Thanarat H. Chalidabhongse

Chulalongkorn University · Department of Computer Engineering

We present a new fast algorithm for background modeling and subtraction. Sample background values at each pixel are quantized into codebooks which represent a compressed form of background model for a long image sequence. This allows us to capture structural background variation due to periodic-like motion over a long period of time under limited m...

This paper presents a novel algorithm for detecting mov-ing objects from a static background scene that contains shading and shadows using color images. Although the background subtraction technique has been used for years in many vision systems as a preprocessing step for object detection and tracking, most of these algorithms are suscep-tible to...

Intestinal parasitic infection leads to several morbidities in humans worldwide, especially in tropical countries. The traditional diagnosis usually relies on manual analysis from microscopic images which is prone to human error due to morphological similarity of different parasitic eggs and abundance of impurities in a sample. Many studies have de...

Automatic liver tumor segmentation is a paramount important application for liver tumor diagnosis and treatment planning. However, it has become a highly challenging task due to the heterogeneity of the tumor shape and intensity variation. Automatic liver tumor segmentation is capable to establish the diagnostic standard to provide relevant radiolo...

A femoral fracture is a severe injury occurring in traumatic and pathologic causes. Diagnosis and Preoperative planning are indispensable procedures relying on preoperative radiographs such as X-ray and CT images. Nevertheless, CT imaging has a higher cost, radiation dose, and longer acquisition time than X-ray imaging. Thus, the fracture 3D recons...

Manual examination of faecal smear samples to identify the existence of parasitic eggs is very time-consuming and can only be done by specialists. Therefore, an automated system is required to tackle this problem since it can relate to serious intestinal parasitic infections. This paper reviews the ICIP 2022 Challenge on parasitic egg detection and...

Automatic detection of parasitic eggs in microscopy images has the potential to increase the efficiency of human experts whilst also providing an objective assessment. The time saved by such a process would both help ensure a prompt treatment to patients, and off-load excessive work from experts' shoulders. Advances in deep learning inspired us to...

Intestinal parasitic infection leads to several morbidities to humans worldwide, especially in tropical countries. The traditional diagnosis usually relies on manual analysis from microscopic images which is prone to human error due to morphological similarity of different parasitic eggs and abundance of impurities in a sample. Many studies have de...

Identification of abnormalities in red blood cells (RBC) is key to diagnosing a range of medical conditions from anaemia to liver disease. Currently this is done manually, a time-consuming and subjective process. This paper presents an automated process utilising the advantages of machine learning to increase capacity and standardisation of cell ab...

Glucose-6-phosphate dehydrogenase (G6PD) deficiency is the most common enzymopathy in humans. More than 400 million people worldwide are affected by this genetic condition. Testing for G6PD deficiency before drug administration is essential for patient safety. Rapidly ascertaining the G6PD status of a person is desirable for proper treatment. The d...

Automated red blood cell classification on blood smear images helps hematologist to analyze RBC lab results in less time and cost. Overlapping cells can cause incorrect predicted results that have to separate into multiple single RBCs before classifying. To classify multiple classes with deep learning, imbalance problems are common in medical imagi...

Scene text localization is a very crucial step in the issue of scene text recognition. The major challenges—such as how there are various sizes, shapes, unpredictable orientations, a wide range of colors and styles, occlusion, and local and global illumination variations—make the problem different from generic object detection. Unlike existing scen...

Random field formulation has proven to be a powerful framework for solving stereo correspondence problems because of its ability to intuitively incorporate global smoothness constraint with local matching costs. However, solving such problems for cases where large number of pixel variables and possible disparity labels are common can be impractical...

Human action movement has constrained by the articulated body which leads to the variation of movement velocity from point-to-point. In this paper, adaptive key frame intervals are used to specify the proper number of frames by detecting the variation of human motion. Features which are extracted within the interval contain information of primitive...

The gold standard for early detection of breast cancer has been the mammogram. However, this technique still has limitation for women with dense breast. Combining mammogram with digital breast tomosynthesis overcomes the limitation but increases exposure dose approximately twice. This study focuses on reducing radiation dose by synthesizing the 2D...

Human actions in video have the variation in both spatial and time domains which cause the difficulty for action classification. According to the nature of articulated body, an amount of movement from point-to-point is not constant, which can be illustrated as a bell-shape. In this paper, key frames are detected for specifying a starting and ending...

Text detection in natural scene images is a challenging problem due to many variations and uncontrollable factors comparing to text detection on scanned document. Unlike the existing Thai text detection methods which focus on using connected component analysis combining with other rule-based techniques to localize text, our proposed method is based...

