Image features can be learned and subsequently used for reconstruction and classification tasks in the fields of machine learning and computer vision. In this work, we propose image reconstruction using convolutional ...
详细信息
ISBN:
(纸本)9781509061822
Image features can be learned and subsequently used for reconstruction and classification tasks in the fields of machine learning and computer vision. In this work, we propose image reconstruction using convolutional sparse coding (CSC) on IBM's TrueNorth Neuromorphic computing system. CSC explicitly models local interactions through the convolution operations. convolutional kernels define a dictionary and sparse Feature Maps (SFMs) that are generated through a training process. The images are reconstructed with convolutional operations on SFMs and respective kernels. In this paper, we report on experimental results demonstrating promising sparse reconstructions on the IBM Neuromorphic TrueNorth hardware for two different benchmarks: MNIST and CIFAR-10. It is noted that this is the first ever important step towards convolutional sparse coding on neuromorphic hardware.
In this paper, we address the rain streak removal from a single image. In order to efficiently detect and remove the annoying rain streaks, we propose a global single-directional gradient prior with the L0 norm to mod...
详细信息
ISBN:
(数字)9781510646445
ISBN:
(纸本)9781510646445;9781510646438
In this paper, we address the rain streak removal from a single image. In order to efficiently detect and remove the annoying rain streaks, we propose a global single-directional gradient prior with the L0 norm to model the rain streak. To preserve the abundant information of the background, we learn a convolutional sparse coding (CSC) to represent the background. Furthermore, we develop an alternating direction method of multipliers (ADMM) to solve multi-variable optimization problems. Experiments on synthesized and real-world images show that the proposed method outperforms state-of-art methods in terms of rain streak removal and background preservation.
Face recognition has been an important task in pattern recognition and computer vision. Recently, sparse representation has become a popular data representation method in face recognition field. convolutionalsparse c...
详细信息
ISBN:
(纸本)9781538632574
Face recognition has been an important task in pattern recognition and computer vision. Recently, sparse representation has become a popular data representation method in face recognition field. convolutional sparse coding, which replaces the linear combination of a set of dictionary atoms with the sum of s series of mapping term convoluted with the dictionary filters, was proposed to improve the application performance of traditional sparsecoding. In this paper, we apply this convolutional sparse coding method to do the face recognition. As the trained dictionary filters could capture more discriminative information in the corresponding face images, it could believed that better classification performance can be achieved. Experimental results on the face image database demonstrated the novel convolutional sparse coding algorithm can achieve better recognition rate.
In this paper, we present a novel classification model which combines the convolutional sparse coding framework with the classification strategy. In the training phase, the proposed model trained a convolutional filte...
详细信息
ISBN:
(纸本)9781467399616
In this paper, we present a novel classification model which combines the convolutional sparse coding framework with the classification strategy. In the training phase, the proposed model trained a convolutional filter bank by all images of each class. In the test phase, the label of test image is determined by all convolutional filter banks. Compared with canonical sparse representation and dictionary learning classification algorithm, more representative information of the corresponding images could be captured by the trained filters, thus better classification performance can be obtained. Experimental results on some image benchmark databases demonstrated the effectiveness of the proposed method.
The identification of prototypical waveforms, such as sleep spindles and epileptic spikes, is crucial for the diagnosis of neurological disorders. These prototypical waveforms are usually recurrently presented in cert...
详细信息
The identification of prototypical waveforms, such as sleep spindles and epileptic spikes, is crucial for the diagnosis of neurological disorders. These prototypical waveforms are usually recurrently presented in certain brain states, serving as potential biomarkers for clinical evaluations. convolutional sparse coding(CSC) approaches have demonstrated strength in identifying recurrent patterns in time-series. However,existing CSC approaches do not explicitly explore state-specific patterns, making it difficult to identify state-related biomarkers. To address this problem, we propose state-sensitive CSC to learn state-specific prototypical waveforms. Specifically, we model signals of a certain state with specific waveforms that only appear frequently in this state and background waveforms that are independent of states. Based on this,state-sensitive CSC separates state-specific waveforms from background ones explicitly by incorporating incoherence constraints into optimizations. Experiments with epilepsy brain signals demonstrate that our approach can effectively identify prototypical waveforms in pre-ictal states, providing potential biomarkers for seizure prediction. Our approach provides a promising tool for automatic biomarker candidate identification.
convolutional neural network(CNN) and its variants have led to many state-of-the-art results in various ***,a clear theoretical understanding of such networks is still ***,a multilayer convolutional sparse coding(ML-C...
详细信息
convolutional neural network(CNN) and its variants have led to many state-of-the-art results in various ***,a clear theoretical understanding of such networks is still ***,a multilayer convolutional sparse coding(ML-CSC) model has been proposed and proved to equal such simply stacked networks(plain networks).Here,we consider the initialization,the dictionary design and the number of iterations to be factors in each layer that greatly affect the performance of the ML-CSC *** by these considerations,we propose two novel multilayer models:the residual convolutional sparse coding(Res-CSC) model and the mixed-scale dense convolutional sparse coding(MSD-CSC) *** are closely related to the residual neural network(ResNet) and the mixed-scale(dilated) dense neural network(MSDNet),***,we derive the skip connection in the ResNet as a special case of a new forward propagation rule for the ML-CSC *** also find a theoretical interpretation of dilated convolution and dense connection in the MSDNet by analyzing the MSD-CSC model,which gives a clear mathematical understanding of *** implement the iterative soft thresholding algorithm and its fast version to solve the Res-CSC and MSD-CSC *** unfolding operation can be employed for further ***,extensive numerical experiments and comparison with competing methods demonstrate their effectiveness.
