Bunyarit Uyyanonvara

• PhD
• Head of Department at Sirindhorn International Institute of Technology (SIIT)

This paper presents a new supervised method for segmentation of blood vessels in retinal photographs. This method uses an ensemble system of bagged and boosted decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological transformation, line strength measures, and Gabor filter responses. The...

This research aims to develop an efficient system for screening of diabetic retinopathy. Diabetic retinopathy is the major cause of blindness. Severity of diabetic retinopathy is recognized by some features, such as blood vessel area, exudates, haemorrhages and microaneurysms. To grade the disease the screening system must efficiently detect these...

Detection of a hemorrhage in CT scan slices is one of the crucial steps for a neurosurgeon to diagnose any abnormality and severity in the brain of a patient. It is usually time consuming as there are as many as 256 produced slices from a CT scan machine for each patient. In this paper, we introduce an automatic hemorrhage detection in brain CT sli...

The artificial intraocular lens (IOL) is inserted to replaced the crystalline lens of the human eye after cataract surgery or refraction clear lens extraction. When the IOL, is in an aquatic environment, glistenings, which are liquid-filled microvacuoles, can be discriminated from normal state. Automatic detection of glistenings is a new problem, t...

About 85% of people between the age of 12 and 24 experience acne, the acne treatment cost exceed $3 billion in U.S.A. Currently dermatologist use manual skin assessment method such as visual and photography then manually mark and count acne on patient face which is time consuming and subjective. This paper proposed acne detection method using Speed...

Human body shape plays an important role in many industries, especially in Healthcare. We have seen changes in the body size and shape of the Thai population from the data collected through national sizing surveys over two decades. These changes can also indicate the trend of national health status. In this paper, a body shape clustering algorithm...

Human body shapes are considered important information for fashion and clothing companies. In order to design better fitting clothes for the population or target customers, accurate analysis of body shapes is required. So far, most works on grouping body shapes are done using body measurements and classifying them into a given number of clusters. H...

Exudates are an important sign of Diabetic Retinopathy. Retinal Exudates form when lipid leakage occurs from damage capillaries. They are deep yellowish in colour and can be easily confused with other yellowish regions in retina. Detection of exudates is very important for developing an automated screening system for detection of diabetic retinopat...

This research aims to develop an efficient system for screening of diabetic retinopathy. Diabetic retinopathy is the major cause of blindness. Severity of diabetic retinopathy is recognized by some features, such as blood vessel area, exudates, haemorrhages and micro aneurysms. To grade the disease the screening system must efficiently detect these...

This paper presents a survey of blob detection methods which has been applied on image processing with relation of medical images proposed by literature. “The blob detection is a mathematical method which detects regions or points in digital images”. [1] The regions or points which have noticeable difference with their surroundings is called blob....

Beauty industry has become one of the largest growth industries. The most famous service for beauty clinic is acne treatment. The first process of acne treatment is acne counting and classification which is manually done by dermatologist. In this paper, an automatic acne detection system was proposed and developed as an acne detection device. The s...

Precise localisation of an optic disk (OD) in the retinal images is one of the most important problems in the ophthalmic image processing. Although a considerable progress has been made towards a computerised solution of the problem, the numerical algorithms often fail on retinal images characterised by poor quality. Therefore, the authors propose...

In this paper, an effective image processing technique has been studied to develop a system of acne detection. The focus is on binary thresholding applied to facial images with various types, shapes or amounts of acne. A typical image on a cheek has been usually used to take in the experiment which results are markings on acnes automatically, this...

An intraocular lens (IOL) is implanted in the eye after a cataract surgery. When an IOL is in an aqueous environment, glistenings that are fluid-filled microvacuoles are often observed. Previously, studies of glistenings involved tedious work of manual glistenings labeling and rough estimation of glistening distribution. This paper proposes a softw...

Thailand is a country with awareness in the importance of solution on the problem of global warming. Thailand is one of the countries in the group of Non-Annex 1. The country has no obligation in reducing the emission of greenhouse gas. Although Thailand has no obligation in reducing the emission of greenhouse gas, the guideline stipulated in Kyoto...

The ventricle is part of the brain filled with cerebrospinal fluid (CSF). The ventricle shape and volume are used to diagnosis patients who have brain disease because some brain diseases will cause the change of the ventricle shape or volume. It is very useful to detect any changes in an early stage. This paper proposes an algorithm for automatic s...

Tortuosity classification is important for retinopathy of prematurity screening systems. Timely and early detection can help reduce the incidence of blindness in premature infants. In this work, we implement and evaluate the performance of support vector machine classifier for tortuosity classification and compare it with three different classifica...

