Se-Yun Kim

Curvature based ECG signal compression for effective communication on WPAN

As electrocardiogram (ECG) signals are generally sampled with a frequency of over 200 Hz, a method to compress diagnostic information without losing data is required to store and transmit them efficiently on a wireless personal area network (WPAN). In this paper, an ECG signal compression method for communications on WPAN, which uses feature points based on curvature, is proposed. The feature points of P, Q, R, S, and T waves, which are critical components of the ECG signal, have large curvature values compared to other vertexes. Thus, these vertexes were extracted with the proposed method, which uses local extrema of curvatures. Furthermore, in order to minimize reconstruction errors of the ECG signal, extra vertexes were added according to the iterative vertex selection method. Through the experimental results on the ECG signals from Massachusetts Institute of Technology-Beth Israel hospital arrhythmia database, it was concluded that the vertexes selected by the proposed method preserved all feature points of the ECG signals. In addition, it was more efficient than the amplitude zone time epoch coding method.

Minimizing Algorithm of Baseline Wander for ECG Signal using Morphology-pair

The baseline wander is most fatal noise, because it obstructs reliable diagnosis of cardiac disorder. Thus, in this paper, the morphology-pair is proposed for estimation of baseline wander except P, T-wave and QRS-complex. Proposed Morphology-pair is able to except P, R, T-wave which have characteristics of local maxima. Likewise Q, S-wave such as local minima are excepted by proposed Morphology-pair. The final baseline wander eliminated ECG signal is deducted by subtraction of original ECG and estimated baseline wander. The experimental results based on the MIT/BIH database show that the proposed algorithms produce promising results.

A Development of the TFT-LCD Image Defect Inspection Method Based on Human Visual System

The TFT-LCD image has non-uniform brightness that is the major difficulty of finding the visible defect called Mura in the field. To facilitate Mura detection, background signal shading should level off and Mura signal must be amplified. In this paper, Mura signal amplification and background signal flattening method is proposed based on human visual system (HVS). The proposed DC normalized contrast sensitivity function (CSF) is used for the Mura signal amplification and polynomial regression (PR) is used to level off the background signal. In the enhanced image, tri-modal thresholding segmentation technique is used for finding Dark and White Mura at the same time. To select reliable defect, falsely detected invisible region is eliminated based on Webers Law. By the experimental results of artificially generated 1-d signal and TFT-LCD image, proposed algorithm has novel enhancement results and can be applied to real automated inspection system.

Intensity Flow Estimation of Thin Film Transistor Liquid Crystal Display Panel Surface Image Using Multiweighted Morphology Pairs

In this paper, we present a new image enhancement method for a vision-based automated defect inspection system on the surface image of a thin film transistor liquid crystal display (TFT-LCD) panel. The TFT-LCD image has nonuniform brightness, which is a major difficulty in finding defective regions. The proposed method effectively estimates the nonuniform intensity variation except in defective regions using multiweighted morphological filters. After estimation, defects can be segmented easily using difference from the original image. Experimental results verified the performance of the proposed method.

Design of a SIFT based Target Classification Algorithm robust to Geometric Transformation of Target

This paper proposes a method for classifying targets robust to geometric transformations of targets such as rotation, scale change, translation, and pose change. Targets which have rotation, scale change, and shift is firstly classified based on CM(Confidence Map) which is generated by similarity, scale ratio, and range of orientation for SIFT(Scale-Invariant Feature Transform) feature vectors. On the other hand, DB(DataBase) which is acquired in various angles is used to deal with pose variation of targets. Range of the angle is determined by comparing and analyzing the execution time and performance for sampling intervals. We experiment on various images which is geometrically changed to evaluate performance of proposed target classification method. Experimental results show that the proposed algorithm has a good classification performance.

Abnormality Detection of ECG Signal by Rule-based Rhythm Classification

Low misclassification performance is significant with high classification accuracy for a reliable diagnosis of ECG signals, and diagnosing abnormal state as normal state can especially raises a deadly problem to a person in ECG test. In this paper, we propose detection and classification method of abnormal rhythm by rule-based rhythm classification reflecting clinical criteria for disease. Rule-based classification classifies rhythm types using rule-base for feature of rhythm section, and rule-base deduces decision results corresponding to professional materials of clinical and internal fields. Experimental results for the MIT-BIH arrhythmia database show that the applicability of proposed method is confirmed to classify rhythm types for normal sinus, paced, and various abnormal rhythms, especially without misclassification in detection aspect of abnormal rhythm.

Double Self Quotient Image Based Image Flattening for Defect Detection in Thin Film Transistor Liquid Crystal Display Panel

This paper presents the results of using self quotient image (SQI) to flatten the background region of a thin film transistor liquid crystal display image. To overcome an inherent shortcoming of SQI method, namely the halo effect in thin film transistor liquid crystal display images, double SQI method is introduced. Experimental results demonstrate that SQI can be used effectively to eliminate a non-uniformity of the background region in a test image.

Fourier spectrum based periodic cell pattern elimination in thin film transistor liquid crystal display cell image

This paper presents a hardware that inspects defects on TFT-LCD cell modules and packed in a PCI-board equipped with FPGA and DSP processors. Images of TFT-LCD cell modules normally contain periodic cell patterns which make it difficult to detect defects. We propose an efficient and powerful algorithm for elimination of the cell pattern using magnitude spectrum analysis.

Target extraction in FLIR image using Bi-modality of local characteristic and Chamfer distance

In this paper, target extraction method in FLIR(forward-looking infrared) images based on fuzzy thresholding which used bi-modality and adjacency to determine membership value is proposed. The bi-modality represents how a pixel is classified into a part of target using distribution of pixel values in a local region, and The adjacency is a measure to represent how each pixel is far from the target region. First, membership value is calculated using above two measures, and then fuzzy thresholding is performed to extract the target. To evaluate performance of proposed target extraction method, we compare other segmentation methods using various FLIR tank image. Experimental results show that the proposed algorithm is a good segmentation performance.

TFT-LCD Defect Detection Using Multi-level Threshold and Probability Density Function

TFT-LCD image consists of ununiform background, random noises and target defect signal components. Defects in TFT-LCD have some intensity variations compared to background region. It is sometimes difficult for human inspectors to figure out. In this paper, we propose multi-level threshold scheme for detection of the real defect using probability density function with Parzen Window. The experimental results show that the proposed algorithms produce promising results and can be applied to automated inspection systems for finding defects in the TFT-LCD image.