arXiv subjects

Jun Cheng

Publications and source records attributed to Jun Cheng.

142 records · Page 8Linked to original sources

arXiv2018

Sparse Range-constrained Learning and Its Application for Medical Image Grading

Sparse learning has been shown to be effective in solving many real-world problems. Finding sparse representations is a fundamentally important topic in many fields of science including signal processing, computer vision, genome study and medical imaging. One important issue in applying sparse representation is to find the basis to represent the data,especially in computer vision and medical imaging where the data is not necessary incoherent. In medical imaging, clinicians often grade the severity or measure the risk score of a disease based on images. This process is referred to as medical image grading. Manual grading of the disease severity or risk score is often used. However, it is tedious, subjective and expensive. Sparse learning has been used for automatic grading of medical images for different diseases. In the grading, we usually begin with one step to find a sparse representation of the testing image using a set of reference images or atoms from the dictionary. Then in the second step, the selected atoms are used as references to compute the grades of the testing images. Since the two steps are conducted sequentially, the objective function in the first step is not necessarily optimized for the second step. In this paper, we propose a novel sparse range-constrained learning(SRCL)algorithm for medical image grading.Different from most of existing sparse learning algorithms, SRCL integrates the objective of finding a sparse representation and that of grading the image into one function. It aims to find a sparse representation of the testing image based on atoms that are most similar in both the data or feature representation and the medical grading scores. We apply the new proposed SRCL to CDR computation and cataract grading. Experimental results show that the proposed method is able to improve the accuracy in cup-to-disc ratio computation and cataract grading.

cs.CV↗

arXiv2018

Structure-preserving Guided Retinal Image Filtering and Its Application for Optic Disc Analysis

Retinal fundus photographs have been used in the diagnosis of many ocular diseases such as glaucoma, pathological myopia, age-related macular degeneration and diabetic retinopathy. With the development of computer science, computer aided diagnosis has been developed to process and analyse the retinal images automatically. One of the challenges in the analysis is that the quality of the retinal image is often degraded. For example, a cataract in human lens will attenuate the retinal image, just as a cloudy camera lens which reduces the quality of a photograph. It often obscures the details in the retinal images and posts challenges in retinal image processing and analysing tasks. In this paper, we approximate the degradation of the retinal images as a combination of human-lens attenuation and scattering. A novel structure-preserving guided retinal image filtering (SGRIF) is then proposed to restore images based on the attenuation and scattering model. The proposed SGRIF consists of a step of global structure transferring and a step of global edge-preserving smoothing. Our results show that the proposed SGRIF method is able to improve the contrast of retinal images, measured by histogram flatness measure, histogram spread and variability of local luminosity. In addition, we further explored the benefits of SGRIF for subsequent retinal image processing and analysing tasks. In the two applications of deep learning based optic cup segmentation and sparse learning based cup-to-disc ratio (CDR) computation, our results show that we are able to achieve more accurate optic cup segmentation and CDR measurements from images processed by SGRIF.

cs.CV↗

arXiv2018

Disc-aware Ensemble Network for Glaucoma Screening from Fundus Image

Glaucoma is a chronic eye disease that leads to irreversible vision loss. Most of the existing automatic screening methods firstly segment the main structure, and subsequently calculate the clinical measurement for detection and screening of glaucoma. However, these measurement-based methods rely heavily on the segmentation accuracy, and ignore various visual features. In this paper, we introduce a deep learning technique to gain additional image-relevant information, and screen glaucoma from the fundus image directly. Specifically, a novel Disc-aware Ensemble Network (DENet) for automatic glaucoma screening is proposed, which integrates the deep hierarchical context of the global fundus image and the local optic disc region. Four deep streams on different levels and modules are respectively considered as global image stream, segmentation-guided network, local disc region stream, and disc polar transformation stream. Finally, the output probabilities of different streams are fused as the final screening result. The experiments on two glaucoma datasets (SCES and new SINDI datasets) show our method outperforms other state-of-the-art algorithms.

cs.CV↗

arXiv2018

Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtained by constraining the deep CNNs to map training samples to the corresponding anchors as close as possible. We propose two principles to select the anchors, and measure the proximity of two points using the Euclidean and cosine distance metric functions, which results in two novel loss functions. These loss functions require no sample pairs or triplets and can be efficiently optimized by batch stochastic gradient descent. We test the proposed method on three benchmark image classification datasets and demonstrate its promising results.

cs.CV↗

arXiv2018

Refractive index in generalized superconductors with Born-Infeld electrodynamics

We investigate, in the probe limit, the negative refraction in the generalized superconductors with the Born-Infeld electrodynamics. We observe that the system has a negative Depine-Lakhtakia index in the superconducting phase at small frequencies and the greater the Born-Infeld corrections the larger the range of frequencies or the range of temperatures for which the negative refraction occurs. Furthermore, we find that the tunable Born-Infeld parameter can be used to improve the propagation of light in the holographic setup. Our analysis indicates that the Born-Infeld electrodynamics plays an important role in determining the optical properties of the boundary theory.

