic and deconvolve the effect of the transmission path.To address the shortcomings of conventional sparse representation under the changeable operation environment,we propose an approach that combines K-clustering with singular value decomposition(K-SVD)and split-Bregman to extract impulsive components precisely.Via experiments on synthetic signals and real run-to-failure signals,the excellent performance for different impulsive signals detection verifies the effectiveness and robustness of the proposed approach.Meanwhile,a comparison with the state-of-the-art methods is illustrated,which shows that the proposed approach can provide more accurate detected impulsive signals.
文摘Dictionary learning has been applied to face recognition and gets good results. However few works applied dictionary learning in facial expression recognition. This paper investigates the application of K-SVD in facial expression recognition. Since K-SVD focuses on reconstruction and lacks discriminant capability. It has similar classification performance with image pixel values. To address this problem, this paper proposes a Combined Dictionary Scheme, which uses combination of separate dictionaries. This yields better performance than the original single dictionary scheme in terms of both recognition rate and computation complexity.
基金Supported by the National Natural Science Foundation of China(No.61261010No.61362001+7 种基金No.61365013No.61262084No.51165033)Technology Foundation of Department of Education in Jiangxi Province(GJJ13061GJJ14196)Young Scientists Training Plan of Jiangxi Province(No.20133ACB21007No.20142BCB23001)National Post-Doctoral Research Fund(No.2014M551867)and Jiangxi Advanced Project for Post-Doctoral Research Fund(No.2014KY02)
文摘In this paper, a two-level Bregman method is presented with graph regularized sparse coding for highly undersampled magnetic resonance image reconstruction. The graph regularized sparse coding is incorporated with the two-level Bregman iterative procedure which enforces the sampled data constraints in the outer level and updates dictionary and sparse representation in the inner level. Graph regularized sparse coding and simple dictionary updating applied in the inner minimization make the proposed algorithm converge with a relatively small number of iterations. Experimental results demonstrate that the proposed algorithm can consistently reconstruct both simulated MR images and real MR data efficiently, and outperforms the current state-of-the-art approaches in terms of visual comparisons and quantitative measures.
基金supported in part by the National Natural Science Foundation of China(61302041,61363044,61562053,61540042)the Applied Basic Research Foundation of Yunnan Provincial Science and Technology Department(2013FD011,2016FD039)
文摘Text in natural scene images usually carries abundant semantic information. However, due to variations of text and complexity of background, detecting text in scene images becomes a critical and challenging task. In this paper, we present a novel method to detect text from scene images. Firstly, we decompose scene images into background and text components using morphological component analysis(MCA), which will reduce the adverse effects of complex backgrounds on the detection results.In order to improve the performance of image decomposition,two discriminative dictionaries of background and text are learned from the training samples. Moreover, Laplacian sparse regularization is introduced into our proposed dictionary learning method which improves discrimination of dictionary. Based on the text dictionary and the sparse-representation coefficients of text, we can construct the text component. After that, the text in the query image can be detected by applying certain heuristic rules. The results of experiments show the effectiveness of the proposed method.
基金This research was supported by the National Natural Science Foundation of China(No.51704229)Outstanding Youth Science Fund of Xi’an University of Science and Technology(No.2018YQ2-01).
文摘Electrical capacitance tomography(ECT)has great application potential inmultiphase processmonitoring,and its visualization results are of great significance for studying the changes in two-phase flow in closed environments.In this paper,compressed sensing(CS)theory based on dictionary learning is introduced to the inverse problem of ECT,and the K-SVD algorithm is used to learn the overcomplete dictionary to establish a nonlinear mapping between observed capacitance and sparse space.Because the trained overcomplete dictionary has the property to match few features of interest in the reconstructed image of ECT,it is not necessary to rely on the sparsity of coefficient vector to solve the nonlinear mapping as most algorithms based on CS theory.Two-phase flow distribution in a cylindrical pipe was modeled and simulated,and three variations without sparse constraint based on Landweber,Tikhonov,and Newton-Raphson algorithms were used to rapidly reconstruct a 2-D image.