Super Resolution (SR) is the image processing technique that reconstructs a high resolution (HR) image from multiple low resolution images. Image registration is a necessary part of SR reconstruction. The accuracy of motion estimation in registration step affects the quality of the result HR image directly. In this paper, we study the feasibility o...

Stereo correspondence has been one of the most intense areas of research in computer vision. Graph-based energy minimization has proven to be a powerful framework for incorporating global constraints with local matching costs. In this work, dense stereo correspondence is cast as multilabel energy minimization problem, which is then solved using MQP...

Face recognition is an automated process with the ability to identify individuals by their facial characteristics. Currently there is a problem in which the process requires several examples of the person of interest's face in order to produce accurate outcome, and the process is intolerant to the variation in facial expression and the condition of...

This paper proposes a method to detect and extract hand features from video sequences, where a person performs Thai Sign Language (TSL), for recognizing static TSL alphabets. First, the skin regions are segmented using trained skin color model represented in YCbCr color space. Next, Haar-like feature is used to label face and hands' initial positio...

Tracking moving objects such as human has become a major topic in video surveillance applications. Camera handoff is an important problem when using multiple cameras which have overlapping or non-overlapping field of views. However, most handoff techniques rely on a robust tracker and some information from first camera assigned to tracked objects....

Human action in the image sequence can be seen as the relation of the movement of body parts. Since, human has an articulated body, each body part cannot move freely. In each action, the specific directions of body parts arrangement cause a change in posture and movement over time. In this paper, the image oriented gradient and histogram of motion...

The head pose estimation is a process of recovering 3D head position in term of yaw, pitch and roll from 2D images. However, the reduction of information from 3D to 2D leads to an ill-posed problem. In this paper, we propose a novel algorithm of head pose estimation that includes facial features tracking for Thai sign language recognition. In order...

Welcome to the 19th IEEE International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), being held December 7–9, 2011 in Chiang Mai, Thailand. I would like to encourage you all to attend and actively participate in the symposium.

Recognizing human actions is a challenging research area due to the complexity and variation of human's appearances and postures, the variation of camera settings, and angles. In this paper, we introduce a motion descriptor based on direction of optical flow for human action recognition. The directional value of a silhouette is divided into small r...

This paper describes our algorithms for players tracking and ball detection for an automatic broadcast tennis video annotation. The system detects and tracks the players using a robust non-parametric procedure for estimating density gradients called the mean shift algorithm. The basic mean shift tracking algorithm assumes that the target object has...

The statistical background subtraction and shadow detection algorithm (SBGS) is fast and reliable in outdoor scenes with shadows. However, its reliability depends on the number of training frames to construct the initial background model. In addition, the similarity between foreground and background colors, i.e, camouflage problem, could lead to th...

We introduce a performance evaluation methodology called Perturbation Detection Rate (PDR) analysis, for measuring performance of background subtraction (BGS) algorithms. It has some advantages over the commonly used Receiver Operation Characteristics (ROC) analysis. Specifically, it does not require foreground targets or knowledge of fore-ground d...

Presently researches in networked surveillance system grow continuously and substantially. One reason is because of the insecurity incidents such as terrorism acts in Thailand and many countries around the world. This results in the need of intelligent surveillance and monitoring system consisting of real-time image capture, transmission, processin...

This paper describes a vision system that can extract 2D and 3D visual properties of mango such as size (length, width, and thickness), projected area, volume, and surface area from images and use them in sorting. The 2D/3D visual properties are extracted from multiple view images of mango. The images are first segmented to extract the silhouette r...

This paper proposes a method for real-time face detection and identification using two cooperative pan-tilt-zoom (PTZ) cameras. For each camera, the human face is detected and segmented using motion and skin color cues. The face segment is then analyzed by considering the relative position of the facial color blob to determine the pose. After facia...

A system for automatic detection and segmentation of text in low quality Thai sign images is presented in this paper. The method is designed as a part of a real-time Thai sign translator system which can be used in many applications. First, an input image is pre-processed to enhance its quality. Secondly, we apply LoG (Laplacian of Gaussian) to the...

In this paper, a license plate detection system is proposed to localize and extract license plates of moving vehicles in complex scene. The system works on compressed low resolution video streams obtained from real working environments. The illumination conditions are varied which typically occurs in outdoor environment. The vehicles are moving and...

This paper describes a new edge-based car plate detection technique to localize and extract car license plates in complex scene. The system works for both moving and stationary vehicles in compressed low resolution video streams obtained from real working environments. To cope with the varied illumination condition, which typically occurs in outdoo...