hep-th↗

arXiv2018

Learning Scene-specific Object Detectors Based on a Generative-Discriminative Model with Minimal Supervision

One object class may show large variations due to diverse illuminations, backgrounds and camera viewpoints. Traditional object detection methods often perform worse under unconstrained video environments. To address this problem, many modern approaches model deep hierarchical appearance representations for object detection. Most of these methods require a timeconsuming training process on large manual labelling sample set. In this paper, the proposed framework takes a remarkably different direction to resolve the multi-scene detection problem in a bottom-up fashion. First, a scene-specific objector is obtained from a fully autonomous learning process triggered by marking several bounding boxes around the object in the first video frame via a mouse. Here the human labeled training data or a generic detector are not needed. Second, this learning process is conveniently replicated many times in different surveillance scenes and results in particular detectors under various camera viewpoints. Thus, the proposed framework can be employed in multi-scene object detection applications with minimal supervision. Obviously, the initial scene-specific detector, initialized by several bounding boxes, exhibits poor detection performance and is difficult to improve with traditional online learning algorithm. Consequently, we propose Generative-Discriminative model to partition detection response space and assign each partition an individual descriptor that progressively achieves high classification accuracy. A novel online gradual optimized process is proposed to optimize the Generative-Discriminative model and focus on the hard samples.Experimental results on six video datasets show our approach achieves comparable performance to robust supervised methods, and outperforms the state of the art self-learning methods under varying imaging conditions.

cs.CV↗

arXiv2018

Joint Optic Disc and Cup Segmentation Based on Multi-label Deep Network and Polar Transformation

Glaucoma is a chronic eye disease that leads to irreversible vision loss. The cup to disc ratio (CDR) plays an important role in the screening and diagnosis of glaucoma. Thus, the accurate and automatic segmentation of optic disc (OD) and optic cup (OC) from fundus images is a fundamental task. Most existing methods segment them separately, and rely on hand-crafted visual feature from fundus images. In this paper, we propose a deep learning architecture, named M-Net, which solves the OD and OC segmentation jointly in a one-stage multi-label system. The proposed M-Net mainly consists of multi-scale input layer, U-shape convolutional network, side-output layer, and multi-label loss function. The multi-scale input layer constructs an image pyramid to achieve multiple level receptive field sizes. The U-shape convolutional network is employed as the main body network structure to learn the rich hierarchical representation, while the side-output layer acts as an early classifier that produces a companion local prediction map for different scale layers. Finally, a multi-label loss function is proposed to generate the final segmentation map. For improving the segmentation performance further, we also introduce the polar transformation, which provides the representation of the original image in the polar coordinate system. The experiments show that our M-Net system achieves state-of-the-art OD and OC segmentation result on ORIGA dataset. Simultaneously, the proposed method also obtains the satisfactory glaucoma screening performances with calculated CDR value on both ORIGA and SCES datasets.

cs.CV↗

arXiv2017

Construction of Unrestricted Rate Parallel Random Input Output Code

A coding scheme for two-page unrestricted-rate PRIO code that each page may have different code rates is proposed. In the second page, the code for each messages consists of two complementary codewords with code length n. There are a total of 2n-1 codes which are disjoint to guarantees uniquely decodable for 2n-1 messages. In the first page, the code for each message consists of all weight-u vectors with their non-zero elements restricted to (2u-1) same positions, where non-negative integer u is less than or equal to half of code length. Finding codes to be disjoint in first page is equivalent to construction of constant-weight codes, and the numbers of disjoint codes are the best-known numbers of codewords in constant-weight codes. Our coding scheme is constructive, and the code length is arbitrary.The sum rates of our proposed codes are higher than those of previous work.

cs.IT↗

arXiv2016

Multiview Cauchy Estimator Feature Embedding for Depth and Inertial Sensor-Based Human Action Recognition

The ever-growing popularity of Kinect and inertial sensors has prompted intensive research efforts on human action recognition. Since human actions can be characterized by multiple feature representations extracted from Kinect and inertial sensors, multiview features must be encoded into a unified space optimal for human action recognition. In this paper, we propose a new unsupervised feature fusion method termed Multiview Cauchy Estimator Feature Embedding (MCEFE) for human action recognition. By minimizing empirical risk, MCEFE integrates the encoded complementary information in multiple views to find the unified data representation and the projection matrices. To enhance robustness to outliers, the Cauchy estimator is imposed on the reconstruction error. Furthermore, ensemble manifold regularization is enforced on the projection matrices to encode the correlations between different views and avoid overfitting. Experiments are conducted on the new Chinese Academy of Sciences - Yunnan University - Multimodal Human Action Database (CAS-YNU-MHAD) to demonstrate the effectiveness and robustness of MCEFE for human action recognition.

