Colour is one of the quality features used in determining agarwood quality and grade. This resear... more Colour is one of the quality features used in determining agarwood quality and grade. This research investigates the relationship of agarwood physical colour properties with its price. Colour features of agarwood images taken from Red, Green, Blue (RGB), Hue, Saturation, Intensity (HSI) and Commission Internationale de l'Eclairage standard L,*a,*b colorspace (CIELAB) has been extracted by Fuzzy C-Means (FCM) classification. The performance of these colorspaces has been determined using five cluster validity indices. One hundred and forty agarwood images consisting of seven different prices have been analyzed. From the experiment, it has been shown that CIELAB colorspace with four numbers of clusters gave more consistent and accurate results compared to the others. It also gave a significant relationship when tested using analysis of variance (ANOVA) and Duncan Multiple Range Test (DMRT). The method performs best when classifying lower price agarwood with component L for RM250 an...
Colour is one of the quality features used in determining agarwood quality and grade. This resear... more Colour is one of the quality features used in determining agarwood quality and grade. This research investigates the relationship of agarwood physical colour properties with its price. Colour features of agarwood images taken from Red, Green, Blue (RGB), Hue, Saturation, Intensity (HSI) and Commission Internationale de l'Eclairage standard L,*a,*b colorspace (CIELAB) has been extracted by Fuzzy C-Means (FCM) classification. The performance of these colorspaces has been determined using five cluster validity indices. One hundred and forty agarwood images consisting of seven different prices have been analyzed. From the experiment, it has been shown that CIELAB colorspace with four numbers of clusters gave more consistent and accurate results compared to the others. It also gave a significant relationship when tested using analysis of variance (ANOVA) and Duncan Multiple Range Test (DMRT). The method performs best when classifying lower price agarwood with component L for RM250 and RM800, b for RM350 and RM2500 while a for RM900. Overall, the proposed method proved that there is a significant relationship between agarwood price and its physical colour properties, which thus shows that the image processing has an enormous potential to be used in the agarwood chips grading task for the future development.
The oil palm is the largest plantation industry in Malaysia. It has been one of the major contrib... more The oil palm is the largest plantation industry in Malaysia. It has been one of the major contributors to the country’s economy and the main pillar of the commodity sectors. For over 40 years, the oil palm industry has faced a lethal and incurable disease, Basal Stem Rot (BSR), which is caused by a type of bracket fungus, Ganoderma boninense. The oil palm physical symptoms infected by BSR disease are appearance of many unopened spears, flattening of crown and smaller crown size. Terrestrial Laser Scanning (TLS, also known as ground-based LiDAR) can be used to provide accurate and precise information on tree morphology with high resolution. This study proposed an image processing technique using the ground input data taken from a TLS. Five parameters were used in the study are number of laser hits in strata 200 cm and 850 cm from the top, namely as C200 and C850, respectively, crown area, frond number and frond angle. The objectives of this study are to analyse the relationship betw...
Application of artificial neural network in predicting crop yield: a review
Agricultural system is very complex since it deals with large data situation which comes from a n... more Agricultural system is very complex since it deals with large data situation which comes from a number of factors. A lot of techniques and approaches have been used to identify any interactions between factors that affecting yields with the crop performances. The application of neural network to the task of solving non-linear and complex systems is promising. This paper presents a review on the use of artificial neural network (ANN) in predicting crop yield using various crop performance factors. General overview on the application of ANN and the basic concept of neural network architecture are also presented. From the literature, it has been shown that ANN provides better interpretation of crop variability compared to the other methods.
The interest in visual-based surveillance systems, especially in natural disaster applications, s... more The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than t...
Maturity of paddy contributes a very high impact on the production of rice quality. Immature padd... more Maturity of paddy contributes a very high impact on the production of rice quality. Immature paddy will produce high percentage of broken rice, poor grain quality and more chances of disease attack during storage. This research focuses on the use of image processing technique for paddy maturity identification. Three types of automatic image thresholding techniques had been used during a segmentation process, i.e., Mean, Median and Otsu. The average intensity of paddy image is used as features in development of a decision rule to identify paddy maturity. All of the techniques give small value of standard deviation which is around 0.01 in mature and immature paddy. Results from the test validation had shown that, all of the techniques can identify mature paddy with the percentage of success rate of 92.31%. For immature paddy, features extracted by Median give superior result which is 100% success rate compared to the others. In overall, Median is the most reliable approached for matur...
The interest in visual-based surveillance systems, especially in natural disaster applications, s... more The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than t...
