CVLab COMPUTER VISION LAB

National Tsing Hua University


Image Deblurring

59_cover
Fri, 20 Jul 2018 - intern_james
Blind Image Deblurring with Modified Richardson-Lucy Deconvolution for Ringing Artifact Suppression
Hao-Liang Yang, Yen-Hao Chiao, Po-Hao Huang, Shang-Hong Lai
In this paper, we develop a unified image deblurring framework that consists of both blur kernel estimation and non-blind image deconvolution. For blind kernel estimation, we propose a patch selection procedure and integrate it with a coarse-to-fine kernel estimation algorithm to develop a robust blur kernel estimation algorithm. For the non-blind image deconvolution, we modify the traditional Richardson-Lucy (RL) image restoration algorithm to suppress the notorious ringing artifact in the regions around strong edges. Experimental results on some real blurred images are shown to demonstrate the improved efficiency and image restoration by using the proposed algorithm.
15_cover
Sun, 21 Nov 2010 - herman
Image Deblurring by Exploting Inherent Bi-Level Regions
Po-Hao Huang, Yu-Mo Lin, Hao-Liang Yang, Shang-Hong Lai
We propose an image restoration framework for restoring an image degraded by unknown motion blur. Our approach takes advantage of inherent bi-level regions of an image to estimate a blur kernel. The framework contains three parts: bi-level region searching, initial blur kernel estimation and iterative maximum a posteriori (MAP) image restoration. Firstly, candidate bi-level regions are located around the detected corners. We use four image features to score each region and choose the best N regions for estimating an initial blur kernel. Finally, an alternating minimization algorithm is developed to iteratively refine both the blur kernel and the restored image. Experimental results of synthetic and real blurred images are shown to demonstrate the performance of the proposed algorithm.
ICIP09 Image Deblurring by Exploting Inherent Bi-Level Regions (pdf)

Medical Imaging

75_cover
Mon, 23 Jul 2018 - intern_james
Reconstruction of 3D Vertebrae and Spinal Cord Models from CT and STIR-MRI Images
C. Yen, H.-R. Su and S.-H. Lai
In this paper, we propose a system that integrates vertebrae, spinal cord and nerves segmentation results from STIR-MRI and CT images, by estimating the transformation relationship between the segmented vertebra models extracted from these two types of images. Since the segmentation results are already obtained, we build the 3D spinal cord and nerves model. Then we apply a deformable registration algorithm to register the pre-built 3D vertebra models in CT and STIR-MRI. Thus, we apply the local affine transformation to integrate STIR-MRI spinal cord and nerves information with CT vertebrae. This is accomplished by applying a linear interpolation method to achieve the purpose of local affine transformation. In the experimental results, we show the 3D segmentation results of spinal nerve from the STIR-MRI (Short Tau Inversion Recovery - Magnetic Resonance Imaging) images, and also show the integrated 3D spine models from CT and STIR-MRI images.
72_cover
Mon, 23 Jul 2018 - intern_james
3D Liver Segmentation and Model Reconstruction from CT Images
Y. Y. Cheng, H. M. Chang, H. R. Su, S. H. Lai, K. C. Liu and C. H. Lin.
In this paper, we present a system for segmenting the 3D liver region from CT images and reconstructing its 3D model. The segmentation is accomplished in 3-D space which is extended from the user controlled 2-D random walker technique and implemented by a slice-section method. After obtaining the 3D liver segmentation result, we apply the surface reconstruction algorithm based on bipartite polar classification to build the 3-D liver surface model. In the experimental results, we apply the proposed algorithm to ten test CT datasets to evaluate its accuracy and we demonstrate the good accuracy compared with the human labeled results.
71_cover
Mon, 23 Jul 2018 - intern_james
3D Spinal Cord and Nerves Segmentation from STIR-MRI
C. Yen, H.R. Su, S.H. Lai, K.C. Liu, R.R. Lee
In this paper, we present a system for spinal cord and nerves segmentation from STIR-MRI. We propose an user interactive segmentation method for 3D images, which is extended from the 2D random walker algorithm and implemented with a slice-section strategy. After obtaining the 3D segmentation result, we build the 3D spinal cord and nerves model for each view using VTK, which is an open-source, freely available software. Then we obtain the point cloud of the spinal cord and nerves surface by registering the three surface models constructed from three STIR-MRI images of different directions. In the experimental results, we show the 3D segmentation results of spinal cord and nerves from the STIR-MRI (Short Tau Inversion Recovery - Magnetic Resonance Imaging)images in three different views, and also display the reconstructed 3D surface model.
62_cover
Fri, 20 Jul 2018 - intern_james
Texture Feature Analysis of Ultrasonic Images with Wryneck
Hsiao-Mei Chang, Ya-Yun Cheng, Hong-Ren Su, Shang-Hong Lai, Chu-Hsu Lin, and Hung-Chih Hsu
Torticollis, also called wryneck, is a clinical sign or symptom that could be the result of a variety of possible disorders. Among the etiologies, congenital muscular torticollis (CMT) with impairment of the sternocleidomastoid (SCM) is the most frequent cause of torticollis in infants. Infants with CMT have the symptom of head tilt to one side, which is often combined with rotation of the head to the opposite side. In this paper, we report a study on the analysis of the ultrasonic images on two sides of the neck for the CMT classification. To this end, we first apply an interactive ROI segmentation procedure, followed by the extraction of several different texture features for the classification of CMT type. We use three types of texture features, including gray-lever co-occurrence matrix, Laplacian of Gaussian, and Gabor features. In addition, three feature comparison methods, such as mutual information, Bhattacharyya Distance, and Kullback-Leibler divergence, are used to compute the distribution distances for different texture features and feed them into the support vector machine classifier for the CMT classification. Experimental results demonstrate the performance of the proposed image analysis and classification method on real ultrasonic images.
58_cover
Fri, 20 Jul 2018 - intern_james
CT-MR image registration in 3D K-Space based on Fourier moment matching
H.-R. Su and S.-H. Lai
CT-MRI registration is a common processing procedure for clinical diagnosis and therapy. We propose a novel K-space affine image registration algorithm via Fourier moment matching. The proposed algorithm is based on estimating the affine matrix from the moment relationship between the corresponding Fourier spectrums. This estimation strategy is very robust because the energy of the Fourier spectrum is mostly concentrated in the low-frequency band, thus the moments of the Fourier spectrum are robust against noises and outliers. Our experiments on the real CT and MRI datasets show that the proposed Fourier-based registration algorithm provides higher registration accuracy than the existing mutual information registration technique.
35_cover
Thu, 25 Nov 2010 - rily
Compensation of Motion Artifacts in MRI via Graph-Based Optimization
Tung-Ying Lee, Hong-Ren Su, Shang-Hong Lai, and Ti-chiun Chang
In two-dimensional Fourier transform magnetic resonance imaging (2DFT-MRI), patient/object motion during the image acquisition results in ghosting and blurring. These motion artifacts are commonly considered as a major limitation in the MRI community. To correct these artifacts without resorting to additional navigator echoes, most existing methods perform image quality measure to estimate motion; but they may easily fail when the motion is large. Viewed as a blind image restoration problem where the motion point spread function (PSF) is unknown, state-of-the-art restoration algorithms can not be easily applied because they cannot handle a complex PSF kernel that has the same size as the image. To overcome these challenges, we propose a novel approach that exploits the image structure to segment the kernel into several fragments. Based on this kernel representation, determining a kernel fragment can be formulated as a binary optimization problem, where each binary variable represents whether a segment in MR signals is corrupted by a certain motion or not. We establish a graphical model for these variables and estimate the kernel by minimizing an energy functional associated with the model. Experimental results show that the proposed method can provide satisfactory compensation of motion artifacts even when large motions are involved in the MR images.

