Woo Chaw Seng

A review of biometric technology along with trends and prospects

Abstract Identity management through biometrics offer potential advantages over knowledge and possession based methods. A wide variety of biometric modalities have been tested so far but several factors paralyze the accuracy of mono-modal biometric systems. Usually, the analysis of multiple modalities offers better accuracy. An extensive review of biometric technology is presented here. Besides the mono-modal systems, the article also discusses multi-modal biometric systems along with their architecture and information fusion levels. The paper along with the exemplary evidences highlights the potential for biometric technology, market value and prospects.

A new method for fruits recognition system

Several fruit recognition techniques are developed based upon color and shape attributes. However, different fruit images may have similar or identical color and shape values. Hence, using color features and shape features analysis methods are still not robust and effective enough to identify and distinguish fruits images. A new fruit recognition system has been proposed, which combines three features analysis methods: color-based, shape-based and size-based in order to increase accuracy of recognition. The proposed method classifies and recognizes fruit images based on obtained feature values by using nearest neighbours classification. Consequently, our system shows the fruit name and a short description to user. The proposed fruit recognition system analysis classifies and identifies fruits successfully up to 90% accuracy. This system also serves as a useful tool in a variety of fields such as education, image retrieval and plantation science.

A Comparison Study on Hand Recognition Approaches

Hand recognition is one of the popular biometry technologies, especially in physical access control and time and attendance monitoring. Over the years, researches have been carried out in developing different techniques to identify the hand images. Yet, there is little literature work compiling the previous hard work on hand recognition researches in the past four decades. Firstly, we outline the introduction on biometrics. Then, we present the evolution of hand recognition as in the historical perspective. As in the third section, we study on the technology overview of system operation. We compare various approaches done in three categories, namely hand geometry, hand contour and palm print. After that, we further discuss the performance of the methodology as stated in the comparison. Lastly, we conclude our survey with future development. Thereby, this paper serves the purpose as a gateway for hand recognition literature survey to the novel or interested researchers.

Automatic classification of medical X-ray images using a bag of visual words

A novel approach is presented to gain high classification rate for each class of ImageCLEF 2007 medical database. The learning phase consists of four iterations where different classification models were generated as per iteration. For the iterations, a model generation process was performed in two steps. The first step starts with construction of a model from the entire dataset. This model was then assessed to filter high accuracy classes (HAC). These classes were those predicted with an accuracy rate above 80%. This evaluation performed on 20% of the training dataset was taken as test data. In the second step, classes under HAC were only used to construct the classification model. The same processes will be performed in the next iteration on the classes which were left with accuracy below 80% from the previous iteration. The methodology presented is based on a bag of visual words for feature extraction and the radial basis function (RBF)-based support vector machine classifier. As a result, four classification models were generated from 77, 17, 12 and 10 classes, respectively. These models were constructed and evaluated on a database consisting of 11 000 medical X-ray images (training dataset) and 1000 (testing dataset) of 116 classes. The accuracy rate obtained by each generated model outperformed the results obtained by only one model on the entire dataset.

Evaluation of a Content-Based Retrieval System for Blood Cell Images with Automated Methods

Content-based image retrieval techniques have been extensively studied for the past few years. With the growth of digital medical image databases, the demand for content-based analysis and retrieval tools has been increasing remarkably. Blood cell image is a key diagnostic tool for hematologists. An automated system that can retrieved relevant blood cell images correctly and efficiently would save the effort and time of hematologists. The purpose of this work is to develop such a content-based image retrieval system. Global color histogram and wavelet-based methods are used in the prototype. The system allows users to search by providing a query image and select one of four implemented methods. The obtained results demonstrate the proposed extended query refinement has the potential to capture a user’s high level query and perception subjectivity by dynamically giving better query combinations. Color-based methods performed better than wavelet-based methods with regard to precision, recall rate and retrieval time. Shape and density of blood cells are suggested as measurements for future improvement. The system developed is useful for undergraduate education.

