Sun-Tae Chung

Iris recognition using a low level of details

This paper describes a new iris recognition algorithm, which uses a low level of details. Combining statistical classification and elastic boundary fitting, the iris is first localized. Then, the localized iris image is down-sampled by a factor of m, and filtered by a modified Laplacian kernel. Since the output of the Laplacian operator is sensitive to a small shift of the full-resolution iris image, the outputs of the Laplacian operator are computed for all space-shifts. The quantized output with maximum entropy is selected as the final feature representation. Experimentally we showed that the proposed method produces superb performance in iris segmentation and recognition. Index Terms: iris segmentation, iris recognition, shift-invariant, multiscale Laplacian kernel.

Eye Localization based on Multi-Scale Gabor Feature Vector Model

Eye localization is necessary for face recognition and related application areas. Most of eye localization algorithms reported thus far still need to be improved about precision and computational time for successful applications. In this paper, we propose an improved eye localization method based on multi-scale Gator feature vector models. The proposed method first tries to locate eyes in the downscaled face image by utilizing Gabor Jet similarity between Gabor feature vector at an initial eye coordinates and the eye model bunch of the corresponding scale. The proposed method finally locates eyes in the original input face image after it processes in the same way recursively in each scaled face image by using the eye coordinates localized in the downscaled image as initial eye coordinates. Experiments verify that our proposed method improves the precision rate without causing much computational overhead compared with other eye localization methods reported in the previous researches.

Motion detection in complex and dynamic backgrounds

For the detection of moving objects, background subtraction methods are widely used. In case the background changes, we need to update the background in real-time for the reliable detection of foreground objects. An adaptive Gaussian mixture model (GMM) combined with probabilistic learning is one of the most popular methods for the real-time update of the complex and dynamic background. However, the probabilistic learning approach does not work well in high traffic regions. In this paper, we classify each pixel into four different types: still background, dynamic background, moving object, and still object, and update the background model based on the classification. For the classification, we analyze a sequence of frame differences at each pixel and its neighborhood. We experimentally show that the proposed method learn complex and dynamic backgrounds in high traffic regions more reliably, compared with traditional methods.

Real-time audio surveillance system for PTZ camera

In this paper, we propose an audio surveillance system to detect and localize dangerous sound in real-time so as to be able to direct a PTZ camera to catch a snapshot image about the location of sound source instantly. The proposed audio surveillance system firstly detects foreground sound based on adaptive Gaussian mixture background sound model, and classifies it into one of pre-trained classes of foreground sounds based on GMM model. Next, it decides whether it belongs to dangerous class group or not. If it does, then a sound source localization algorithm based on Dual delay-line algorithm is applied to localize the sound source. Finally, the proposed system uses the sound source location information to pan and tilt the PTZ camera towards the orientation of the dangerous sound source, and take a snapshot against over the sound source region. Experiment results show that the proposed system can detect foreground sound stably and recognize dangerous sounds with a precision of 79% while the sound source localization can estimate orientation of the sound source with acceptably small error.

3D Face Modeling based on 3D Morphable Shape Model

Since 3D face can be rotated freely in 3D space and illumination effects can be modeled properly, 3D face modeling Is more precise and realistic in face pose, illumination, and expression than 2D face modeling. Thus, 3D modeling is necessitated much in face recognition, game, avatar, and etc. In this paper, we propose a 3D face modeling method based on 3D morphable shape modeling. The proposed 3D modeling method first constructs a 3D morphable shape model out of 3D face scan data obtained using a 3D scanner Next, the proposed method extracts and matches feature points of the face from 2D image sequence containing a face to be modeled, and then estimates 3D vertex coordinates of the feature points using a factorization based SfM technique. Then, the proposed method obtains a 3D shape model of the face to be modeled by fitting the 3D vertices to the constructed 3D morphable shape model. Also, the proposed method makes a cylindrical texture map using 2D face image sequence. Finally, the proposed method builds a 3D face model by rendering the 3D face shape model with the cylindrical texture map. Through building processes of 3D face model by the proposed method, it is shown that the proposed method is relatively easy, fast and precise than the previous 3D face model methods.

Design and implementation of an embedded multimedia live streaming decoder system

In this paper, we propose an effective design and implementation of a versatile embedded multimedia live streaming decoder system based on TIs DM814x processor, which can not only decode video live streams of various video codecs(H.264, MPEG-4, etc.), audio live streams of various audio codecs(AAC, MP3, G.711, etc.), but also demultiplex (demux) MPEG-2 TS, decode video stream and audio streams inside, all streams carried over RTP after the stream servers are contacted by RTSP URLs. Those decoded live raw streams are displayed out through the attached HDMI, HD-SDI, NTSC, and line-out interface of the embedded decoder. The S/W architecture, protocol handling and buffer management of the proposed embedded decoder system are studied carefully and explained here in some detail. Currently, our implementation is observed to work properly. However, synchronization among video, audio, and associated (meta) data at the decoding and displaying are not precisely achieved and still are under development, whose results will be reported later.

Identification System Based on Partial Face Feature Extraction

This paper presents a new human identification algorithm using partial features of the uncovered portion of face when a person wears a mask. After the face area is detected, the feature is extracted from the eye area above the mask. The identification process is performed by comparing the acquired one with the registered features. For extracting features SIFT(scale invariant feature transform) algorithm is used. The extracted features are independent of brightness and size- and rotation-invariant for the image. The experiment results show the effectiveness of the suggested algorithm.

Illumination-Robust Face Recognition based on Illumination-Separated Eigenfaces

The popular eigenfaces-based face recognition among proposed face recognition methods utilizes the eigenfaces obtained from applying PCA to a training face image set. Thus, it may not achieve a reliable performance under illumination environments different from that of training face images. In this paper, we propose an illumination-separate eigenfaces-based face recognition method, which excludes the effects of illumination as much as possible. The proposed method utilizes the illumination-separate eigenfaces which is obtained by orthogonal decomposition of the eigenface space of face model image set with respect to the constructed face illumination subspace. Through experiments, it is shown that the proposed face recognition method based on the illumination-separate eigenfaces performs more robustly under various illumination environments than the conventional eigenfaces-based face recognition method.

Layered Object Detection using Adaptive Gaussian Mixture Model in the Complex and Dynamic Environment

For the detection of moving objects, background subtraction methods are widely used. In case the background has variation, we need to update the background in real-time for the reliable detection of foreground objects. Gaussian mixture model (GMM) combined with probabilistic learning is one of the most popular methods for the real-time update of the background. However, it does not work well in the complex and dynamic backgrounds with high traffic regions. In this paper, we propose a new method for modelling and updating more reliably the complex and dynamic backgrounds based on the probabilistic learning and the layered processing.

Smart Card User Identification Using Low-sized Face Feature Information

PIN(Personal Identification Number)-based identification method has been used to identify the user of smart cards. However, this type of identification method has several problems. Firstly, PIN can be forgotten by owners of the card. Secondly, PIN can be used by others illegally. Furthermore, the possibility of hacking PIN can be high because this PIN type matching process is performed on terminal. Thus, in this paper we suggest a new identification method which is performed on smart card using face feature information. The proposed identification method uses low-sized face feature vectors and simple matching algorithm in order to get around the limits in computing capability and memory size of smart card.