Kwang-Seok Moon

A Study on Hand Region Detection for Kinect-Based Hand Shape Recognition

Hand shape recognition is a fundamental technique for implementing natural human-computer interaction. In this paper, we discuss a method for effectively detecting a hand region in Kinect-based hand shape recognition. Since Kinect is a camera that can capture color images and infrared images (or depth images) together, both images can be exploited for the process of detecting a hand region. That is, a hand region can be detected by finding pixels having skin colors or by finding pixels having a specific depth. Therefore, after analyzing the performance of each, we need a method of properly combining both to clearly extract the silhouette of hand region. This is because the hand shape recognition rate depends on the fineness of detected silhouette. Finally, through comparison of hand shape recognition rates resulted from different hand region detection methods in general environments, we propose a high-performance hand region detection method.

Implementation of Real Time Video Watermark Embedder Based on Haar Wavelet Transform Using FPGA

In this paper, we propose an applicable technique in the real time applications using FPGA chip implementation technique which can be implemented by Haar wavelet based real time video watermarking for robust watermarking for copyright protection of video contents. Proposed method does algorithm design which can reduce computation complexity for hardware implantation and then implement hardware. In implementation result, we can confirm correct watermark inserting by FPGA simulation tool and cannot recognize concealed watermark in video sequence which insert watermark in original video sequence using implemented hardware watermark embedder system. Our implemented watermark embedding chipcan be useful in movie production and broadcasting companies that requires real-time based copyright protection system.

A new digital video watermarking using the dual watermark images and 3D DWT

We propose the effective video watermarking algorithm to protect the copyright. We use the visible binary image as the watermark. Our watermarking procedure is based on the three-dimensional discrete wavelet transform (3D DWT) and the spread spectrum sequence. We pre-process two watermark images using the mixing and the pseudorandom permutation. After dividing a video sequence into video shots, we perform the 3D DWT. And then, the watermark is embedded into the 3D DWT coefficients considering the robustness and the invisibility. At this time, we use two spread spectrum sequences define as the temporal user key. Experimental results show that the watermarked frames are indistinguishable from the original frames subjectively and the proposed video watermarking algorithm is robust enough against attacks of the low pass filtering, the frame dropping, and the MPEG coding.

Multiple Ship Detection and Tracking Using Background Registration and Morphological Operations

This paper presents a method to accurately detect and monitor ships within the area of interest. It is an advanced version of the previous works done regarding moving ship detection and tracking. The proposed tracking scheme is based on the characteristics of both sea and ship, which includes: background information and local position of the ship. Background subtraction and registration is achieved using morphological ‘Open’ operation and the ships are located using their edge information. The experimental results demonstrate robust and real-time ship detection and tracking with 98.7% detection rate. The proposed algorithm will be useful in coastal surveillance and monitoring applications.

3D CAD Drawing Watermarking Based on Three Components

This paper proposed a watermarking for copyright protection of 3D CAD design drawing based on 3 basic components that are Line, ARC, and 3DFACE. The watermark is embedded into the length in Line, the radius of curvature in Arc, and the length ratio of two sides in 3DFACE. Selecting the embedding component can be done by the distribution of 3D drawing or preference of owners. By experimental result, we confirmed the invisibility of embedded watermarks as well as the robustness in various attacks.

A New Digital Watermarking for Architectural Design Drawing Using LINEs and ARCs Based on Vertex

This paper proposed to digital watermarking technique for architectural design drawing using LINEs and ARCs based on vertex in CAD system to prevent infringement of copyright from unlawfulness reproductions and distribution. After extract LINEs and ARCs from designed drawing, we embed watermarks using adaptive algorithm in each characteristics. Watermarks robust to various attacks like as geometrical transformation as being embedded in LINE’s length and ARC’s angle information. Also, the proposed method satisfies enough transparency about watermarked drawing because have suitable embedding strength to each component. Because handlings that are regarded as attacks of watermarked drawing can consist in CAD program, it used AutoCAD 2002 that is common using as a CAD program for experiments. By experimental result, we confirmed robustness and invisibility of embedded watermarks in several conversions of architectural design drawing.

An efficient video watermarking scheme using adaptive threshold and minimum modification on motion vectors

This paper proposes an efficient video watermarking scheme using adaptive threshold and minimum modification of motion vectors. Our proposed algorithm guarantees the amount of embedded watermark data and minimizes modification of original motion vectors to avoid degradation of video quality without reducing payloads. Besides, our algorithm can embed and retrieve watermark data without any increment of bit rate and original video contents. Experimental result shows that the proposed scheme obtains better video quality than other previous algorithms by about 0.5~1.1dB. Our scheme can be useful to real-time video watermarking which must be compatible to MPEG video coding.

Protecting GIS vector map using the k-means clustering algorithm and odd-even coding

For protecting the copyright of GIS vector map, this paper present a watermarking scheme based on polygon type of ESRI by using k-means clustering algorithm. This watermarking scheme use k-means clustering algorithm to make all polygons into some clusters. Then we embed a watermark bit to the mean distance length of each polygon in a cluster by using odd-even coding. Finally, we change the coordinates of vertices according to the new mean distance length of polygon which has been embedded watermark. From experimental results, we verify that the proposed scheme has outstanding invisibility and good robustness against various geometric attacks.

Implementation of Watermark Detection System for Hardware Based Video Watermark Embedder

In this paper, we implement hardware and software based watermark detection system for hardware based real-time video watermark embedder. We implement a watermark detector with STRATIX FPGA from ALTERA, PCI controller and Microsoft VC# by using Wiener filter and similarity technique for watermark detection. The performance of our implemented system is very good in term of visibility and robustness. Our implemented watermark detection system can be useful in movie production and broadcasting companies that requires real-time based copyright protection system.

Acute lymphoid leukemia classification using two-step neural network classifier

Leukemia induced death has been listed in the top ten most dangerous mortality cause for human being. Among many reasons, one of them is the slow decision-making process which make suitable medical treatment cannot be applied on time. Therefore, good clinical decision support system for acute leukemia type classification has always become necessity. In this paper, the author proposed a novel approach to perform acute leukemia type classification using sequential neural network classifier. Our experimental result only cover the first classification process which shows an excellent performance in differentiating normal and abnormal cells. Further research is needed to proof the second neural network classifier effectiveness performance.