Saowaluck Kaewkamnerd

Vehicle classification based on magnetic sensor signal

We extend our work in vehicle classification proposed in [6] and [7]. Our system is based on a low complexity wireless sensor network. The system consists of a low power microprocessor together with AMR magnetic sensors and an RF transceiver. Two AMR magnetic sensors are employed to extracts dominant low-complexity features including vehicle count, speed, length, Hill-pattern peaks, and normalized energy. These features are studied in [6] and [7] and yield a promising result when vehicle classification is based on sizes (96%). However, when classification of similar sizes, e.g. cars, vans, pickup trucks are studied. The results are relatively lower at 77%. The contribution of this paper include (1) the implementation of feature extraction (count, speed, length) on sensor board and (2) the study for additional different low-complexity features such that better classification rate of small vehicles is obtained. These features include Hill-pattern peaks and magnetic signal differential energy normalized to the vehicle speed and length. This paper proposed vehicle classification tree based on above extraction features. Our work focuses on low computational feature extraction and classification processes suitable for implementing on micro-controller. The same data set employed in [7] is analyzed. The classification yields promising improved results over [6] and [7]. The classification rate yield 100 percent for motorcycle, 82.46 percent for car, 78.57 percent for van and 65.71 percent for pickup. The overall accuracy is 81.69 percent.

An automatic device for detection and classification of malaria parasite species in thick blood film

BackgroundCurrent malaria diagnosis relies primarily on microscopic examination of Giemsa-stained thick and thin blood films. This method requires vigorously trained technicians to efficiently detect and classify the malaria parasite species such as Plasmodium falciparum (Pf) and Plasmodium vivax (Pv) for an appropriate drug administration. However, accurate classification of parasite species is difficult to achieve because of inherent technical limitations and human inconsistency. To improve performance of malaria parasite classification, many researchers have proposed automated malaria detection devices using digital image analysis. These image processing tools, however, focus on detection of parasites on thin blood films, which may not detect the existence of parasites due to the parasite scarcity on the thin blood film. The problem is aggravated with low parasitemia condition. Automated detection and classification of parasites on thick blood films, which contain more numbers of parasite per detection area, would address the previous limitation.ResultsThe prototype of an automatic malaria parasite identification system is equipped with mountable motorized units for controlling the movements of objective lens and microscope stage. This unit was tested for its precision to move objective lens (vertical movement, z-axis) and microscope stage (in x- and y-horizontal movements). The average precision of x-, y- and z-axes movements were 71.481 ± 7.266 μm, 40.009 ± 0.000 μm, and 7.540 ± 0.889 nm, respectively. Classification of parasites on 60 Giemsa-stained thick blood films (40 blood films containing infected red blood cells and 20 control blood films of normal red blood cells) was tested using the image analysis module. By comparing our results with the ones verified by trained malaria microscopists, the prototype detected parasite-positive and parasite-negative blood films at the rate of 95% and 68.5% accuracy, respectively. For classification performance, the thick blood films with Pv parasite was correctly classified with the success rate of 75% while the accuracy of Pf classification was 90%.ConclusionsThis work presents an automatic device for both detection and classification of malaria parasite species on thick blood film. The system is based on digital image analysis and featured with motorized stage units, designed to easily be mounted on most conventional light microscopes used in the endemic areas. The constructed motorized module could control the movements of objective lens and microscope stage at high precision for effective acquisition of quality images for analysis. The analysis program could accurately classify parasite species, into Pf or Pv, based on distribution of chromatin size.

Automatic vehicle classification using wireless magnetic sensor

This paper proposes an extension to our previous work on an automatic low-computed vehicle classification using embedded wireless magnetic sensor. A realization of our vehicle classification on embedded wireless magnetic sensor is studied in this work. The implementation allows real-time vehicle classification based on vehicle magnetic length, averaged energy, and Hill-pattern peaks. The system automatically detects vehicles, extracts features, and classifies them. The three features are of low-computation. We classify vehicles into 4 types: motorcycle, car, pickup and van. The classification shows a promising result. It can classify motorcycle with 95% accuracy. The classification rates between 70%-80% are achieved with car, pickup and van due to their similarity in these extracted features. The results obtained are comparable to our implementation using PC in our previous work and demonstrate that the algorithm can be realized on the embedded wireless magnetic sensor.