OCR

Camera Calibration

74_cover
Mon, 23 Jul 2018 - intern_james
Rolling shutter correction for video with large depth of field
Yen-Hao Chiao, Tung-Ying Lee, Shang-Hong Lai
Rolling shutter correction has attracted considerable attention in recent years. Several algorithms have been proposed to correct the distortion. Previous methods on rolling shutter correction did not consider depth variations in the scene. In this work, we overcome the limitation of the previous works that the depth of field in the scene is small. We present a correction model for rectifying the rolling shutter video based on the depth maps estimated from the rolling shutter video. In addition, we propose a two-stage optimization algorithm to estimate the temporal camera motion and the associated depth maps. Experimental results show the improvement of the proposed rolling shutter correction algorithm that takes the depth information into account.
66_cover
Fri, 20 Jul 2018 - intern_james
Real-Time Correction of Wide-Angle Lens Distortion for Images with GPU Computing
Tung-Ying Lee, Chen-Hao Wei, Shang-Hong Lai, and Ruen-Rone Lee
Wide-angle lens provides a broad field of view which benefits some applications, such as video surveillance or endoscopic imaging. However, it also induces lens distortion, especially radial distortion, which may impede further video analysis or perceptual interpretation. For some applications, such as minimally invasive surgery and visual surveillance, realtime correction of image distortion is required. Traditional CPU-centric machines are difficult to achieve the requirement of real-time computation because of a large amount of computation. In this paper, we propose to achieve real-time correction of wide-angle lens distortion of images on several target platforms. In the GPGPU platform, we achieve real-time correction at fullHD resolution by using CUDA. For middle-end devices, an error-controllable mesh is used and the system is implemented by industry standard, OpenGL. We also implement it with OpenGL ES on embedded GPUs for mobile devices. Experiments show using our error-controllable mesh greatly outperforms those using regularly downsampled meshes
43_cover
Thu, 19 Jul 2018 - intern_james
Wide Angle Distortion Correction by Hough Transform and Gradient Estimation
T.-Y. Lee, T.-S. Chang, and S.-H. Lai
Wide-angle cameras have been widely used in surveillance and endoscopic imaging. An automatic distortion correction method is very useful for these applications. Traditional methods extract corners or curved straight lines for estimating distortion parameters. Hough transform is a powerful tool to assess straightness. However, previous methods usually require some human intervention or only focus on using a single curve. In this paper, we propose a new method based on Hough transform by considering all curves into the estimation of distortion parameters. By considering the relationship between distortion parameters and curves, our method is fully automatic and does not require manual selection of curves in an image. Experiments on synthetic and real datasets have been conducted. The results of our method are also compared with other Hough Transform based methods in quantitative measures. The experimental results show that the accuracy of the proposed automatic method is comparable to those of other manual line-based methods.