Abnormal dilation and tortuosity of retinal blood vessels are the primary signs of plus disease in retinopathy of prematurity. Timely prognosis could help reduce the delay in treatment and the risk of retinal detachment. Our objectives is to determine whether tortuosity and dilation sufficient for plus disease could be assessed most accurately by c...

Firefly algorithm is a swarm-based algorithm that can be used for solving optimization problems. In this paper, we focus on image clustering algorithm using the fuzzy set of possible solution is incorporated into the original firefly to improve the performance. The movement of the firefly still follows the original pattern but they are updated acco...

Arrays of regular macropores in electronic, magnetic, photonic and sensing devices can be patterned by X-ray lithography. Such structures inevitably contain some irregularity and require time-consuming pattern inspections. In this work, a pattern inspection by intensity-based digital image processing procedure is proposed and tested on scanning ele...

Digital image processing has increasingly been implemented in nanostructural analysis and would be an ideal tool to characterize the morphology and position of self-assembled magnetic nanoparticles for high density recording. In this work, magnetic nanoparticles were synthesized by the modified polyol process using and as starting materials. Transm...

Nature-inspired algorithms, such as Particle swarm optimization (PSO), Ant colony optimization (ACO), and Firefly algorithm, are well known for solving NP-hard optimization problems. They are capable of obtaining optimal solutions in a reasonable time. The algorithm presented in this paper is a combination of a firefly mating concept and genetic al...

Microaneurysms detection is an important task in computer aided diagnosis of diabetic retinopathy. Microaneurysms are the first clinical sign of diabetic retinopathy, a major cause of vision loss in diabetic patients. Early microaneurysm detection can help reduce the incidence of blindness. Automatic detection of microaneurysms is still an open pro...

The clinical recognition of abnormal retinal tortuosity enables the diagnosis of many diseases. Tortuosity is often interpreted as points of high curvature of the blood vessel along certain segments. Quantitative measures proposed so far depend on or are functions of the curvature of the vessel axis. In this paper, we propose a parallel algorithm t...

Diabetic retinopathy is the commonest cause of blindness in working age people. It is characterised and graded by the development of retinal microaneurysms, haemorrhages and exudates. The damage caused by diabetic retinopathy can be prevented if it is treated in its early stages. Therefore, automated early detection can limit the severity of the di...

Automatic vessel tortuosity measures are crucial for many applications related to retinal diseases such as those due to retinopathy of prematurity (ROP), hypertension, stroke, diabetes and cardiovascular diseases. An automatic evaluation and quantification of retinal vascular tortuosity would help in the early detection of such retinopathies and ot...

Data Convergence is a common problem in many fields. There are several ways to solve this problem. In this paper, we present an new way using a distance optimization approach called Delaunay Search. This approach finds the point which yields the shortest distance to different groups of data in the network of data. The new approach is compared to tw...

Retinopathy of Prematurity (ROP) is a vital cause of vision loss in premature infants, but early detection of its symptoms enables timely treatment and prevents blindness. Tortuosity is the major indicator of ROP that can potentially be automatically quantified. In this paper, which focuses on automatic tortuosity quantification and classification...

Almost all ocular and systemic diseases affect blood vessel attributes (tortuosity, length, width, and curvature). Quantitative measurements of these attributes could thus provide useful tool for diagnosing the severity of several diseases. However, it is still unclear how best to represent the attribute values of multiple vessels in a single image...

The clinical recognition of abnormal retinal tortuosity is significant in the diagnosis of several ocular and systemic diseases. An automatic evaluation and quantification of tortuosity would help in the early detection of such pathologies. We applied two tortuosity evaluation approach based on continuous curvature to a dataset of 45 infant fundus...

Vascular dilation is a significant characteristic of Retinopathy of Prematurity (ROP). Timely prognosis could help reduce the delay in treatment and the risk of retinal detachment. In preterm retina the width of retinal veins and arteries are quantified by the proposed approach and the detected differences are displayed in a vessel map. Performance...

This paper describes a new supervised method for segmentation of blood vessels in retinal images of multi ethnic school children. This method uses an ensemble classification system of boot strapped decision trees. A filter bank of the dual Gaussian and the Gabor filters, along with the line strength measure of blood vessels is used to generate the...

Object recognition is one of the most classic problem in computer vision where several techniques in classification have been proposed. In this work, we investigate a new promising improvement on a classification problem using multiple feature types. We assume that different features are suitable for different objects and the occurrence of particul...

