Jinsoo Cho

Gachon University | kyungwon · Department of Computer Engineering

In this paper, we propose the method for automatically transfers images into tactile maps information based on cognition characteristics of visually impaired persons to more easily provide various image information for visually impaired persons. The proposed method automatically classify color images into row complexity and high complexity based on...

In this paper, we proposed a real-time education assistive technology system based on haptic display to improve education environment of total blindness people. The proposed system consist of a lecture and writing S/W for educator and a previously developed haptic display H/W for total blindness people. The one has the major function which is quick...

As the use of image input and output devices increases, the importance of extracting text area in color images is also increasing. In this paper, in order to extract text area of the images efficiently, we present a text area extraction method for color images based on labeling and gradient difference method. The proposed method first eliminates no...

As projectors become smaller and less expensive, the use of mobile (or portable) projectors is significantly increasing in environments where an ideal white screen is not readily available. Images from mobile projectors in this environment are often reproduced with visually distracting color distortion due to the use of arbitrary colored projection...

The existing methods for creating an object panorama generally have limits in creating an object panorama with various models because the latter depends on a special environment where the model can be rotated to take images. In this paper, a method of creating an object panorama by modeling a new panoramic space based on the photographing environme...

In this paper we propose a geometric image compensation method for a portable projector based on prewarping and optimal projection area generation to compensate for general types of image distortions caused by nonflat projection planes. The proposed method effectively compensated for the distortions.

High-performance algorithm and VLSI architecture for H.264/AVC context-adaptive, variable-length decoder (CAVLD) run before computations are proposed to reduce the computation cycles. The run before values of input symbols are estimated if they are zeroes in parallel. By skipping the estimation step when long symbols starting with '000' are input,...

In this paper, we propose a method for generating a realistic object panorama by considering geometric transformations of camera views in a general photographing environment. In the proposed method, we first model a trumpet-shape panorama space based on geometric transformations of camera, such as vertical rotation and horizontal rotation movement...

In this paper, we propose detail-information browsing, which can form a mesh structure identical to the original model in only the region of interest(ROI) of a user. The proposed method is based on creating a simple level of detail(LOD) model from a D model with the large-scale memory requirements of D model rendering. In our method, first of all,...

Screen adaptive geometric image calibration method is proposed to calibrate the geometric distortions of the image projected on nonflat screen surface, such as inclined, bent, or broken surface. The proposed method can be directly applied to handheld video projector.

In this paper, we propose a method that can compensate the geometric distortions of image caused from an arbitrary nonflat display surface(or wall) under the environment of portable overhead projector without a flat screen. In the proposed method, we first project a grid pattern to an arbitrary nonflat display surface and then derive an equation of...

In this paper, we propose the new method that offer detailed-information through relax the system memory limitation about 3D model to user. That method based on making LOD(Level of Detail) model from huge 3D data of structure cultural assets. In our method as transformed AOSP algorithm, first of all it create the hierarchical structure space about...

In this paper, we propose an automated silhouette extraction method that can effectively extract inner-patterns and silhouettes from 3D scan data of cultural asset. First of all, after creating the edge list of 3D vector data, we decide contour edge and crease edge according to viewpoint. In the next step, after extracting surface silhouette by inv...

The resolution of the latest digital display systems, such as high-definition television (HDTV), has increased, making its visual quality a key selling point in the current consumer electronics market. Color transient improvement (CTI) is the process used to reduce the color edge transition time, so that current market demand for the high quality v...

We propose a VLSI design of Multi-Format Decoder (MFD) to support multiple video codec standards such as MPEG-2, MPEG-4, H. 264 and VC-1. A decoupled MFD architecture is introduced in order to easily add or remove the codecs. The decoupled architecture preserves the stability of the previously designed and verified codecs. It also reduces the gate...

In this paper, we propose the VLSI design of Multi-Format Video Decoder (MFD) to support video codec standards such as MPEG-2, MPEG-4, H.264 and VC-1. The target of the proposed MFD is the Full HD (High Definition) video processing needed for the high-end D-TV SoC (System-on-Chip). The size of the design is reduced by sharing the common large-size...

Edge enhancement of digital images or videos is generally based on a luminance or color transient improvement that reduces the edge transition time. However, it often generates negative side-effects such as overshoot and undershoot. In this paper, we present an adaptively rate-controlled shoot suppression method for suppressing the shoots that occu...

Luminance or color transient improvement is used for enhancing luminance or color edge transition of digital images or videos, but it often suffers from undesirable overshoot and undershoot. In this paper, we present an edge-adaptive local min/max nonlinear filter-based shoot suppression method. The proposed method uses an edge-adaptive local min/m...

Heart disease is one of the more life-threatening diseases. Accurate diagnosis and treatment are central to the survival of patients. Numerous diagnostic methods that can assess abnormalities of the heart have been developed. Among these methods, cardiac functional analysis has been widely used to derive cardiac functional parameters that describe...

The motion of the myocardium is a sensitive indicator of many types of heart disease. Quantitative characterization of this motion is essential for the accurate diagnosis and treatment of heart disease. Although several magnetic resonance imaging (MRI) techniques, such as tagged MRI and phase contrast MRI, provide noninvasive tools to obtain correl...

Segmentation of myocardial boundaries, especially the endocardial boundary, in images from magnetic resonance imaging (MRI) often suffers from flow-related signal loss, partial volume effects, and the presence of papillary muscles. To address these problems, a velocity-aided cardiac segmentation method based a modified active contour model with the...

In this paper, we consider an optimal rate control algorithm for shape coding of emerging MPEG-4 compression system. Current MPEG-4 shape coding consists of two sub-steps; First distortion is introduced by scaling down and up way. Then, second, context-based arithmetic coding is applied. Since the arithmetic coding is "lossless", scaling down and u...

In this paper, we derive an optimal rate control algorithm for shape coding as defined in the forthcoming MPEG-4 international standard. The current MPEG-4 shape coding scheme consists of two steps: first, distortion is introduced by down and up scaling; then, context-based arithmetic encoding is applied. Since arithmetic coding is “lossless”, the...

Ph.D. Committee Chair: Paul J. Benkeser