Web based agricultural data management system and methods of managing thereof
A web based agricultural data management system is provided, the system includes a server and a d... more A web based agricultural data management system is provided, the system includes a server and a database network connectible to an interface terminal, wherein data is translatable to readable and viewable maps used in agriculture.
The Chokanan mango (Mangifera indica) has a high commercial potential. Its sugar content increase... more The Chokanan mango (Mangifera indica) has a high commercial potential. Its sugar content increases as the colour changes during the maturation process. In this research, the relationship between the sweetness of the Chokanan mango and its mean pixel values in RGB and HSB colour space is analyzed. This information could be utilized in determining the level of sweetness of the Chokanan mango without destroying the fruit. A Keyence machine vision system was employed to capture the images of the mango in RGB and HSB colour spaces. Based on the findings, it could be concluded that hue not only has the highest correlation value (-0.916), but also has the lowest value of the standard deviation at all levels of sweetness compared to other colour components. It is possible to determine sweetness at Level 1 and Level 2 with a 100% success rate and a 87% success rate at Level 3.
Change detection studies in Matang Mangrove Forest area, Perak
In this research wok, three different techniques of change detection were used to detect changes ... more In this research wok, three different techniques of change detection were used to detect changes in forest areas. One of the techniques used a local similarity measure approach to detect changes. This new approach of change detection technique, which used mutual information to measure the similarity between two multi-temporal images, was developed based on correspondence of the pixel values, rather than the difference in their intensity. Pixels suffering any changes will be maximally dissimilar. The study was conducted using multi-temporal SPOT 5 satellite images, with the resolution of 10 m x10 m on 5th August 2005 and 13th June 2007. The experimental results show that local mutual information provides more reliable results in detecting changes of the multi-temporal images containing different lighting condition compared to the image differencing and NDVI technique, specifically in areas with less plant growth. In addition, it can also overcome the problem on selecting the threshol...
Natural rubber tree is one of major plantation crops in Malaysia. To increase the production and ... more Natural rubber tree is one of major plantation crops in Malaysia. To increase the production and germination of the rubber, proper placement of seeds is needed. Ventral surface of rubber seed needs to be placed downward attached to the soil. Nowadays, it is necessary to use an automatic detection technology in order to reduce labor intensity and improve the production efficiency. Therefore, this study was conducted to identify the dorsal and ventral surface of rubber seeds using image processing and machine learning approach. Canny edge detection was used to identify features at the center of the seed namely maximum length of detected edge, ratio major and minor axis, number of pixel, maximum convolution, and number of intersection. These features were used as the input parameters in classifying the dorsal and ventral surface at horizontal position. A new prediction model using decision rule was developed for identification of the dorsal and ventral surface. Support Vector Machine (...
Elastic image registration for landslides monitoring
Landslide is a type of mass movement that causes damage in many areas. The evolving remote sensin... more Landslide is a type of mass movement that causes damage in many areas. The evolving remote sensing technology in producing high resolution images may help in landslide studies. However, the problem in detecting small size landslides is still challenging when suitable image resolution of the area being analyzed is not available. In this paper, a novel method based on elastic image registration, appropriate for the detection of small landslides will be presented. This method can be used to detect and quantify landslide movement with sub-pixel accuracy. It is based on the invocation of deformation operators which imitate the deformations expected to be observed when a landslide occurs. The similarity between two images is measured by a similarity function which takes into consideration grey level value correlation and geometric deformation. The geometric deformation term ensures that the minimum necessary deformation compatible with the two images is employed. An extra term, ensuring m...
The oil palm is the largest plantation industry in Malaysia. It has been one of the major contrib... more The oil palm is the largest plantation industry in Malaysia. It has been one of the major contributors to the country’s economy and the main pillar of the commodity sectors. For over 40 years, the oil palm industry has faced a lethal and incurable disease, Basal Stem Rot (BSR), which is caused by a type of bracket fungus, Ganoderma boninense. The oil palm physical symptoms infected by BSR disease are appearance of many unopened spears, flattening of crown and smaller crown size. Terrestrial Laser Scanning (TLS, also known as ground-based LiDAR) can be used to provide accurate and precise information on tree morphology with high resolution. This study proposed an image processing technique using the ground input data taken from a TLS. Five parameters were used in the study are number of laser hits in strata 200 cm and 850 cm from the top, namely as C200 and C850, respectively, crown area, frond number and frond angle. The objectives of this study are to analyse the relationship betw...