Diabetic Retinopathy is a medical condition where the retina is damaged because fluid leaks from blood vessels into the retina. The presence of hemorrhages in the retina is the earliest symptom of diabetic retinopathy. The number and shape of hemorrhages is used to indicate the severity of the disease. Early automated hemorrhage detection can help...

Retinal vessel segmentation algorithms are a fundamental component of automatic retinal disease screening systems. This work examines the blood vessel segmentation methodologies in two dimensional retinal images acquired from a fundus camera and a survey of techniques is presented. The aim of this paper is to review, analyze and categorize the reti...

A modification of the watershed algorithm is introduced to detect an optic disc in retinal images characterized by low quality. The watershed algorithm is applied to a pre-processed image to segment candidate blobs. Features are then extracted from each blob and used for the classification. The entropy is used to find the candidate blobs to return...

Several diseases can be indicated by the characteristic of retinal blood vessel. Instead of observing the retinal blood vessel in the retinal fundus image directly; a digital retinal fundus image analysis tool can help ophthalmologists to make accurate diagnosis in an efficient manner. This paper aim at developing a graphical user interface for eas...

This paper presents a new supervised method for segmentation of blood vessels in retinal images. This method uses an ensemble system of boot strapped decision trees and utilizes a feature vector based on the orientation analysis of gradient vector field, morphological linear transformation, line strength measures and Gabor filter responses. The fea...

This paper presents an algorithm to segment the blood vessels in retinal images. The contribution of this work is that we exhibit how a line detection can be applied in a multi-scale framework to fulfill the sophisticated task of vessel segmentation. The key idea of our algorithm is to systematically combine the outputs of Gaussian based line detec...

Although Thailand has no obligation to reduce greenhouse gas production since it is not in the Annex I, the guidelines set forth in the Kyoto Protocol has provided opportunities for Thailand to participate in reducing emissions under the clean development mechanism. The carbon credit registry system is needed to achieve that goal. This paper report...

The ventricle is filled with cerebrospinal fluid (CSF) in the brain. Some brain diseases are caused by changing of the ventricle shape or volume. The ventricle shape and volume are used to diagnose patients who have brain diseases. This paper proposes an algorithm of digital image processing for segmentation of a ventricle from CT brain images. The...

Abnormal retinal tortuosity is a significant diagnostic indicator for a number of retinal pathologies. We propose robust quantitative tortuosity metrics based on curvature calculated from improved chain code algorithm. In comparison to other published methods, the proposed metrics can estimate appropriate tortuosity for vessels with constant or cha...

The change in morphology, diameter, branching pattern and/or tortuosity of retinal blood vessels is an important indicator of various clinical disorders of the eye and the body. This paper reports a supervised methodology for segmentation of the retinal vasculature from ocular fundus images. A 7-D feature vector is constructed by computing the outp...

The change in morphology, diameter, branching pattern or tortuosity of retinal blood vessels is an important indicator of various clinical disorders of the eye and the body. This paper reports an automated method for segmentation of blood vessels in retinal images. A unique combination of techniques for vessel centerlines detection and morphologica...

The change in morphology, diameter, branching pattern and/or tortuosity of retinal blood vessels is an important indicator of various clinical disorders of the eye and the body. This paper reports an automated method for segmentation of blood vessels in retinal images by means of a unique combination of differential filtering and morphological proc...

Measurement of blood vessel tortuosity is a useful capability for automatic ophthalmological diagnostic tools. Screening of Retinopathy of Prematurity (ROP), a disease of eye that affects premature infants, for example, depends crucially on automatic tortuosity evaluation. Quite a few techniques for tortuosity measurement and classification have be...

Microaneurysms are the first clinical sign of diabetic retinopathy. The number of microaneurysms is used to indicate the severity of the disease. Early microaneurysm detection can help reduce the incidence of blindness. This paper investigates a set of optimally adjusted morphological operators used for microaneurysm detection on non-dilated pupil...

Tortuosity is one of the first manifestations of many retinal diseases such as those due to retinopathy of prematurity (ROP), hypertension, stroke, diabetes and cardiovascular diseases. An automatic evaluation and quantification of retinal vessel tortuosity would help in the early detection of such retinopathies and other systemic diseases. This pa...

Retinal vessel extraction is important for the diagnosis of numerous eye diseases. It plays an important role in automatic retinal disease screening systems. This paper presents an efficient method for the automated analysis of retinal images. Fine anatomical features, such as blood vessels, are detected by analyzing the gradient orientation of the...

