A5083042979- Advanced Vision and Imaging
- Video Coding and Compression Technologies
- Advanced Image Processing Techniques
- Advanced Data Compression Techniques
- Image and Signal Denoising Methods
- Digital Filter Design and Implementation
- Image and Video Quality Assessment
- Image Processing Techniques and Applications
- Numerical Methods and Algorithms
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Image Enhancement Techniques
- Image and Object Detection Techniques
- Medical Image Segmentation Techniques
- Analog and Mixed-Signal Circuit Design
- Video Surveillance and Tracking Methods
- Blind Source Separation Techniques
- Advancements in PLL and VCO Technologies
- Advanced Image Fusion Techniques
- Advanced Adaptive Filtering Techniques
- Robotics and Sensor-Based Localization
- Image Processing and 3D Reconstruction
- Face and Expression Recognition
- Medical Imaging Techniques and Applications
- Neural Networks and Applications
Hong Kong Polytechnic University
2015-2024
Saint Francis University
2024
Saint Francis University
2021-2024
Fuzhou University
2020
Institute of Information Science
2018
Nanjing University of Science and Technology
2017
Beijing Institute of Technology
2007
University of Wollongong
2002
Imperial College London
1983-1984
In this paper we address the problem of producing a high-resolution image from single low-resolution without any external training set. We propose framework for both magnification and deblurring using only original its blurred version. our method, each pixel is predicted by neighbors through Gaussian process regression. show that when proper covariance function, regression can perform soft clustering pixels based on their local structures. further demonstrate algorithm extract adequate...
Low-light image enhancement is a challenging task that has attracted considerable attention. Pictures taken in low-light conditions often have bad visual quality. To address the problem, we regard as residual learning problem to estimate between low- and normal-light images. In this paper, propose novel Deep Lightening Network (DLN) benefits from recent development of Convolutional Neural Networks (CNNs). The proposed DLN consists several Back-Projection (LBP) blocks. LBPs perform lightening...
This paper reviews the NTIRE 2020 challenge on real world super-resolution. It focuses participating methods and final results. The addresses setting, where paired true high low-resolution images are unavailable. For training, only one set of source input is therefore provided along with a unpaired high-quality target images. In Track 1: Image Processing artifacts, aim to super-resolve synthetically generated image processing artifacts. allows for quantitative benchmarking approaches w.r.t....
This paper proposes a two-stage framework for fast image interpolation via random forests (FIRF). The proposed FIRF method gives high accuracy, as well requires low computation. underlying idea of this work is to apply classify the natural patch space into numerous subspaces and learn linear regression model each subspace map low-resolution high-resolution patch. consists two stages. Stage 1 removes most ringing aliasing artifacts in initial bicubic interpolated image, while 2 further...
Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps generate SR images with remarkable quality. However, the more complex network we have, time consumption is required for practical applications. It important have a simplified efficient SR. In this paper, propose an Attention Back Projection Network (ABPN) super-resolution. Similar some recent works, believe...
Sparse representation has been extensively studied for image super-resolution (SR), and it achieved great improvement. Deep-learning-based SR methods have also emerged in the literature to pursue better results. In this paper, we propose use a set of decision tree strategies fast high-quality SR. Our proposed using (SRDT) method takes divide-and-conquer strategy, which performs few simple binary tests classify an input low-resolution (LR) patch into one leaf nodes directly multiplies LR with...
The screen content coding (SCC) extension of high efficiency video (HEVC) improves gain for videos by introducing two new modes, namely, intra block copy (IBC) and palette (PLT) modes. However, the is achieved at increased cost computational complexity. In this paper, we propose a decision tree-based framework fast mode investigating various features in training sets. To avoid exhaustive searching process, sequential arrangement trees proposed to check each separately inserting classifier...
There is a great leap in objective accuracy on image super-resolution, which recently brings new challenge super-resolution with larger up-scaling (e.g. 4×) using pixel based distortion for measurement. This causes over-smooth effect cannot grasp well the perceptual similarity. The advent of generative adversarial networks makes it possible super-resolve low-resolution to generate photo-realistic images sharing distribution high-resolution images. However, suffer from problems mode-collapse...
This paper reviews the NTIRE 2021 challenge on learning super-Resolution space. It focuses participating methods and final results. The addresses problem of a model capable predicting space plausible super-resolution (SR) images, from single low-resolution image. must thus be sampling diverse outputs, rather than just generating SR goal is to spur research into developing formulations models better suited for highly ill-posed problem. And thereby advance state-of-the-art in broader field. In...