Detection and classification device for malaria parasites in thick-blood films

In Thailand, malaria diagnosis still relies primarily on microscopic examination of Giemsa-stained thick and thin blood films. However, the method requires vigorously trained technicians to correctly identify the disease, and is known to be error-prone due to human fatigue. The limited number of such technicians further reduces the effectiveness of the attempt to control malaria. Thus, this project aims to develop an automated system to identify and analyze parasite species on thick blood films by image analysis techniques. The system comprises two main components: (1) Image acquisition unit and (2) Image analysis module. In our work, we have developed an image acquisition system that can be easily mounted on most conventional light microscopes. It automatically controls the movement of microscope stage in 3-directional planes. The vertical adjustment (focusing) can be made in a nanometer range (7–9 nm). Images are acquired with a digital camera that is installed at the top of microscope. The captured images are analyzed by our image analysis software which utilizes the state-of-the-art algorithms to detect and identify malaria parasites.

Wireless magnetic sensor network for collecting vehicle data

We develop a new traffic data collecting device. The device is based on magneto-resistive technology, in which the circuit resistance is changed with the imposing magnetic field. It is known that ferrous-body vehicles interfere with Earths magnetic field, which can be monitored with our device. The signal will then be processed and yields vehicle count, speed, occupancy time, and classification. We also design our device to communicate to its base station via radio frequency. We form a network of these many sensor nodes at places where traffic monitoring are required. Our system is very flexible and adapt to many environments of vehicle detection.

Automatic DNA Diagnosis for 1D Gel Electrophoresis Images using Bio-image Processing Technique

BackgroundDNA gel electrophoresis is a molecular biology technique for separating different sizes of DNA fragments. Applications of DNA gel electrophoresis include DNA fingerprinting (genetic diagnosis), size estimation of DNA, and DNA separation for Southern blotting. Accurate interpretation of DNA banding patterns from electrophoretic images can be laborious and error prone when a large number of bands are interrogated manually. Although many bio-imaging techniques have been proposed, none of them can fully automate the typing of DNA owing to the complexities of migration patterns typically obtained.ResultsWe developed an image-processing tool that automatically calls genotypes from DNA gel electrophoresis images. The image processing workflow comprises three main steps: 1) lane segmentation, 2) extraction of DNA bands and 3) band genotyping classification. The tool was originally intended to facilitate large-scale genotyping analysis of sugarcane cultivars. We tested the proposed tool on 10 gel images (433 cultivars) obtained from polyacrylamide gel electrophoresis (PAGE) of PCR amplicons for detecting intron length polymorphisms (ILP) on one locus of the sugarcanes. These gel images demonstrated many challenges in automated lane/band segmentation in image processing including lane distortion, band deformity, high degree of noise in the background, and bands that are very close together (doublets). Using the proposed bio-imaging workflow, lanes and DNA bands contained within are properly segmented, even for adjacent bands with aberrant migration that cannot be separated by conventional techniques. The software, called GELect, automatically performs genotype calling on each lane by comparing with an all-banding reference, which was created by clustering the existing bands into the non-redundant set of reference bands. The automated genotype calling results were verified by independent manual typing by molecular biologists.ConclusionsThis work presents an automated genotyping tool from DNA gel electrophoresis images, called GELect, which was written in Java and made available through the imageJ framework. With a novel automated image processing workflow, the tool can accurately segment lanes from a gel matrix, intelligently extract distorted and even doublet bands that are difficult to identify by existing image processing tools. Consequently, genotyping from DNA gel electrophoresis can be performed automatically allowing users to efficiently conduct large scale DNA fingerprinting via DNA gel electrophoresis. The software is freely available from http://www.biotec.or.th/gi/tools/gelect.

Chromosome classification for metaphase selection

Identification of good metaphase spread is an important step in chromosome analysis for genetic disorder detection. In this paper, we propose a rule for chromosome classification to identify good metaphase spreads. The chromosome shapes were classified into four main classes. The first and the second classes refer to individual chromosomes with straight and bended shapes, respectively. The third class is characterized as those chromosomes with overlapping bodies and the forth class is for the non-chromosomal artifacts. Good metaphase spreads should largely contain the first and the second classes while the number of the third class should be kept minimal. Several image parameters were examined and used for creating rule-based classification. The threshold value for each parameter is determined using statistical model. We observed that the empirical probability density function of the parameters can be represented by Gaussian model and, hence, the threshold value can be easily determined. The proposed rules can efficiently and accurately classify the individual chromosome with > 90% accuracy.

