Abdullah Zawawi Talib

Enhancing the low quality images using Unsupervised Colour Correction Method

Underwater images are affected by reduced contrast and non-uniform colour cast due to the absorption and scattering of light in the aquatic environment. This affects the quality and reliability of image processing and therefore colour correction is a necessary pre-processing stage. In this paper, we propose an Unsupervised Colour Correction Method (UCM) for underwater image enhancement. UCM is based on colour balancing, contrast correction of RGB colour model and contrast correction of HSI colour model. Firstly, the colour cast is reduced by equalizing the colour values. Secondly, an enhancement to a contrast correction method is applied to increase the Red colour by stretching red histogram towards the maximum (i.e., right side), similarly the Blue colour is reduced by stretching the blue histogram towards the minimum (i.e., left side). Thirdly, the Saturation and Intensity components of the HSI colour model have been applied for contrast correction to increase the true colour using Saturation and to address the illumination problem through Intensity. We compare our results with three well known methods, namely Gray World, White Patch and Histogram Equalisation using Adobe Photoshop. The proposed method has produced better results than the existing methods.

Modeling Groups of Pedestrians in Least Effort Crowd Movements Using Cellular Automata

Groups of pedestrians like family members and friends normally move slower than others and therefore act as a virtual barrier and slow down the crowd. In this paper we present our variation of least effort cellular automata algorithm which also considers the effect of pedestrian groups on crowd movement. The algorithm has been used in small scale movement layer of our multi-agent crowd simulation platform in order to allow more realistic simulations of crowd flows. A simple walkway scenario has been used to test the outcome of the model. Preliminary results of the simulation of the effect of groups are reported in this paper.

Removing salt-and-pepper noise from binary images of engineering drawings

Removing noise in engineering drawing images is important before applying image analysis processes. Noise should be removed while keeping the fine detail of the image intact. A noise removal algorithm that can remove noise while retaining fine graphical elements is presented in this paper. The algorithm studies the neighborhood of thin lines before choosing to remove or retain it. Real scanned images from GRECpsila03 and GRECpsila05 arc segmentation contests corrupted by 15% uniform salt/pepper noise are used in this experiment. Objective distortion measurements including PSNR and MSE show that our algorithm gives better quality images compared with other methods.

Simulating Crowd Movements Using Fine Grid Cellular Automata

Cellular automata models have been extensively used for simulating pedestrian movements. One weakness of this type of models, is the size of the cells which is mostly considered to be of the size of a pedestrian (i.e. 40cm*40cm or near to it). Each pedestrian stands in a single cell and during simulation time steps, transits to neighbouring cells. The size of the cells dictates discrete speed steps for pedestrians and chess like movements. A pedestrian could move one or more cells in a simulation time step or do not move at all. In order to have more smooth movement and different speeds for pedestrians (i.e. from different ages, physical and health status) we propose a finer grid cellular automata. We use this model to build a least effort cellular automata movement algorithm. The algorithm has been used in small scale movement layer of our multi-agent crowd simulation platform in order to allow more realistic simulations of crowd flows. A simple walkway scenario has been used to test the outcome of the model. Results of the simulation are reported in this paper.

An Exploratory Study on the Trend of Smartphone Usage in a Developing Country

The purpose of this study is to better understand the current dynamics of the Malaysian market for mobile content and applications. This paper presents the result of a survey on the trend of smartphone from the perspective of end consumers. The data was collected from 1814 respondents across major cities in Malaysia. This study has looked into the familiarity of users towards smartphones, choices of smartphone brand and service providers, and most importantly the determinants that influence their purchasing decision. Additionally, the consumers’ preferences on smartphone specifications such as design, computing power, operating platform, and price are investigated. The statistics presented is to provide fundamental information regarding the status and trends in the smartphone market in Malaysia. Such information is useful for academics to the development of future works in the field, and for smartphone manufacturers, application developers and other stakeholders to plan their direction in the Malaysian smartphone market.

