Eui Chul Lee

Illumination Normalization for SIFT Based Finger Vein Authentication

Recently, the biometric information such as faces, fingerprints, and irises has been used widely in a security system for biometric authentication. Among these biometric features which are unique to each individual, the blood vessel pattern in fingers is superior for identifying individuals and verifying their identities: We may obtain easily the information on blood vessels which is almost impossible to counterfeit because the pattern exists inside the body unlike the others. In this work, we propose a finger vein recognition method using an illumination normalization and a SIFT (Scale-Invariant Feature Transform) matching identification. To verify individual identification, the proposed methodology is composed of two steps: (i) we first normalize the illumination of finger vein images, and (ii) extract SIFT descriptors from the image and match them to the given data. Experimental results indicate that the proposed method is shown to be successful for authentication system.

A Multimodal Biometric Recognition of Touched Fingerprint and Finger-Vein

multimodal biometric systems have been widely used to overcome the limitation of unimodal biometric systems and to achieve high recognition accuracy. However, users feel inconvenience because most of the multimodal systems require several steps in order to acquire multimodal biometric data, which also requires the specific behaviors of users. In this research, we propose a new multimodal biometric recognition of touched fingerprint and finger-vein. This paper is novel in the following four ways. First, we can get a fingerprint and a finger-vein image at the same time by the proposed device, which acquires the fingerprint and finger-vein images from the first and second knuckles of finger, respectively. Second, the devices size is so small that we can adopt it on a mobile device, easily. Third, fingerprint recognition is done based on the minutia points of ridge area and finger-vein recognition is performed based on local binary pattern (LBP) with appearance information of finger area. Fourth, based on decision level fusion, we combined two results of fingerprint and finger-vein recognition. Experimental results confirmed the efficiency and usefulness of the proposed method.

A study on eye gaze estimation method based on cornea model of human eye

In this paper, we propose a new gaze estimation method by analyzing the cornea surface model which is estimated through three dimensional analysis of human eye in HMD (Head Mounted Display) environments. This paper has four advantages over previous works. First, in order to obtain accurate gaze position, we use a cornea sphere model based on Gullstrand eye scheme. Second, we calculate the 3D position of the cornea sphere and a gaze vector by using a camera, three collimated IR-LEDs and one illuminated IRLED. Third, three coordinates such as camera, monitor and eye coordinates are unified, which can simplify the complex 3D converting calculation and allow for calculation of the 3D eye position and gaze position on a HMD monitor. Fourth, a simple user dependent calibration method is proposed by gazing at one position of HMD monitor based on Kappa compensation. Experimental results showed that the average gaze estimation error of the proposed method was 0.89 degrees.

EEG Based Comparative Measurement of Visual Fatigue Caused by 2D and 3D Displays

Visual fatigue is a very important issue of display market to implementing more comfortable display device in terms of human factor. This study is performed in order to measure the visual fatigue using objective evaluation method (i.e., EEG) in 3D display environment. We performed the difference of visual fatigue using a subjective method and compared it to an objective measure. As a result, the 3D content affected the power of brain wave in the beta frequency (14-25 Hz). Beta power was more strong at the viewing the 3D contents. Also, subjective result also showed more strong visual fatigue in the 3D condition than in the 2D condition. We found that visual fatigue significantly appeared amount of power in the beta band between stereoscopic (3D) image and 2D image.

Object Recognition and Selection Method by Gaze Tracking and SURF Algorithm

The goal of this research is to make a robust camera vision system which can help those with disabilities of their hands and feet to select and control home appliances. The proposed method operates by object recognition and awareness of interest by gaze tracking. Our research is novel in the following three ways compared to previous research. First, in order to track the gaze position accurately, we designed a wearable eyeglasses type device for capturing the eye image using a near-infrared (NIR) camera and illuminators. Second, in order to achieve object recognition in the frontal view, which represents the facial gaze position in the real world, an additional wide view camera is attached to the wearable device. Third, for the rapid feature extraction of the objects in the wide view camera, we use the speeded-up robust features (SURF) algorithm, which is robust to deformations such as image rotation, scale changes, and occlusions. The experimental results showed that we obtained a gaze tracking error of only 1.98 degrees and successful matching results of object recognition.