Ganoderma boninense (G.boninense) is the causal agent of basal stem rot (BSR) which significantly... more Ganoderma boninense (G.boninense) is the causal agent of basal stem rot (BSR) which significantly reduced the productivity of oil palm plantations in Southeast Asia. At early stage, the disease did not show any physical symptoms that could be seen with naked eyes resulted in detection difficulties. To date, there was no effective detection for this disease, and conventional methods such as manual and laboratory-based required trained specialists as well as time-consuming. Therefore, this study was conducted using hyperspectral remote sensing to investigate the differences in spectral reflectance of young leaf (frond one (F1) of healthy and G. boninense infected oil palm seedlings. The seedlings were inoculated with G. boninense pathogen at five months old. At five months after inoculation, 558 spectral signatures of F1 were extracted from acquired hyperspectral images. Noise removal was done to the extracted spectral signatures to remove outliers in the data. Then, the spectral sign...
Basal Stem Rot (BSR) is the most destructive disease instigated by a white wood rotting fungus ca... more Basal Stem Rot (BSR) is the most destructive disease instigated by a white wood rotting fungus called Ganoderma boninense, which cause great economic setback in oil palm productivity. It attacks the basal stem of oil palm trees, causing them to slowly rot. It also affects the xylem tissues that eventually interrupt water transportation to the upper part of the oil palm, turning the leaves at the frond become yellow. This problem should be prevented during nursery stage by separating between healthy and BSR-infected seedling. Therefore, this study focuses on the potential use of thermal imaging for detecting BSR in oil palm at seedling. Thermal images of oil palm seedling from healthy and BSR-infected were captured and processed to extract several thermal properties of the seedling, i.e., maximum, minimum, mean, and standard deviation of pixel intensity value. These values were then undergone statistical analysis to identify its significant different in differentiating healthy and BS...
Multi-temporal analysis of terrestrial laser scanning data to detect basal stem rot in oil palm trees
Precision Agriculture
Terrestrial laser scanning technology is an advanced active remote sensing ranging method that is... more Terrestrial laser scanning technology is an advanced active remote sensing ranging method that is well suited for yielding high-resolution scans of the morphology of a tree, which is an indicator of the health of the plant. The Ganoderma boninense fungus causes basal stem rot (BSR), which threatens the oil palm industry in Malaysia. To date, the current practice of inspection in a plantation is conducted every 6 months. Monitoring the progress with a closer gap is required to comprehend if any changes can be seen earlier than 6 months. Therefore, the objectives of this study were to identify the most suitable parameters of the oil palm trees to detect the BSR disease based on temporal laser scanning data and to identify suitable time frames for monitoring the progress of the symptoms of the disease. Terrestrial laser scanning data was used to analyse changes in the crown and frond metrics of oil palm trees with two different scan durations i.e., 2- and 4-months after the first scan. This spatio-temporal data is important in the precision agriculture field for better oil palm management, to understand the disease development for long-term solutions and also to provide a fast response so that appropriate treatment can be given to the palm as early as possible. Statistical analyses, i.e., the Kruskal–Wallis test with α = 0.05 and the Wilcoxon post-hoc test, were conducted to determine significant differences in the parameters at different points in time. The results show that crown strata number 17 (850 cm from the top) and the crown area were the most suitable parameters to be used. Furthermore, the oil palm trees with BSR can be detected by comparing the 4-month scan or the second 2-month scan. The results have shown that the effect of Ganoderma boninense infection can be differentiated at the later stage. In conclusion, the changes can be measured at 4-months after the first inspection, thus helping to preventing crop losses.
Basal stem rot disease (BSR) in oil palm plants is caused by the Ganoderma boninense (G. boninens... more Basal stem rot disease (BSR) in oil palm plants is caused by the Ganoderma boninense (G. boninense) fungus. BSR is a major disease that affects oil palm plantations in Malaysia and Indonesia. As of now, the only available sustaining measure is to prolong the life of oil palm trees since there has been no effective treatment for the BSR disease. This project used an ALOS PALSAR-2 image with dual polarization, Horizontal transmit and Horizontal receive (HH) and Horizontal transmit and Vertical receive (HV). The aims of this study were to (1) identify the potential backscatter variables; and (2) examine the performance of machine learning (ML) classifiers (Multilayer Perceptron (MLP) and Random Forest (RF) to classify oil palm trees that are non-infected and infected by G. boninense. The sample size consisted of 55 uninfected trees and 37 infected trees. We used the imbalance data approach (Synthetic Minority Over-Sampling Technique (SMOTE) in these classifications due to the differing...
Uploads
Papers by Siti Bejo