基金Project supported by the National Natural Science Foundation of China （Nos. 61272304 and 61363029） and the Guangxi Key Laboratory of Trusted Software （No. kx201313）
文摘Sparse representation is a mathematical model for data representation that has proved to be a powerful tool for solving problems in various fields such as pattern recognition, machine learning, and computer vision. As one of the building blocks of the sparse representation method, dictionary learning plays an important role in the minimization of the reconstruction error between the original signal and its sparse representation in the space of the learned dictionary. Although using training samples directly as dictionary bases can achieve good performance, the main drawback of this method is that it may result in a very large and inef- ficient dictionary due to noisy training instances. To obtain a smaller and more representative dictionary, in this paper, we propose an approach called Laplacian sparse dictionary （LSD） learning. Our method is based on manifold learning and double sparsity. We incorporate the Laplacian weighted graph in the sparse representation model and impose the 11-norm sparsity on the dictionary. An LSD is a sparse overcomplete dictionary that can preserve the intrinsic structure of the data and learn a smaller dictionary for each class. The learned LSD can be easily integrated into a classification framework based on sparse representation. We compare the proposed method with other methods using three benchmark-controlled face image databases, Extended Yale B, ORL, and AR, and one uncontrolled person image dataset, i-LIDS-MA. Results show the advantages of the proposed LSD algorithm over state-of-the-art sparse representation based classification methods.
文摘In recent years,there has been a growing usage of sparse representations in signal processing.This paper revisits theK-SVD,an algorithm for designing overcomplete dictionaries for sparse and redundant representations.We present a newapproach to solve dictionary learning models by combining the alternating direction method of multipliers and the orthogonal matching pursuit.The experimental results show that our approach can reliably obtain better learned dictionary elements and outperform other algorithms.
文摘目的现实中采集到的人脸图像通常受到光照、遮挡等环境因素的影响,使得同一类的人脸图像具有不同程度的差异性,不同类的人脸图像又具有不同程度的相似性,这极大地影响了人脸识别的准确性。为了解决上述问题对人脸识别造成的影响,在低秩矩阵恢复理论的基础上提出了具有识别力的结构化低秩字典学习的人脸识别算法。方法该算法基于训练样本的标签信息将低秩正则化以及结构化稀疏同时引入到学习的具有识别力的字典上。在字典学习过程中,首先利用样本的重建误差约束样本与字典之间的关系;其次将Fisher准则应用到稀疏编码过程中,使其编码系数具有识别能力;由于训练样本中的噪声信息会影响字典的识别力,所以在低秩矩阵恢复理论的基础上将低秩正则化应用到字典学习过程中;接着,在字典学习过程中加入了结构化稀疏使其不丢失结构信息以保证对样本进行最优分类;最后再利用误差重构法对测试样本进行分类识别。结果本文算法在AR以及ORL人脸数据库上分别进行了实验仿真。在AR人脸数据库中,为了分析样本不同维数对实验结果造成的影响,选取了第一时期拍摄的每人6幅图像,包括1幅围巾遮挡,2幅墨镜遮挡以及3幅脸部表情变化以及光照变化(未被遮挡)的图像作为训练样本,同时选取相同组合的样本图像作为测试样本,无论哪种方法,图像的维度越高识别率越高。对比SRC(sparse representation based on classification)算法与DKSVD(discriminative K-means singular value decomposition)算法的识别率可知,DKSVD算法通过字典学习减缓了训练样本中的不确定因素对识别结果的影响;对比DLRD_SR(discriminative low-rank dictionary learning for sparse representation)算法与FDDL(Fisher discriminative dictionary learning)算法的识别率可知,当图像有遮挡等噪声信息存在时,字典低秩化可以提高至少5.8%的识别率;对比本文算法与DLRD_SR算法可知,在字典学习的过程中加入Fisher准则后识别率显著提高,同时理想稀疏值能保证对样本进行最优的分类。当样本图像的维度达到500维时人脸图像在有围巾、墨镜遮挡的情况下识别率可达到85.2%;其中墨镜和围巾的遮挡程度分别可以看成是人脸图像的20%和40%,为了验证本文算法在不同脸部表情变化、光照改变以及遮挡情况下的有效性,根据训练样本的具体图像组合情况进行实验。无论哪种样本图像组合,本文算法在有遮挡存在的样本识别中具有显著优势。在训练样本只包含脸部表情变化、光照变化以及墨镜遮挡图像的情况下,本文算法的识别率高于其他算法至少2.7%,在训练样本只包含脸部表情变化、光照变化以及围巾遮挡图像的情况下,本文算法的识别率高于其他算法至少3.6%,在训练样本包含脸部表情变化、光照变化、围巾遮挡以及墨镜遮挡图像的情况下,其识别率高于其他算法至少1.9%。在ORL人脸数据库中,人脸图像在无遮挡的情况下识别率达到95.2%,稍低于FDDL算法的识别率;在随机块遮挡程度达到20%时,相比较于SRC算法、DKSVD算法、FDDL算法以及DLRD_SR算法,本文算法的识别率最高;当随机块遮挡程度达到50%时,以上算法的识别率均不高,但本文算法的其识别率仍然最高。结论本文算法在人脸图像受到遮挡等因素的影响时具有一定的鲁棒性,实验结果表明该算法在人脸识别方面具有可行性。
