Browsing by Author "Tseng, Chen-Yu"

Now showing 1 - 8 of 8

A CELL-BASED MATTING LAPLACIAN FOR CONTRAST ENHANCEMENT
(2012)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
While various kinds of local tone mapping approaches have been proposed for contrast enhancement, how to automatically recovering overly bright and/or overly dark regions in an image without introducing extra artifacts still remains a challenging problem. Conventional approaches usually apply a translation-invariant filter to decompose the contrast information of an image into a global component and a detailed component and then adjust the contrast components according to some preselected criteria. However, the use of translation-invariant filter makes it hard to adaptively decompose the contrast information based on local image contents. To overcome this problem, we derive a global optimization approach with the use of cell-based matting Laplacian matrix to obtain more accurate decomposition. Besides, for the adjustment of contrast component, we present a spatially varying gamma adjustment approach that can locally recover poorly exposed regions and properly enhance contrast detail. This translation-varying approach can successfully suppress the halo artifacts without the loss of image details.
Digital Image Restoration for Phase-Coded Imaging Systems
(2010)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
Chang, Chir-Weei
;
Chen, Po-Chang
;
Chang, Chuan-Chung
This paper proposes a digital image restoration algorithm for phase-coded imaging systems. In order to extend the depth-of-field (Dof), an imaging system equipped with a properly designed phase-coded lens can achieve an approximately constant point spread function (PSF) for a wide range of depths. In general, a phase-coded imaging system produces blurred intermediate images and requires subsequent restoration processing to generate clear images. For lowcomputational consumer applications, the kernel size of the restoration filter is a major concern. To fit for practical applications, a pyramid-based restoration algorithm is proposed in which we decompose the intermediate image into the form of Laplacian pyramid and perform restoration over each level individually. This approach provides the flexibility in filter design to maintain manufacturing specification. On the other hand, image noise may seriously degrade the performance of the restored images. To deal with this problem, we propose a Pyramid-Based Adaptive Restoration (PBAR) method, which restores the intermediate image with an adaptive noise suppression module to improve the performance of the phase-coded imaging system for Dof extension.
Image Detail and Color Enhancement Based on Channel-wise Local Gamma Adjustment
(2009)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
Lai, Yueh-Yi
;
Zhou, Yi-Cai
;
電子工程學系及電子研究所
This paper proposes a novel local gamma adjustment algorithm to virtually expand the dynamic range of displayed images. Image details are automatically enhanced based on the estimation of local image details in the original image. By individually adjusting the local gamma value over the R, G, and B color channels, image colorfulness can also be enhanced. The proposed algorithm requires low computational complexity and may provide enhancement results comparable to, or even better than, manually adjusted images.
Image Enhancement Based on Gamma Map Processing
(2010)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
Chen, Yi-An
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
This paper proposes a novel image enhancement technique based on Gamma Map Processing (GMP). In this approach, a base gamma map is directly generated according to the intensity image. After that, a sequence of gamma map processing is performed to generate a channel-wise gamma map. Mapping through the estimated gamma, image details, colorfulness, and sharpness of the original image are automatically improved. Besides, the dynamic range of the images can be virtually expanded.
Learning-Based Hierarchical Graph for Unsupervised Matting and Foreground Estimation
(2014-12-01)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
Automatically extracting foreground objects from a natural image remains a challenging task. This paper presents a learning-based hierarchical graph for unsupervised matting. The proposed hierarchical framework progressively condenses image data from pixels into cells, from cells into components, and finally from components into matting layers. First, in the proposed framework, a graph-based contraction process is proposed to condense image pixels into cells in order to reduce the computational loads in the subsequent processes. Cells are further mapped into matting components using spectral clustering over a learning based graph. The graph affinity is efficiently learnt from image patches of different resolutions and the inclusion of multiscale information can effectively improve the performance of spectral clustering. In the final stage of the hierarchical scheme, we propose a multilayer foreground estimation process to assemble matting components into a set of matting layers. Unlike conventional approaches, which typically address binary foreground/background partitioning, the proposed method provides a set of multilayer interpretations for unsupervised matting. Experimental results show that the proposed approach can generate more consistent and accurate results as compared with state-of-the-art techniques.
