-
Article
Siamese Dense Network for Reflection Removal with Flash and No-Flash Image Pairs
This work addresses the reflection removal with flash and no-flash image pairs to separate reflection from transmission. When objects are covered by glass, the no-flash image usually contains reflection, and t...
-
Article
Deep feature embedding learning for person re-identification based on lifted structured loss
Person re-identification (re-id) aims at matching the same individual in videos captured by multiple cameras, and much progress has been made in recent years due to large scale pedestrian data sets and deep le...
-
Chapter and Conference Paper
Multiple Connected Residual Network for Image Enhancement on Smartphones
Image enhancement on smartphones needs rapid processing speed with comparable performance. Recently, convolutional neural networks (CNNs) have achieved outstanding performance in image processing tasks such as...
-
Chapter and Conference Paper
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones. The challenge consisted of two tracks. In the first one, partic...
-
Article
A fast deconvolution-based approach for single-image super-resolution with GPU acceleration
In this paper, we propose fast deconvolution-based image super-resolution (SR) with graphics processing unit (GPU)-accelerated computation. Recently, the deconvolution-based single-image SR has been proven to ...
-
Article
Perceptual multi-exposure image fusion with overall image quality index and local saturation
Realistic rendering of natural scenes captured by digital cameras is the ultimate goal of image processing. In recent years, high dynamic range (HDR) imaging has received increasing attention for producing hig...
-
Article
Korean-English bilingual videotext recognition for news headline generation based on a split-merge strategy
This paper deals with Korean-English bilingual videotext recognition for news headline generation. Because videotext contains semantic content information, it can be effectively used for understanding videos. ...
-
Article
Learning to Rank with Ensemble Ranking SVM
In this paper, we propose a novel learning to rank method using Ensemble Ranking SVM. Ensemble Ranking SVM is based on Ranking SVM which has been commonly used for learning to rank. The basic idea of Ranking S...
-
Article
2D to 3D conversion with motion-type adaptive depth estimation
2D to 3D conversion is an important task for 3DTV broadcasting services due to the lack of stereoscopic 3D contents. In this paper, we propose 2D to 3D conversion with motion-type adaptive depth estimation. B...
-
Article
Adaptive Constraint Propagation for Semi-Supervised Kernel Matrix Learning
We propose adaptive constraint propagation (ACP) for semi-supervised kernel matrix learning (SS-KML). SS-KML aims to learn a kernel matrix from the given samples which contains just a little supervised informa...
-
Chapter and Conference Paper
Blocking Artifact Reduction in DIBR Using an Overcomplete 3D Dictionary
It has been reported that the image quality and depth perception rates are undesirably decreased by compression in DIBR. This is because high-frequency components are filtered by compression, and thus several ...
-
Chapter and Conference Paper
Illumination Invariant Eye Detection in Facial Images Based on the Retinex Theory
Eye detection plays an important role in face recognition because eye features provide a high recognition rate. However, illumination effects such as heavy shadows and drastic lighting change make it difficult...
-
Chapter and Conference Paper
Specular Highlight Removal Using Reflection Component Separation and Joint Bilateral Filtering
We provide a novel specular highlight removal method using reflection component separation and joint bilateral filtering. In general, highlights in images can be represented as the linear combination of diffus...
-
Chapter and Conference Paper
New Optical Flow Approach for Motion Segmentation Based on Gamma Distribution
This paper provides a new motion segmentation algorithm in image sequences based on gamma distribution. Conventional methods use a Gaussian mixture model (GMM) for motion segmentation. They also assume that th...
-
Chapter and Conference Paper
Automatic Segmentation of Non-rigid Objects in Image Sequences Using Spatiotemporal Information
This paper provides an automatic segmentation method of non-rigid objects in image sequences. The non-rigid objects have fuzzy, blurred, and indefinite boundaries such as smoke and clouds, and are random and u...
-
Chapter and Conference Paper
A Novel Approach for Bayesian Image Denoising Using a SGLI Prior
This paper provides an effective prior for image denoising in a Bayesian framework. The prior combines two well-known discontinuity measures which have been used in illumination normalization methods. We make ...
-
Chapter and Conference Paper
A Video Summarization Method for Basketball Game
There have been various research efforts on automatic summarization of sports video. However, most previous works were based on event detection and thus cannot reflect the semantic importance of scenes and con...