GREC'09 arc segmentation contest: performance evaluation on old documents

Empirical performance evaluation of raster to vector methods is an important topic in the area of graphics recognition. By studying automatic vectorization methods we can reveal the maturity of the tested methods whether as a research prototype or a commercial software. Arc Segmentation Contest held in conjunction with the eighth IAPR International Workshop on Graphics Recognition (GREC09) is an excellent opportunity for researchers to present the results of their proposed raster to vector methods. The contest provides a uniform platform where the output of different methods can be analyzed. The relevance of the contest is further revealed by the creation of new test images with their ground truth data. Old documents were used in this contest. Five methods participated (two research prototypes and three commercial software). Two tests were performed namely between-methods test (participated by all methods) and within-method test (participated by only one method). This paper presents the results of the contest.

Learning History Using Role-Playing Game (RPG) on Mobile Platform

Mobile learning is one of the most convenient approaches in e-learning as it is accessible from virtually anywhere. This paper describes our experience in designing and implementing a framework for a mobile learning application that can assist students in understanding history lesson using role-playing game (RPG) approach. The implementation is based on the narrative of a Malaysian legendary warrior, Merong Mahawangsa. This application was developed on an iOS platform and a crowd simulation technique was used in the application in order to make it more interactive and realistic. The Dijkstra shortest path algorithm was used to search the shortest path for the avatar to move around. Initial investigations suggest that applying the RPG concept has indeed provided a much better learning environment especially in helping students in learning their history lessons.

Salt and Pepper Noise Removal from Document Images

In this paper a noise removal algorithm is proposed by adding a procedure to enhance noise removal to a third party algorithm as a post processing step. The procedure (TAMD) has been proposed to enhance salt and pepper noise removal. TAMD analyzes thin line blobs before deciding to retain or remove them. It has been successfully applied previously in two noise removal algorithms by integrating their algorithm logic with the procedure. In this paper, a noise removal algorithm is proposed by utilizing it as a post processing step. The performance of the proposed noise removal algorithm is compared to many other algorithms including state of the art methods such as median and center weighted median. Real scanned images of mechanical engineering drawings corrupted by 20% salt and pepper noise are used in the experiment. Objective performance evaluation (PSNR and DRDM) has shown that our proposed noise removal algorithm is better than other studied algorithms.

Visual Language Framework for Plant Modeling Using L-System

The L-system algorithm can be very useful in modeling realistic plants for virtual environment modeling and also in graphics applications besides as a tool for biological plant simulation. However, there are hardly any L-system applications which cater for people who do not have prior knowledge in L-systems nor programming skills. This paper describes how we design and develop a visual language framework for L-system plant modeling to cater to this group of people as well as experts in L-system modeling. The purpose of this research is to design a visual language framework for L-system and to study the usefulness and effectiveness of visual language in L-system plant modeling. The visual language framework covers the L-system attributes and grammar in the form of icon-based visual language.

Tracking Multiple Fish in a Single Tank Using an Improved Particle Filter

Studies on tracking fishes have become a popular research endeavour in recent years. Many methods have been used to track fishes by integrating microchips in fishes, using infra-red cameras, image processing and motion sensor. The use of particle filter in the process of tracking has been widely used by researchers. Particle filters is used to track people, fluid movement and animals. In this paper, the particle filter algorithm is improved to track multiple fish in a fish tank. The aim is to identify every fish trajectories and fish target location for further analysis. The main challenge is to ensure that the correct fish are tracked and the algorithm manages to identify specific fish even if they overlaps with each another. The objective of the study is to improve the existing particle filter to track multiple fish in a single fish tank. The improved algorithm contains an additional cache which stores the object’s position to estimate the next potential move of the fish. The result is evaluated by comparing existing algorithm without the enhancement with the improved algorithm. Besides, suggestions in improving the particle filter will also be discussed in this paper.