K-Nearest Neighbor algorithm (KNN) is a simple yet efficient method of classifying objects based on the closest training sample within the feature space. The simplicity and simultaneous processing within the KNN algorithm is considerably an advantage. Erion Plaku proposed a distributed computation of the KNN graph for large dimensional point sets....

The process of the alternative functioning of the surveillance system has been discussed in this paper along with software implementation at a low cost. A frame subtraction technique has been applied, which projects a moving object in consideration to be in current view, while subtraction of the current and the previous frame image reaches a certai...

Retinal vessel extraction is important for the de-tection of numerous eye diseases. It plays an important role in automatic retinal disease screening systems. In this paper, vessel extraction algorithm based on combination of matched filter and bottom hat transform is proposed. First, green channel is extracted from original image. It is then appli...

This paper presents a method for automatic segmen-tation of blood vessels in retinal images. The method is based on vessel tracking technique. The key idea of the method is that first a set of seed points (center of vessel cross sections) is extracted. Then, the seed points are connected to establish the vessel skeleton. Finally, the false vessel p...

Retinal vessel tortuosity measurement is the reliable method used as an opthalmological diagnostic tool. For example, Retinopathy of Prematurity (ROP), this disease can be characterised by the increasing in vascular dilation and tortuosity. This paper proposes a method of how to measure and define tortuous scale using the mean curvature. The tortuo...

Exudate detection is important for diabetic retinopathy screening systems. Early detection can help to reduce the incidence of blindness in diabetic patients. In this work we implement and evaluate the performance of different algorithms for automatic exudate detection. These consist of a mathematical morphological technique, a fuzzy c-means cluste...

Corner detection and optical flow are common techniques for feature-based video stabilization. However, these algorithms are computationally expensive and should be performed at a reasonable rate. This paper presents an algorithm for discarding irrelevant feature points and maintaining them for future use so as to improve the computational cost. Th...

Exudates are among the preliminary signs of diabetic retinopathy, a major cause of vision loss in diabetic patients. Early detection of exudates could improve patients’ chances to avoid blindness. In this paper, we present a series of experiments on feature selection and exudates classification using naive Bayes and support vector machine (SVM) cla...

This paper proposes an object detection method using the methods of variable size blob detection along with feature stability. The objective of this algorithm is for detecting variable size and variable shape objects without the use in preceding information of the object of interest. Process of the algorithm constructs a scale-space tree from blobs...

To prevent blindness from diabetic retinopathy, periodic screening and early diagnosis are neccessary. Due to lack of expert ophthalmologists in rural area, automated early exudate (one of visible sign of diabetic retinopathy) detection could help to reduce the number of blindness in diabetic patients. Traditional automatic exudate detection method...

Exudates are the primary sign of Diabetic Retinopathy. Early detection can potentially reduce the risk of blindness. An automatic method to detect exudates from low-contrast digital images of retinopathy patients with non-dilated pupils using a Fuzzy C-Means (FCM) clustering is proposed. Contrast enhancement preprocessing is applied before four fea...

Robust real-time hand detection and tracking in video sequences would enable many applications in areas as diverse ashuman-computer interaction, robotics, security and surveillance, and sign language-based systems. In this paper, we introducea new approach for detecting human hands that works on single, cluttered, low-resolution images. Our prototy...

Exudates are one of the primary signs of diabetic retinopathy which is a main cause of blindness that could be prevented with an early screening process. Pupil dilation is required in the normal screening process but this affects patients' vision. Automatic computerized screening could facilitate the screening process, reduce inspection time, and i...

SUMMARY Retinopathy of Prematurity (ROP) is an infant disease characterized by increased dilation and tortuosity of the retinal blood ves- sels. Automatic tortuosity evaluation from retinal digital images is very useful to facilitate an ophthalmologist in the ROP screening and to pre- vent childhood blindness. This paper proposes a method to automa...

Diabetic retinopathy is a complication of diabetes that is caused by changes in the blood vessels of the retina. The symptoms can blur or distort the patient's vision and are a main cause of blindness. Exudates are one of the primary signs of diabetic retinopathy. Detection of exudates by ophthalmologists normally requires pupil dilation using a ch...

With the completion of the human genome project, novel sequencing and genotyping technologies had been utilized to detect mutations. Such mutations have continually been produced at exponential rate by researchers in various communities. Based on the population's mutation spectra, occurrences of Mendelian diseases are different across ethnic groups...

This paper proposes PACS (picture archiving communication system) to manage and transfer information for dental field focusing on 2 main fields as follows. First application was to open digital imaging and communications in medicine (DICOM) files of patients inside the database via local area network (LAN) and hypertext transfer protocol [HTTP]. Se...

