- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Image and Video Quality Assessment
- Generative Adversarial Networks and Image Synthesis
- Face recognition and analysis
- Image and Signal Denoising Methods
- Image Enhancement Techniques
- Video Surveillance and Tracking Methods
- Face and Expression Recognition
- Image Processing Techniques and Applications
- Visual Attention and Saliency Detection
- Emotion and Mood Recognition
- Advanced Computing and Algorithms
- Color Science and Applications
- Speech and Audio Processing
- Human Pose and Action Recognition
- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Advanced Vision and Imaging
- Consumer Perception and Purchasing Behavior
- Advanced Neural Network Applications
- Photoacoustic and Ultrasonic Imaging
- Brain Tumor Detection and Classification
- Autonomous Vehicle Technology and Safety
- Video Coding and Compression Technologies
National Chung Hsing University
2015-2024
National Taipei University
2015-2023
University of Southern California
2011-2015
Image restoration is a challenging ill-posed problem which also has been long-standing issue. In the past few years, convolution neural networks (CNNs) almost dominated computer vision and had achieved considerable success in different levels of tasks including image restoration. However, recently Swin Transformer-based model shows impressive performance, even surpasses CNN-based methods to become state-of-the-art on high-level tasks. this paper, we proposed called SUNet uses Transformer...
Low-Light Image Enhancement is a computer vision task which intensifies the dark images to appropriate brightness. It can also be seen as an ill-posed problem in image restoration domain. With success of deep neural networks, convolutional networks surpass traditional algorithm-based methods and become mainstream area. To advance performance enhancement algorithms, we propose network (HWMNet) based on improved hierarchical model: M-Net+. Specifically, use half wavelet attention block M-Net+...
A new methodology for objective image quality assessment (IQA) with multi-method fusion (MMF) is presented in this paper. The research motivated by the observation that there no single method can give best performance all situations. To achieve MMF, we adopt a regression approach. MMF score set to be nonlinear combination of scores from multiple methods suitable weights obtained training process. In order improve results further, divide distorted images into three five groups based on...
Research on visual quality assessment has been active during the last decade.In this work, we provide an in-depth review of recent developments in field.As compared with existing survey papers, our current work several unique contributions.First, besides image databases and metrics, put equal emphasis video metrics as is a less investigated area.Second, discuss application evaluation to perceptual coding example for applications.Third, benchmark performance state-of-the-art...
An ensemble method for full-reference image quality assessment (IQA) based on the parallel boosting (ParaBoost) idea is proposed in this paper. We first extract features from existing metrics and train them to form basic scorers (BIQSs). Then, we select additional address specific distortion types construct auxiliary (AIQSs). Both BIQSs AIQSs are trained small subsets of certain and, as a result, they weak performers with respect wide variety distortions. Finally, adopt ParaBoost framework,...
A no-reference (NR) learning-based approach to assess image quality is presented in this paper. The devised features are extracted from wide perceptual domains, including brightness, contrast, color, distortion, and texture. These used train a model (scorer) which can predict scores. scorer selection algorithms utilized help simplify the proposed system. In final stage, ensemble method combine prediction results selected scorers. Two multiple-scale versions of also along with single-scale...
Developing an automatic age estimation method towards human faces continues to possess important role in computer vision and pattern recognition. Many studies regarding facial mainly focus on two aspects: aging feature extraction classification/regression model learning. To set our work apart from existing approaches, we consider a different aspect -system structuring, which is, under constrained condition: given fixed type learning method, how design framework improve the performance based...
In this work, we study the visual quality of streaming video and propose a fusion-based assessment (FVQA) index to predict its quality. first step, sequences are grouped according their content complexity reduce diversity within each group. Then, at second several existing methods fused provide final score, where fusion coefficients learned from training samples in same We demonstrate superior performance FVQA as compared with other using MCL-V database.
This paper presents a new methodology for objective visual quality assessment with multi-metric fusion (MMF). The current research is motivated by the observation that there no single metric gives best performance scores in all situations. To achieve MMF, we adopt regression approach. First, collect large number of image samples, each which has score labeled human observers and associated different metrics. MMF set to be nonlinear combination multiple metrics suitable weights obtained...
In this paper, we focus on the creation of general purpose 2-D image quality databases. Although there are many them, they still lack some important characteristics, such as high-definition resolution, diversified source images, more commonly seen distortions, and a larger amount test (distorted) images. To tackle problem, create database, which has higher resolution than most addition, collect 250 images from 10 categories, far other existing Moreover, generate distortions to represent real...
This paper presents a comparison study on visual quality scores obtained from single-stimulus and double-stimulus approaches for pattern images, respectively. We also conduct the general (non-pattern) which serve as control group. The non-pattern (PNP) images are collected built by Perceptual Data Analysis Processing Laboratory, National Chung Hsing University, evaluated group of people with both approaches. Then, we examine difference mean opinion methods respect to image types, contents...