Abstract Background The DNA microarray technology allows the measurement of expression levels thousands genes under tens/hundreds different conditions. In data, with similar functions usually co-express certain conditions only [1]. Thus, biclustering which clusters and simultaneously is preferred over traditional clustering technique in discovering these coherent genes. Various algorithms have been developed using bicluster formulations. Unfortunately, many useful formulations result...
Up to 35 intra prediction modes are available for each Luma unit in the coming HEVC standard. This can provide more accurate predictions and thereby improve compression efficiency of coding. However, encoding complexity is thus increased dramatically due a large number involved mode decision process. In addition, overhead bits should be assigned signal index. Intuitively, it not necessary all checked signaled time. Therefore, novel adaptive skipping algorithm signaling processing presented...
Screen content coding (SCC) is an extension of high efficiency video by adopting new modes to improve the SCC at expense increased complexity. This paper proposes online-learning approach for fast mode decision and unit (CU) size in SCC. To make a decision, corner point first extracted as unique feature screen content, which essential pre-processing step guide Bayesian modeling. Second, distinct color number CU derived another build precise model using skipping unnecessary modes. Third,...
Deep learning based single image super-resolution methods use a large number of training datasets and have recently achieved great quality progress both quantitatively qualitatively. Most deep networks focus on nonlinear mapping from low-resolution inputs to high-resolution outputs via residual without exploring the feature abstraction analysis. We propose Hierarchical Back Projection Network (HBPN), that cascades multiple HourGlass (HG) modules bottom-up top-down process features across all...
Mathematical morphology is very attractive for automatic image segmentation because it efficiently deals with geometrical descriptions such as size, area, shape, or connectivity that can be considered segmentation-oriented features. This paper presents an image-segmentation system based on some well-known strategies. The process divided into three basic steps, namely: simplification, marker extraction, and boundary decision. Simplification, which makes use of area morphology, removes...
A unified approach to the realization of forward and inverse discrete cosine transforms is proposed. With this approach, an odd prime length DCT/IDCT with two half-length convolutions can be realized without extra overhead in terms number multiplications. The formulation most suitable for using distributed arithmetic, which case typical convolvers used as core unit hardware implementation transforms. Hence, efficient chip proposed demonstrate superiority formulation. architecture easily meet...
Multiview video plus depth format has been adopted as the emerging 3D representation recently. It includes a limited number of textures and maps to synthesize additional virtual views. Since quality influences view synthesis process, their sharp edges should be well preserved avoid mixing foreground with background. To address this issue, 3D-High Efficiency Video Coding (HEVC) introduces new coding tools, partition-based intra mode [depth modeling (DMM)], residual description technique...
In this correspondence, a two-channel linear phase finite-impulse-response (FIR) quadrature mirror filter (QMF) bank minimax design problem is formulated as nonconvex optimization so that weighted sum of the maximum amplitude distortion bank, passband ripple magnitude and stopband prototype minimized subject to specifications on these performances. A modified filled function method proposed for finding global minimum problem. Computer numerical simulations show our efficient effective.
A screen content coding (SCC) extension to high efficiency video has been developed incorporate many new tools in order achieve better for videos mixed with camera-captured and graphics/text/animation. For instance, the Intra Block Copy (IntraBC) mode helps encode repeating patterns within same frame while Palette aims at encoding a few major colors. However, IntraBC brings along computational complexity due exhaustive block matching though there are already some constraints fast approaches...
Face hallucination or super-resolution is a practical application of general image which has been recently studied by many researchers. The challenge good face comes from variety poses, illuminations, facial expressions, and other degradations. In proposed methods, researchers resolve it using generative neural network to reduce the perceptual loss so we can generate photo-realistic image. problem that usually overlook fidelity super-resolved could affect further processing. Meanwhile, CNN...
In this paper, we propose a novel reference based image super-resolution approach via Variational AutoEncoder (RefVAE). Existing state-of-the-art methods mainly focus on single which cannot perform well large upsampling factors, e.g., 8×. We super-resolution, for any arbitrary can act as super-resolution. Even using random map or low-resolution itself, the proposed RefVAE transfer knowledge from to super-resolved images. Depending upon different references, method generate versions of images...