Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world. One of the emerging technologies is light field (LF) cameras based on micro-lens arrays. To reco...
详细信息
Recent imaging technologies are rapidly evolving for sampling richer and more immersive representations of the 3D world. One of the emerging technologies is light field (LF) cameras based on micro-lens arrays. To record the directional information of the light rays, a much larger storage space and transmission bandwidth are required by an LF image as compared with a conventional 2D image of similar spatial dimension. Hence, the compression of LF data becomes a vital part of its application. In this paper, we propose an LF codec with disparity guided sparse coding over a learned perspective-shifted LF dictionary based on selected Structural Key Views (SC-SKV). The sparse coding is based on a limited number of optimally selected SKVs;yet the entire LF can be recovered from the coding coefficients. By keeping the approximation identical between encoder and decoder, only the residuals of the non-key views, disparity map, and the SKVs need to be compressed into the bit stream. An optimized SKV selection method is proposed such that most LF spatial information can be preserved. To achieve optimum dictionary efficiency, the LF is divided into several coding regions, over which the reconstruction works individually. Experiments and comparisons have been carried out over benchmark LF data set, which show that the proposed SC-SKV codec produces convincing compression results in terms of both rate-distortion performance and visual quality compared with Joint Exploration Model: with 37.9% BD-rate reduction and 1.17-dB BD-PSNR improvement achieved on average, especially with up to 6-dB improvement for low bit rate scenarios.
sparse coding methods have shown the superiority in data representation. However, traditional sparse coding methods cannot explore the manifold structure embedded in data. To alleviate this problem, a novel method, ca...
详细信息
sparse coding methods have shown the superiority in data representation. However, traditional sparse coding methods cannot explore the manifold structure embedded in data. To alleviate this problem, a novel method, called Structure Preserving sparse coding (SPSC), is proposed for data representation. SPSC imposes both local affinity and distant repulsion constraints on the model of sparse coding. Therefore, the proposed SPSC method can effectively exploit the structure information of high dimensional data. Beside, an efficient optimization scheme for our proposed SPSC method is developed, and the convergence analysis on three datasets are presented. Extensive experiments on several benchmark datasets have shown the superior performance of our proposed method compared with other state-of-the-art methods.
Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, in vivo, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HAR...
详细信息
Diffusion MRI (dMRI) provides the ability to reconstruct neuronal fibers in the brain, in vivo, by measuring water diffusion along angular gradient directions in q-space. High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation than the popularly used diffusion tensor imaging, but the high number of samples needed to estimate diffusivity requires longer patient scan times. To accelerate dMRI, compressed sensing (CS) has been utilized by exploiting a sparse dictionary representation of the data, discovered through sparse coding. The sparser the representation, the fewer samples are needed to reconstruct a high resolution signal with limited information loss, and so an important area of research has focused on finding the sparsest possible representation of dMRI. Current reconstruction methods however, rely on an angular representation per voxel with added spatial regularization, and so, for non-zero signals, one is required to have at least one non-zero coefficient per voxel. This means that the global level of sparsity must be greater than the number of voxels. In contrast, we propose a joint spatial-angular representation of dMRI that will allow us to achieve levels of global sparsity that are below the number of voxels. A major challenge, however, is the computational complexity of solving a global sparse coding problem over large-scale dMRI. In this work, we present novel adaptations of popular sparse coding algorithms that become better suited for solving large-scale problems by exploiting spatial-angular separability. Our experiments show that our method achieves significantly sparser representations of HARDI than is possible by the state of the art. (C) 2018 Elsevier B.V. All rights reserved.
The modified quadratic discriminant function (MQDF) is an effective classifier for handwritten Chinese character recognition (HCCR). However, it suffers from high memory requirement for the storage of its parameters, ...
详细信息
The modified quadratic discriminant function (MQDF) is an effective classifier for handwritten Chinese character recognition (HCCR). However, it suffers from high memory requirement for the storage of its parameters, which makes it impractical to be embedded in memory limited hand-held devices. In this paper, we explore the applicability of sparse coding to build compact MQDF classifiers. To be specific, we use sparse coding to compact the parameters of MQDF. Two methods of sparse coding, viz., the maximum likelihood-based method and the K-SVD method, are adopted to build two compact MQDF classifiers, namely, MQDF-ML classifier and MQDF-KSVD classifier. Furthermore, we learn multiple dictionaries rather than single dictionary for sparse coding, because the multiple dictionary learning is capable of not only greatly reducing the computational complexity, but also alleviating the degradation of recognition accuracy, compared to the single dictionary learning. Experiments and comparison with the existing method have demonstrated the effectiveness of our proposed method for the issue of unconstrained handwritten Chinese character recognition. (C) 2017 Elsevier Ltd. All rights reserved.
Finding an appropriate feature representation for audio data is central to speech emotion recognition. Most existing audio features rely on hand-crafted feature encoding techniques, such as the AVEC challenge feature ...
详细信息
Finding an appropriate feature representation for audio data is central to speech emotion recognition. Most existing audio features rely on hand-crafted feature encoding techniques, such as the AVEC challenge feature set. An alternative approach is to use features that are learned automatically. This has the advantage of generalizing well to new data, particularly if the features are learned in an unsupervised manner with less restrictions on the data itself. In this work, we adopt the sparse coding framework as a means to automatically represent features from audio and propose a hierarchical sparse coding (HSC) scheme. Experimental results indicate that the obtained features, in an unsupervised fashion, are able to capture useful properties of the speech that distinguish between emotions.