We proposed a blind image quality assessment model which used classification and prediction for three-dimensional (3D) (denoted as CAP-3DIQA) that can automatically evaluate the of stereoscopic images. First, in stage, separated distorted images into several subsets according to types distortions. This process will assign with same distortion type group. After classified set is fed predictor contains five different perceptual channels predict score individually. Finally, we regression module...
Deep convolutional neural networks (DCNN) have demonstrated their potential to generate reasonable results in image inpainting. Some existing method uses convolution surrounding features, then passes features by fully connected layers, and finally predicts missing regions. Although the final result is semantically reasonable, some blurred situations generated because standard used, which conditioned on effective pixels substitute values masked holes. In this paper, we introduce dense blocks...
Image restoration is a low-level vision task which to restore degraded images noise-free images. With the success of deep neural networks, convolutional networks surpass traditional methods and become mainstream in computer area. To advance performanceof denoising algorithms, we propose blind real image network (SRMNet) by employing hierarchical architecture improved from U-Net. Specifically, use selective kernel with residual block on structure called M-Net enrich multi-scale semantic...
In this paper, we propose a new divide-and-conquer based method, called fusion of multiple binary age-grouping-estimation systems, for human facial age estimation. Under specific constraint, such as given feature or classification/regression what is the better framework estimation? First employ binary-grouping systems group classification. Each face image will be classified into one two groups. Within groups, models are trained to estimate ages faces their respectively. We also investigate...
The recent super-resolution (SR) techniques are divided into two directions. One is to improve PSNR and the other visual quality. We believe improving quality more important practical than blindly PSNR. In this paper we employ a generative adversarial network (GAN) new perceptual loss function for photo-realistic single image (SISR). Our main contributions as follows: propose dense block which uses complex connections between each layer build powerful generator. Next, quality, found set of...
This paper presents a comparison study on subjective quality scores obtained by both single stimulus (without reference) and triple (with methods. The TID2013 database is reevaluated approach, which realized absolute category rating (ACR). And the mean opinion score (MOS) provided along with represents results from triple-stimulus pair (3-stimulus PC) method. In end, correlation coefficient hypothesis testing are used to determine if there significant difference between sets of scores....
In this paper, a deep Convolutional Neural Network CNN based system, called Depthwise Separable (DSCNN) fusion for human facial age estimation is presented. This system includes following four stages. the first stage, data augmentation procedure utilized to enrich dataset. second pre-trained model fine-tuned gender classification task. For third three newly designed DSCNN estimators are conduct gender-specific grouped images from previous stage. The architectures of these DSCNNs constructed...
Image restoration is a challenging and ill-posed problem which also has been long-standing issue. In this paper, we proposed multi-branch model inspired from the Human Visual System (i.e., Retinal Ganglion Cells) for image deraindrop. The experiments show that architecture, called CMFNet, state-of-the-art performance results. source code pretrained models are available at https://github.com/FanChiMao/CMFNet. And interactive demonstration of deraindrop can be accessed https://reurl.cc/dXaeNg.
With the gradually increasing demand for high-resolution images, image super-resolution (SR) technology has become more and important in our daily life. In general, high resolution is often accomplished by accuracy density of sensor. However, such an approach too expensive on design equipment. Particularly, sensor satellites incurs great risks. Inspired EEGAN, some parts networks: Ultra-Dense Subnet (UDSN) Edge-Enhanced (EESN) are modified. The UDSN used to extract features obtain images...
This work presents a novel facial makeup detection method, which includes four steps: entropy information computation, feature extraction, selection and classification. To carry out this objective, first all face images are subject to the computation. Once of faces obtained, extraction step is applied instead original images. The extracted features further processed reduce redundant on vector, done by procedure. A statistical analysis approach chosen realize purpose, aims lower dimension...
Inspired by Gatys and Goodfellow's style transfer generative adversarial network (GAN), we use CycleGAN to achieve age progression. is good at generating fake images also competitive with other GANs. It not only generates but increases the number of in our database. We know better database, performance model. try a deeper generator transform youth photos elder photos. To avoid artifacts, adopt idea "cycle" add new loss which can tell discriminator too strict generated images. Finally,...
In this work, we focus on building style transfer, which transforms ruin or old buildings to modern architecture. Inspired by Gaty's and Goodfellow's transfer generative adversarial network (GAN), use CycleGAN conquer type of problem. As know, image usually generated unexpected artifacts. To avoid the artifacts generate better images, add so called "perception loss" into network, is feature loss extracted VGG pre-trained model. part "cycle" structure, adjust cycle changing ratio weighting...