Image decomposition is a fundamental but challenging ill-posed problem in image processing and has been widely applied to compression, enhancement, texture removal, etc. In this paper, we introduce a novel structure-t...
详细信息
Image decomposition is a fundamental but challenging ill-posed problem in image processing and has been widely applied to compression, enhancement, texture removal, etc. In this paper, we introduce a novel structure-texture image decomposition model via non-convex total generalized variation regularization (NTGV) and convolutional sparse coding (CSC). NTGV aims to characterize the detailed-preserved structural component ameliorating the staircasing artifacts existing in total variation-based models, and CSC aims to characterize image fine-scale textures. Moreover, we incorporate both structure-aware and texture-aware measures to well distinguish structural and textural component. The proposed model is numerically implemented by an alternating minimization scheme based on alternating direction method of multipliers. Experimental results demonstrate the effectiveness of our approach on several applications including texture removal, high dynamic range image tone mapping, detail enhancement and non-photorealistic abstraction.
Light-field microscopy (LFM) is a type of all-optical imaging system that is able to capture 4D geometric information of light rays and can reconstruct a 3D model from a single snapshot. In this paper, we propose a ne...
详细信息
Light-field microscopy (LFM) is a type of all-optical imaging system that is able to capture 4D geometric information of light rays and can reconstruct a 3D model from a single snapshot. In this paper, we propose a new 3D localization approach to effectively detect 3D positions of neuronal cells from a single light-field image with high accuracy and outstanding robustness to light scattering. This is achieved by constructing a depth-aware dictionary and by combining it with convolutional sparse coding. Specifically, our approach includes 3 key parts: light-field calibration, depth-aware dictionary construction, and localization based on convolutional sparse coding (CSC). In the first part, an observed raw light-field image is calibrated and then decoded into a two-plane parameterized 4D format which leads to the epi-polar plane image (EPI). The second part involves simulating a set of light-fields using a wave-optics forward model for a ball-shaped volume that is located at different depths. Then, a depth-aware dictionary is constructed where each element is a synthetic EPI associated to a specific depth. Finally, by taking full advantage of the sparsity prior and shift-invariance property of EPI, 3D localization is achieved via convolutional sparse coding on an observed EPI with respect to the depth-aware EPI dictionary. We evaluate our approach on both non-scattering specimen (fluorescent beads suspended in agarose gel) and scattering media (brain tissues of genetically encoded mice). Extensive experiments demonstrate that our approach can reliably detect the 3D positions of granular targets with small Root Mean Square Error (RMSE), high robustness to optical aberration and light scattering in mammalian brain tissues.
Convolution sparsecoding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input...
详细信息
Convolution sparsecoding (CSC) has attracted much attention recently due to its advantages in image reconstruction and enhancement. However, the coding process suffers from perturbations caused by variations of input samples, as the consistence of features from similar input samples are not well addressed in the existing literature. In this paper, we will tackle this feature consistence problem from a set of samples via a proposed manifold constrained convolutional sparse coding (MCSC) method. The core idea of MCSC is to use the intrinsic manifold (Laplacian) structure of the input data to regularize the traditional CSC such that the consistence between features extracted from input samples can be well preserved. To implement the proposed MCSC method efficiently, the alternating direction method of multipliers (ADMM) approach is employed, which can consistently integrate the underlying Laplacian constraints during the optimization process. With this regularized data structure constraint, the MCSC can achieve a much better solution which is robust to the variance of the input samples against overcomplete filters. We demonstrate the capacity of MCSC by providing the state-of-the-art results when applied it to the task of reconstructing light fields. Finally, we show that the proposed MCSC is a generic approach as it also achieves better results than the state-of-the-art approaches based on convolutional sparse coding in other image reconstruction tasks, such as face reconstruction, digit reconstruction, and image restoration.
Stereo matching is an important research topic in the field of computer vision. It recovers depth information from a pair of color images. Unfortunately, converting multi-dimensional (more than two-dimensional) data i...
详细信息
Stereo matching is an important research topic in the field of computer vision. It recovers depth information from a pair of color images. Unfortunately, converting multi-dimensional (more than two-dimensional) data into two-dimensional data, such formulations ignore the spatial structure of multi-dimensional images/data. Tensors can be used to describe high-dimensional data structure, which can retain the hidden structure of data, but cannot obtain the deep features that helps to improve the performance of the algorithm. Therefore, it is very important to establish a deep tensor model. In this paper, we propose a two layer tensor form convolutional sparse coding model, which can automatically learn the deep convolutional kernel. Based on the learned two layer convolutional kernels, a two-layer dictionary learning model is established. Then, a new weighted matching cost method is constructed, which combines shallow and deep features. The experimental results on the Middlebury benchmark v2 and Middlebury benchmark v3 show that the proposed two layer tensor convolutional sparse coding is effective for stereo matching.
暂无评论