A Content-Based Retrieval System for Blood Cells Images

Content-based image retrieval techniques have extensively been studied for past few years. However; few systems are dedicated to medical images today while demands for content-based analysis and retrieval tools increases with growth of digital medical image databases. A prototype of content-based image retrieval system is built to investigate performance of descriptors for blood cell image retrieval.Here, traditional global color histogram and wavelet-based method is investigated. In addition, performance of indexing method for the aforementioned descriptors is analyzed. The prototype system allows users to search by providing a query image and selecting one of four implemented methods.Research goal is enhancing current content-based image retrieval techniques. Proposed method is able to perform clinically relevant queries on image databases without user supervision.

Content-Based Image Retrieval for Blood Cells

The rapid development of technologies and steadily growing amounts of digital information highlight the need of developing an accessing system. Content-based image indexing and retrieval has been an important research area in computer science for the last few decades. The approaches of content-based image retrieval using low level features such as colour, shape and texture are investigated to create a prototype that perceives blood cell images similar to a human. The histogram of red, green, and blue colour components is analyzed. The wavelet decomposition is also used to analyze texture. In addition, morphological operations such as opening and closing are applied to analyze object shape. Lastly, colour, texture, and shape in image retrieval are integrated in order to increase the retrieval accuracy. Experimental results using four different classes of 150 blood cell images showed 95.68% of retrieval accuracy.

Traffic sign recognition model on mobile device

Incorporation of a good machine vision into mobile device can create a powerful application. With such advancement, mobile users can use their existing smartphone as their third-eye to perceive the world. This paper introduces a framework using the smartphone to increase ambient intelligence and road safety of moving vehicles through traffic sign alert application. The driver is alerted of the incoming traffic signs in different modes depending on the users preference. However, the competency of the application is still bounded with the capability of a normal human vision. Unlike conventional research work, this paper emphasizes on portability and expandability. Portability means there is no additional installation or placement of electronic hardware required in the vehicle in order to make the system work. Expandability focuses on the transparency of the traffic sign recognition output to other applications within same hardware device or external devices. This provides an option to other developers to use or expand their own applications by using the result of the proposed application. An interaction model of the traffic sign recognition system on mobile device is introduced.

Combined Feature Extraction on Medical X-ray Images

Medical images form an essential source of information for various important processes such as diagnosis of diseases, surgical planning, medical reference, research and training. Therefore, effective and meaningful search and classification of these images are vital. In this paper, the approaches of content-based image retrieval (CBIR) using low level features such as shape and texture are investigated in order to create a framework that classify medical X-ray image automatically. Gray level Co-occurrence Matrix, Canny Edge Operator, Local Binary Pattern and pixel level information of the images in this work act as image based feature representations which are adopted in our method. The state-of-the-art machine learning method, Support Vector Machine (SVM) is used for classification. In addition, the performance of image classification offered by combining the promising features stated above is investigated. Experimental results using 116 different classes of 11,000 X-ray images showed 90.7% classification accuracy.

An improved genetic-fuzzy system for classification and data analysis

Interpretability of classification systems, which refers to the ability of these systems to express their behavior in an understandable way, has recently gained more attention and it is considered as an important requirement especially for knowledge-based systems. The main objective of this study is to improve the ability of a well-known fuzzy classifier proposed in Ishibuchi and Nojima (2007) to maximize the accuracy while preserve its interpretability. To achieve the above-mentioned objective, we propose two variants of the original fuzzy classifier. In the first variant classifier, the same components of the original classifier were used except NSGA-II which was replaced by an enhanced version called Controlled Elitism NSGA-II. This replacement aims at improving the ability of the first variant classifier to find non-dominated solutions with better interpretability-accuracy trade-off. In the second variant classifier, we further improve the first variant classifier by enhancing the selection method of the antecedent conditions of the rules generated in the initial population of genetic algorithm. Unlike the method applied in the original classifier and the first variant classifier, which uses a random selection of the antecedent conditions, we proposed a feature-based selection method to favor the antecedent conditions associated with the most relevant features. The results show that the two variant classifiers find more non-dominated fuzzy rule-based systems with better generalization ability than the original method which suggests that Controlled Elitism NSGA-II algorithm is more efficient than NSGA-II. In addition, feature-based selection method applied in the second variant classifier allowed this method to successfully obtain high-quality solutions as it has consistently achieved the best error rates for all the data sets compared to the original method and the first variant classifier.