In this paper, a new framework for personalized stock recommendation system based on adaptive user models is presented. The system is designed to provide personalized and appropriated information to the investors based on their personal profiles and their historical system interactions. The system components include initializing and updating user m...

The Background Subtraction Algorithm has been proven to be a very effective technique for automated video surveillance applications. In statistical approach, background model is usually estimated using Gaussian model and is adaptively updated to deal with changes in dynamic scene environment. However, most algorithms update background parameters li...

In this paper, we present a new stereo approach for tracking human face by using only two cameras in system. One pan-tilt camera is used for tracking person focused on face. One static camera cooperate with pan-tilt camera are used as a stereo system to estimate face 3D position. We propose to update relative position between cameras to reflect cam...

The background subtraction algorithm has been proven to be a very effective technique for automated video surveillance applications. In statistical approach, background model is usually estimated using Gaussian model and is adaptively updated to deal with changes in dynamic scene environment. However, most algorithms update background parameters li...

We present a real-time algorithm for foreground–background segmentation. Sample background values at each pixel are quantized into codebooks which represent a compressed form of background model for a long image sequence. This allows us to capture structural background variation due to periodic-like motion over a long period of time under limited m...

In this paper, we develop face and hand tracking for sign language recognition system. The system is divided into two stages: the initial and tracking stages. In initial stage, we use the skin feature to localize face and hands of signer. The ellipse model on CbCr space is constructed and used to detect skin color. After the skin regions have been...

This paper presents a new auto brighoess control algorithm fur adaptive background subtraction. The algorithm is designed to cope with the problem of auto-brightness adjustment feature of consumer-type cameras. The experimental results show the proposed method improves performance of the classification. This will be beneficial to many computer visi...

We develop the face and hand detection and tracking for sign language recognition system. We first perform a preliminary evaluation on several color spaces to find the most suitable one using a nonparametric model approach. Then, we propose to use the elliptical model in the CbCr color space to lower the complexity of the detection algorithm and to...

The paper presents a statistical adaptive realtime background subtraction algorithm that is very robust to moving shadows and dynamic scene environment. The algorithm enhances the previously developed method reported by T. Horprascrt et al. (see Proc. IEEE ICCV'99 Frame-rate Workshop, 1999) by adding adaptation of the model corresponding to a dynam...

The virtual metamorphosis system lets people change their forms into any other form in a virtual scene. To realize these changes, a computer vision system estimates facial expressions and body postures and reproduces them in a computer graphics avatar in real time. We introduce three systems in order of their development: the Virtual Kabuki system,...

This paper presents a novel algorithm for detecting moving objects from a static background scene that contains shading and shadows using color images. We develop a robust and eeciently computed b ackground subtraction algorithm that is able to cope with local illumination changes, such as shadows and highlights, as well as global illumination chan...

An approach for estimating 3D head orientation in a monocular image sequence is presented. The approach employs recently developed imagebased parameterized tracking for face and face features to locate the area in which an estimation of point feature locations is performed. This involves tracking of five points (four at the eye corners and the fift...

We describe a real-time 3D computer vision system for detecting and tracking human movement. Multiple cameras observe a person; silhouette analysis and template matching achieve real-time 3D estimation of human posture Dynamics/kinematics model of human body and Kalman filter are utilized to help the tracking process as well as to interpolate some...

An approach for estimating 3D head orientation in a monocular image sequence is proposed. The approach employs recently developed image-based parameterized tracking for face and face features to locate the area in which a sub-pixel parameterized shape estimation of the eye's boundary is performed. This involves tracking of five points (four at the...

An approach for estimating 3D head orientation in a monocular image sequence is proposed. The approach employs recently developed image-based parameterized tracking for face and face features to locate the area in which a sub-pixel parameterized shape estimation of the eye's boundary is performed. This involves tracking of five points (four at the...

Recognition of unconstrained, handwritten connected numerals based on a dual cooperative neural network (DCN) is presented. First, a sequence of connected numerals is segmented into regions of interest by a group of windows moving along the horizontal axis of numeral sequence. The windows of the group are distributed in position in such a way as to...

We introduce a performance evaluation methodology called Perturbation Detection Rate (PDR) analysis for measuring performance of foreground-background seg-mentation. It has some advantages over the commonly used Receiver Operation Characteristics (ROC) analy-sis. Specifically, it does not require foreground targets or knowledge of foreground distri...

Thesis research directed by Dept. of Computer Science. Thesis (Ph. D.)--University of Maryland, College Park, 2001. Includes bibliographical references (leaves 151-165).