Based on the key observation that the coding residuals between the recovered sparse codes of the noisy SAR image and those of the clean SAR image are sparse, we propose a sparse representation-based despeckling algori...
详细信息
Based on the key observation that the coding residuals between the recovered sparse codes of the noisy SAR image and those of the clean SAR image are sparse, we propose a sparse representation-based despeckling algorithm for SAR image. As the sparse codes of the clean SAR image are not available, the rich nonlocal repetitive structures of the logarithmic SAR images are exploited. To collect the similar patches within the logarithmic SAR image, an adaptive similarity evaluation obeying statistical distribution of the logarithmic speckle noise is derived. Experimental results on both synthetic and real SAR images demonstrate the validity of the proposed algorithm.
Image set compression has recently emerged as an active research topic due to the rapidly increasing demand in cloud storage. In this paper, we propose a novel framework for image set compression based on the rate-dis...
详细信息
Image set compression has recently emerged as an active research topic due to the rapidly increasing demand in cloud storage. In this paper, we propose a novel framework for image set compression based on the rate-distortion optimized sparse coding. Specifically, given a set of similar images, one representative image is first identified according to the similarity among these images, and a dictionary can be learned subsequently in wavelet domain from the training samples collected from the representative image. In order to improve coding efficiency, the dictionary atoms are reordered according to their use frequencies when representing the representative image. As such, the remaining images can be efficiently compressed with sparse coding based on the reordered dictionary that is highly adaptive to the content of the image set. To further improve the efficiency of sparse coding, the number of dictionary atoms for image patches is further optimized in a rate-distortion sense. Experimental results show that the proposed method can significantly improve the image compression performance compared with JPEG, JPEG2000, and the state-of-the-art dictionary learning-based methods.
A configurable neuroinspired inference accelerator is designed as an array of neurons, each operating in an independent clock domain. The accelerator implements a recurrent network using a novel sparse convolution for...
详细信息
A configurable neuroinspired inference accelerator is designed as an array of neurons, each operating in an independent clock domain. The accelerator implements a recurrent network using a novel sparse convolution for feedforward operations and sparse spike-driven reconstruction for feedback operations. The proposed sparse convolution efficiently skips zero-patches, and can be made to support practically any image and kernel size. A globally asynchronous locally synchronous architecture enables scalable design and load balancing to achieve 22% reduction in power. Fabricated in 40-nm CMOS, the 2.56-mm(2) inference accelerator integrates 48 neurons, a hub, and an OpenRISC processor. The chip achieves 718GOPS at 380 MHz, and demonstrates applications in feature extraction from images and depth extraction from stereo images.
Different from the traditional Internet-of-Things (IoT) architecture, information-centric IoT is a novel paradigm in which changes are made to the entire network stack, from layer 3 up to the application layer. IC-IoT...
详细信息
Different from the traditional Internet-of-Things (IoT) architecture, information-centric IoT is a novel paradigm in which changes are made to the entire network stack, from layer 3 up to the application layer. IC-IoT is built on top of named data networking (NDN), a content-centric Internet paradigm whose features are particularly promising for certain IoT applications, such as smart grid. In IC-IoT, privacy is one of the most challenging issues. Among existing privacy-preserving approaches, differential privacy (DP) is a powerful tool that can provide privacy-preserving noisy query answers over statistical databases and has been widely adopted in many practical fields. In particular, as an enhanced implementation of DP, randomized aggregable privacy-preserving ordinal response (RAPPOR) can achieve strong privacy, high-efficiency, and high-utility guarantees for each client string in data crowdsourcing. However, in many IoT applications like smart grid, data are often processed in batches. Developing a new random response algorithm that can support batch-processing will make it more efficient and suitable for IoT applications than existing random response algorithms. In this paper, we propose a new randomized response algorithm that can achieve differential-privacy and utility guarantees for consumer's behaviors and can process one batch of data at each time. First, by applying sparse coding in this algorithm, a behavior signature dictionary is created from the aggregated energy consumption data in IoT. Then, we add noise into the behavior signature dictionary by the classical randomized response techniques to achieve the differential privacy after data *** security analysis with the principle of differential privacy and experimental performance evaluation, we prove that our proposed algorithm can preserve consumer's privacy without compromising utility.
The classification of natural scene images is multi-instance multi-label (MIML) for many labels that exist in a natural scene image. The traditional method of solving MIML is to degenerate it into single-instance sing...
详细信息
The classification of natural scene images is multi-instance multi-label (MIML) for many labels that exist in a natural scene image. The traditional method of solving MIML is to degenerate it into single-instance single-label learning (SISL). However, the precision of the method could decrease due to information loss during the degeneration process. How to reasonably solve the MIML problem is key to obtaining high accuracy in this research area. An MIML algorithm based on instances via combining sparse coding with a deep neural network is proposed. First, an instance-based sparse representation with dictionary learning is adopted. Second, an MIML description model based on a deep network is proposed, which can realise parameter self-learning in combination with sparse representations. Third, the residuals of the sparse representation are introduced to the deep neural network. The results of the experiments show that the method outperforms a number of state-of-the-art approaches.
暂无评论