Individual Emotion Classification between Happiness and Sadness by Analyzing Photoplethysmography and Skin Temperature

Since emotion technology has been applied into numerous applications, the role of recognizing human emotion has become more important. In this paper, two autonomic nervous signals such as SKT and PPG were analyzed in order to extract 2D emotional feature vector (PPI and SKT amplitude) for classification between happy and sad emotions. A support vector machine was adopted for non-linear classification between happiness and sadness. We collected SKT and PPG signals from 5 undergraduates who respectively watched two different kinds of video inducing happiness and sadness. At result, the classification accuracy of 92.41% was obtained by combining two features through using support vector machine which was even more increased result compared with the results using single feature such as SKT (89.29%) and PPG (63.67%).

VISION-BASED GAZE ESTIMATION METHOD FOR STEREOSCOPIC DISPLAY SYSTEMS

Abstract In this paper, we propose a new near infra-red (IR) vision-based gaze tracking method, which is not affected by facial movements in stereoscopic virtual reality (VR) systems. Our proposed method has following five novelties compared to previous works. (i) By using our gaze tracker instead of a conventional input device, users felt more interested and immersed in the stereoscopic VR system, (ii) by using an IR light passing filter and an IR illuminator, we were able to implement a robust gaze tracker irrespective of environmental lighting conditions, (iii) we used the simple 2D based eye and face gaze estimation method without considering the complicated 3D structure and motion of human eye and face, which could reduce the system complexities, (iv) to prevent the unintended movement of gaze position by natural eye blinking, we discriminated the eye blinking by measuring pupil size. And this information was used for button clicking and mode toggling based on the analysis of users fatigue. That is, the measured fatigue information of user was used for the mode toggling between gaze tracking mode and the conventional mouse input mode, (v) the proposed method allowed the natural movement of users head by tracking the IR rhombus-shaped pattern, which was not affected by the change of environmental lighting. Experimental results showed that the gaze estimation accuracy of the proposed method was 0.98 degrees. In addition, the subjective tests showed that the VR application using the proposed method was more interesting and immersive to users than those using conventional input devices.

A new objective visual fatigue measurement system by using a remote infrared camera

This paper presents a new objective visual fatigue measurement system by using one remote camera. In captured image, eye and pupil regions are sequentially detected using some image processing methods. Based on the pupil region, pupil size, pupil accommodation speed, blink frequency, and eye closed duration can be determined. Because more frequent blinks and slower pupil accommodation indicate an increased level of visual fatigue, our system can objectively measure visual fatigue. Also, since there is no need to wear any device, inconvenience may be minimized. Experimental results showed the blink detection accuracy was 98.9% and pupil localization error was 1.9%.

Intelligent Query by Humming System

This research proposes new system which finds the music by using Query-by-Humming (QBH). For finding a stored music, the features of humming data are selected by using G.729 feature extractor. We normalize the extracted features by using mean-shifting, median filtering, average filtering and min-max scaling methods. Then the corresponding music is matched based on dynamic time warping (DTW) algorithm. As experiment, we compared the matching performance by using the database of Roger Jangs Corpus in MIREX.

Color correction using rotation matrix for HDR rendering in iCAM06

Recently, a new image appearance model called iCAM06 was designed for high dynamic range (HDR) image rendering. Most of the HDR rendering algorithms include many color space transformations from RGB of input image to RGB of output devices for HDR rendering. The iCAM06, the representative HDR rendering algorithm, also contains several color space conversion steps during the processes of chromatic adaptation, tone compression, and etc. However, frequent color space changes of the iCAM06 cause hue shift and color distortion of the output image. To solve these problems, we propose the hue shift correction step using the rotation matrix and reduce the hue change of the output images in the iCAM06. In this paper, the rotation matrix for the hue shift correction is calculated on relationship between the input and output tristimulus value. And experimental results show that the proposed method has high hue accuracy compared to the default iCAM06.