cs.CV↗

arXiv2016

The Point Spread Function Reconstruction by Using Moffatlets - I

The shear measurement is a crucial task in the current and the future weak lensing survey projects. And the reconstruction of the point spread function(PSF) is one of the essential steps. In this work, we present three different methods, including Gaussianlets, Moffatlets and EMPCA to quantify their efficiency on PSF reconstruction using four sets of simulated LSST star images. Gaussianlets and Moffatlets are two different sets of basis functions whose profiles are based on Gaussian and Moffat functions respectively. Expectation Maximization(EM) PCA is a statistical method performing iterative procedure to find principal components of an ensemble of star images. Our tests show that: 1) Moffatlets always perform better than Gaussianlets. 2) EMPCA is more compact and flexible, but the noise existing in the Principal Components (PCs) will contaminate the size and ellipticity of PSF while Moffatlets keeps them very well.

astro-ph.IM↗

arXiv2016

Signature Design of Sparsely Spread CDMA Based on Superposed Constellation Distance Analysis

Sparsely spread code division multiple access (SCDMA) is a non-orthogonal superposition coding scheme that permits a base station simultaneously communicates with multiple users over a common channel. The detection performance of an SCDMA system is mainly determined by its signature matrix, which should be sparse to guarantee large Euclidean distance for the equivalent signal constellation after spreading and superposition. Good signature matrices that perform well under both belief prorogation and the maximum likelihood detections are designed. The proposed design applies to several similar well-documented schemes, including trellis code multiple access (TCMA), low density spreading, and superposition modulation systems.

cs.IT↗

arXiv2015

Solution to the mean king's problem using quantum error-correcting codes

We discuss the so-called mean king's problem, a retrodiction problem among non-commutative observables, in the context of error detection. Describing the king's measurement effectively by a single error operation, we give a solution of the mean king's problem using quantum error-correcting codes. The existence of a quantum error-correcting code from a solution is also presented.

quant-ph↗

arXiv2013

Multiview Hessian Discriminative Sparse Coding for Image Annotation

Sparse coding represents a signal sparsely by using an overcomplete dictionary, and obtains promising performance in practical computer vision applications, especially for signal restoration tasks such as image denoising and image inpainting. In recent years, many discriminative sparse coding algorithms have been developed for classification problems, but they cannot naturally handle visual data represented by multiview features. In addition, existing sparse coding algorithms use graph Laplacian to model the local geometry of the data distribution. It has been identified that Laplacian regularization biases the solution towards a constant function which possibly leads to poor extrapolating power. In this paper, we present multiview Hessian discriminative sparse coding (mHDSC) which seamlessly integrates Hessian regularization with discriminative sparse coding for multiview learning problems. In particular, mHDSC exploits Hessian regularization to steer the solution which varies smoothly along geodesics in the manifold, and treats the label information as an additional view of feature for incorporating the discriminative power for image annotation. We conduct extensive experiments on PASCAL VOC'07 dataset and demonstrate the effectiveness of mHDSC for image annotation.

cs.MM↗

arXiv2012

Analysis of Finite Field Spreading for Multiple-Access Channel

Finite field spreading scheme is proposed for a synchronous multiple-access channel with Gaussian noise and equal-power users. For each user, $s$ information bits are spread \emph{jointly} into a length-$sL$ vector by $L$ multiplications on GF($2^s$). Thus, each information bit is dispersed into $sL$ transmitted symbols, and the finite field despreading (FF-DES) of each bit can take advantage of $sL$ independent receiving observations. To show the performance gain of joint spreading quantitatively, an extrinsic information transfer (EXIT) function analysis of the FF-DES is given. It shows that the asymptotic slope of this EXIT function increases as $s$ increases and is in fact the absolute slope of the bit error rate (BER) curve at the low BER region. This means that by increasing the length $s$ of information bits for joint spreading, a larger absolute slope of the BER curve is achieved. For $s, L\geq 2$, the BER curve of the finite field spreading has a larger absolute slope than that of the single-user transmission with BPSK modulation.

cs.IT↗

arXiv2008

Stimulated Raman spin coherence and spin-flip induced hole burning in charged GaAs quantum dots

High-resolution spectral hole burning (SHB) in coherent nondegenerate differential transmission spectroscopy discloses spin-trion dynamics in an ensemble of negatively charged quantum dots. In the Voigt geometry, stimulated Raman spin coherence gives rise to Stokes and anti-Stokes sidebands on top of the trion spectral hole. The prominent feature of an extremely narrow spike at zero detuning arises from spin population pulsation dynamics. These SHB features confirm coherent electron spin dynamics in charged dots, and the linewidths reveal spin spectral diffusion processes.

cond-mat.mes-hall↗

arXiv2005

Stimulated and spontaneous optical generation of electron spin coherence in charged GaAs quantum dots

We report on the coherent optical excitation of electron spin polarization in the ground state of charged GaAs quantum dots via an intermediate charged exciton (trion) state. Coherent optical fields are used for the creation and detection of the Raman spin coherence between the spin ground states of the charged quantum dot. The measured spin decoherence time, which is likely limited by the nature of the spin ensemble, approaches 10 ns at zero field. We also show that the Raman spin coherence in the quantum beats is caused not only by the usual stimulated Raman interaction but also by simultaneous spontaneous radiative decay of either excited trion state to a coherent combination of the two spin states.

cond-mat.mes-hall↗