Shape-From-Focus Depth Reconstruction With a Spatial Consistency Model
(2014-12-01)
Tseng, Chen-Yu
;
Wang, Sheng-Jyh
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
This paper presents a maximum a posteriori (MAP) framework to incorporate a spatial consistency prior model for depth reconstruction in the shape-from-focus (SFF) process. Existing SFF techniques, which reconstruct a dense 3-D depth from multifocus image frames, usually have poor performance over low-contrast regions and usually need a large number of frames to achieve satisfactory results. To overcome these problems, a new depth reconstruction process is proposed to estimate the depth values by solving an MAP estimation problem with the inclusion of a spatial consistency model. This consistency model assumes that within a local region, the depth value of each pixel can be roughly predicted by an affine transformation of the image features at that pixel. A local learning process is proposed to construct the consistency model directly from the multifocus image sequence. By adopting this model, the depth values can be inferred in a more robust way, especially over low-contrast regions. In addition, to improve the computational efficiency, a cell-based version of the MAP framework is proposed. Experimental results demonstrate the effective improvement in accuracy and robustness as compared with existing approaches over real and synthesized image data. In addition, experimental results also demonstrate that the proposed method can achieve quite impressive performance, even with only the use of a few image frames.
SINGLE-IMAGE 3-D DEPTH ESTIMATION FOR URBAN SCENES
(2013-01-01)
Cheng, Hsin-Min
;
Tseng, Chen-Yu
;
Hsin, Cheng-Ho
;
Wang, Sheng-Jyh
;
電子工程學系及電子研究所
In this paper, we focus on recovering a 3-D depth map from a single image. Given an image of urban scene, we extract linear perspective information to establish the 3-D scene model. Unlike approaches which use only occlusion relationship between objects to estimate the relative depth of the image, we further combine the perspective geometry information with the occlusion relationship between objects. Besides, we propose the construction of depth gradient maps to represent the depth variation trend along the vertical and horizontal directions. The image is first partitioned into geometric components and initial depth gradient maps are generated based on the relative position between the vanishing point and the classified components. Incorporating main directions of vanishing lines and occlusion boundaries in the initial depth gradient maps, a refined depth map is obtained by using a CRF (conditional random field) model. We demonstrate that our approach can produce realistic relative depth maps for images of urban scenes.
UNSUPERVISED HIERARCHICAL IMAGE SEGMENTATION BASED ON BAYESIAN SEQUENTIAL PARTITIONING
(2015)
Yeh, Hao-Wei
;
Tseng, Chen-Yu
;
Wu, Tung-Yu
;
Wang, Sheng-Jyh
;
電子工程學系及電子研究所
In this paper, we present an unsupervised hierarchical image segmentation algorithm based on a split-and-merge scheme. In the split phase, we propose an efficient partition algorithm, called Just-Noticeable-Difference Bayesian Sequential Partitioning (JND-BSP), to partition image pixels into a few regions, within which the color variations are perceived to be smoothly changing without apparent color differences. In the merge phase, we propose a simple but effective merging criterion to sequentially construct a hierarchical structure that represents the relative similarity among these partitioned regions. Instead of generating a segmentation result with a fixed number of segments, the new algorithm produces an entire hierarchical representation of the given image in a single run. This hierarchical representation is informative and can be very useful for subsequent processing, like object recognition and scene analysis. To demonstrate the effectiveness and efficiency of our method, we compare our new segmentation algorithm with several existing algorithms. Experiment results show that our new algorithm can not only offers a more flexible way to segment images but also provides segmented results close to human\'s visual perception.