Pap smears are a very effective screening test for cervical precancerous. However, hundreds of small windows have to be looked under microscope by a trained cytologist for a single slide from each patient. It makes this process very tedious and erroneous. The automatic analysis of Pap smear microscopic images is one of the most interesting fields i...

Automatically detect the structure of blood vessels in ROP infants to allow ophthalmologist to analyze and detect the symptom early. This study presents a set of methods for detection of the skeletonized structure of premature infant's low-contrast retinal blood vessel network. Steps has been optimized for this study, namely statistically optimized...

Exudates are the primary signs of diabetic retinopathy which are mainly cause of blindness and could be prevented with an early screening process. Pupil dilation is required in the normal screening process but this affects patients' vision. This paper investigated and proposed automatic methods of exudates detection on low-contrast images taken fro...

Reliable and efficient optic disk localization and segmentation are important tasks in automated retinal screening. General-purpose edge detection algorithms often fail to segment the optic disk (OD) due to fuzzy boundaries, inconsistent image contrast or missing edge features, especially in infants' retinal images where the image acquisition proce...

Automatic detection and tracking of human hands in video imagery has many applications. While some success has been achieved in human-computer interaction applications, hand tracking would also be extremely useful in security systems, where it could help the system to understand and predict human actions, intentions, and goals. We have de-signed an...

In this paper, we propose a new adaptive approach of color quantization. It can significantly reduce the time consumption during the process compared with available methods but still maintains a good quality (greater than 30 dB of PSNR). It is implemented as a part of the media stream compression algorithms for a True Color Signboard System. We ada...

To describe a new method of measuring posterior capsule opacification (PCO) and intraocular lens (IOL) rotation and report the validation of the method. Ophthalmology Department, St. Thomas' Hospital, and Medical Imaging, Department of Physics, King's College, London, United Kingdom. A new interactive software program, POCOman, was developed for th...

A new color image quantization algorithm that uses the squared Euclidean distance of adjacent color points along the highest color variance axis is proposed. This algorithm is a hierarchically divisive colormap design technique. Colors are sorted along the axis with the highest variance of color distribution. The squared Euclidean distances between...

This paper describes a simple but effective hierarchically divisive colormap design technique for color image quantization. By sorting colors based on their components along the principal axis, the one with the highest variance of color distribution, the Euclidean distances between any adjacent colors' along the axis are used to find the cutting pl...

A new color image quantization algorithm that uses the squared Euclidean distance of adjacent color points along the highest color variance axis is proposed. This algorithm is a hierarchically divisive colormap design technique. Colors are sorted along the axis with the highest variance of color distribution. The squared Euclidean distances between...

Color quantization is the process of grouping n data points to k cluster. We proposed a new approach, based on Wu's color quantization (6). Our approach can significantly reduce the time consumption during the process compared with available methods but still maintain an acceptable quality of color distribution. As a rough rule of thumb (4), a quan...

To describe a software program developed to provide an objective assessment of the amount of posterior capsular opacification (PCO) in high-resolution digital images of the posterior capsule after cataract surgery. Images are analyzed by a set protocol of defining the area of the posterior capsule, removing the Purkinje light reflexes by intensity...

After Cataract surgery where a plastic implant lens is implanted into the eye to replace the natural lens, many patients suffer from cell growth across a membrane situated at the back of the lens which degrades their vision. The cell growth is known as Posterior Capsule Opacification (or PCO). It is important to be able to quantify PCO so that the...

In this paper, a method of automatic detection of an Optic Disc (OD) in low-contrast infant's digital fundus images based on circular Hough transform is proposed. Number of dimensions of normal circular Hough Transforms histogram is reduced from 3 to 2 dimensions based on an approximation of OD radius. First few circles are approximated by using ma...

Diabetic retinopathy is a complication of diabetes that is caused by changes in the blood vessels of the retina. The symptom can blur or distort the patient's vision and are mainly cause of blindness. Exudates are one of the primary signs of diabetic retinopathy. Detection of exudates by ophthalmologists normally required pupil dilation using chemi...

ROP or Retinopathy of Prematurity is abnormal growth of blood vessels in the baby's eye. It is a sight threatening condition where the process of retinal vessel growth is disrupted by preterm birth and some of its complications. The earlier the symptom can be detected, the easier the patient can be treated. One of identifiers of an early stage of s...

To prevent and reduce the number of blindness in diabetic patients, periodic screening, automated early exudate detection, and early diagnosis are neccessary. Traditional automatic exudates detections requires many predefined parameters or features while machine learning methods learns and adjusts those parameter automatically but they need time to...