Wireless Sensor Network: Application to Vehicular Traffic

In this paper we are reporting our current development of wireless sensor network to effectively monitor vehicular traffic. A simple star configuration that consists of a server node communicating with a number of sensor nodes is proposed because of its low complexity, and easy and quick deployment, maintenance and relocation. Our system consists of the sensor, processor, and RF transceiver. We choose the magneto-resistive sensor to detect vehicles as it yields high accuracy with small size. The sensor yields important vehicle informations such as vehicle count, speed, and classification. The network topology is a simple star network. Two Medium Access Communication Protocols (MAC) are analyzed and can be automatically switched based on two different traffic scenarios. An antenna design is shown to fit with a small sensor node. Experiments show that the proposed system yields good data processing results. The classification of vehicles is very promising for major types of vehicles: motorcycle, small vehicle, and bus. RF communications is employed that cable installation can be avoided. Protocol frame formats are provided for both RF communications and RS232. This protocol is very simple and can be easily extended when new sensors or new data types are available.

Fast processing of microscopic images using object-based extended depth of field

BackgroundMicroscopic analysis requires that foreground objects of interest, e.g. cells, are in focus. In a typical microscopic specimen, the foreground objects may lie on different depths of field necessitating capture of multiple images taken at different focal planes. The extended depth of field (EDoF) technique is a computational method for merging images from different depths of field into a composite image with all foreground objects in focus. Composite images generated by EDoF can be applied in automated image processing and pattern recognition systems. However, current algorithms for EDoF are computationally intensive and impractical, especially for applications such as medical diagnosis where rapid sample turnaround is important. Since foreground objects typically constitute a minor part of an image, the EDoF technique could be made to work much faster if only foreground regions are processed to make the composite image. We propose a novel algorithm called object-based extended depths of field (OEDoF) to address this issue.MethodsThe OEDoF algorithm consists of four major modules: 1) color conversion, 2) object region identification, 3) good contrast pixel identification and 4) detail merging. First, the algorithm employs color conversion to enhance contrast followed by identification of foreground pixels. A composite image is constructed using only these foreground pixels, which dramatically reduces the computational time.ResultsWe used 250 images obtained from 45 specimens of confirmed malaria infections to test our proposed algorithm. The resulting composite images with all in-focus objects were produced using the proposed OEDoF algorithm. We measured the performance of OEDoF in terms of image clarity (quality) and processing time. The features of interest selected by the OEDoF algorithm are comparable in quality with equivalent regions in images processed by the state-of-the-art complex wavelet EDoF algorithm; however, OEDoF required four times less processing time.ConclusionsThis work presents a modification of the extended depth of field approach for efficiently enhancing microscopic images. This selective object processing scheme used in OEDoF can significantly reduce the overall processing time while maintaining the clarity of important image features. The empirical results from parasite-infected red cell images revealed that our proposed method efficiently and effectively produced in-focus composite images. With the speed improvement of OEDoF, this proposed algorithm is suitable for processing large numbers of microscope images, e.g., as required for medical diagnosis.

Segmentation Techniques for Bioimages

The advancement in camera lens and sensors promotes wide-range of applications in which images are to be analyzed so that important characteristics can be extracted and interpreted. There are also great demands in biology in which images, termed Bioimages, from various studies are to be processed; and hence the resulting analyses can be used in various applications, including medical diagnostics, organism behavior studies etc. Segmentation is commonly the first step in Bioimage processing by which such images are to be partitioned based on some specific algorithms so that each partition contains sub-images that can be further interpreted. The quality of a segmentation algorithm, also known as the ability to extract meaningful sub-images, is highly dependent upon image types, the image quality, such as noises/artifacts. This article reviews various segmentation techniques used for processing Bioimages by providing their advantages and limitations when applying to Bioimages. Readers should be able to choose suitable segmentation techniques that are well-suited to extracting meaningful objects from their input Bioimages.