
Andre Luis Chautard BarczakBond University
Andre Luis Chautard Barczak
PhD Computer Science, Master of Engineering (Mech.), Bachelor of Engineering (Mech.)
About
82
Publications
21,072
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
858
Citations
Introduction
Research interests: computer vision, machine learning, data science, parallel computing, fundamental algorithms.
Publications
Publications (82)
There is a large body of evidence that demonstrates the practicable use of moment invariants in real-time computer vision applications. Object detection, recognition and tracking are some of them, to name a few. However, the efficacy of moment invariants is highly susceptible to varying illumination conditions, which is inherent in real-world appli...
Feature extraction using simple formulations such as moments have found different applications in the field of image processing and computer vision. In the last few years, new moments based on orthogonal functions have been proposed. More specifically, the Radial Tchebichef Moments yield features that are numerically stable, and allow for a relativ...
Big Data analytics for storing, processing, and analyzing large-scale datasets has become an essential tool for the industry. The advent of distributed computing frameworks such as Hadoop and Spark offers efficient solutions to analyze vast amounts of data. Due to the application programming interface (API) availability and its performance, Spark b...
This paper presents a coarse-to-fine learning algorithm for multiclass problems. The algorithm is applied to ensemble-based learning by using boosting to construct cascades of classifiers. The goal is to address the training and detection runtime complexities found in an increasing number of classification domains. This research applies a separate-...
In this study, we explored the progression trajectories of artificial intelligence (AI) systems through the lens of complexity theory. We challenged the conventional linear and exponential projections of AI advancement toward Artificial General Intelligence (AGI) underpinned by transformer-based architectures, and posited the existence of critical...
Chronic Kidney Disease (CKD) remains a significant global health challenge, with increasing prevalence and a substantial impact on patient quality of life. Early and accurate prediction of CKD risk is crucial for timely intervention and management. This study presents a comprehensive comparative analysis of both machine learning and deep learning a...
An important course in the computer science discipline is ‘ Data Structures and Algorithms’ (DSA). The coursework lays emphasis on experiential learning for building students’ programming and algorithmic reasoning abilities. Teachers set up a repertoire of formative programming exercises to engage students with different programmatic scenarios to b...
In the last decade, the computer vision field has seen significant progress in multimodal data fusion and learning, where multiple sensors, including depth, infrared, and visual, are used to capture the environment across diverse spectral ranges. Despite these advancements, there has been no systematic and comprehensive evaluation of fusing RGB-D a...
In the last decade, the computer vision field has seen significant progress in multimodal data fusion and learning, where multiple sensors, including depth, infrared, and visual, are used to capture the environment across diverse spectral ranges. Despite these advancements, there has been no systematic and comprehensive evaluation of fusing RGB-D a...
Due to the rapid growth of available data, various platforms offer parallel infrastructure that efficiently processes big data. One of the critical issues is how to use these platforms to optimise resources, and for this reason, performance prediction has been an important topic in the last few years. There are two main approaches to the problem of...
Big data frameworks play a vital role in storing, processing, and analysing large datasets. Apache Spark has been established as one of the most popular big data engines for its efficiency and reliability. However, one of the significant problems of the Spark system is performance prediction. Spark has more than 150 configurable parameters, and con...
Educational institutions need to formulate a well-established data-driven plan to get long-term value from their learning analytics (LA) strategy. By tracking learners’ digital traces and measuring learners’ performance, institutions can discern consequential learning trends via use of predictive models to enhance their instructional services. Howe...
This article proposes a new parallel performance model for different workloads of Spark Big Data applications running on Hadoop clusters. The proposed model can predict the runtime for generic workloads as a function of the number of executors, without necessarily knowing how the algorithms were implemented. For a certain problem size, it is shown...
In recent times Big Data analytics has got tremendous attention and it involves storing, processing, and analysing large scale datasets. The advent of distributed computing frameworks such as Hadoop and Spark offers an efficient solution to analyse vast amounts of data. Due to the availability of an application program ming interface (API) and its...
Big Data analytics for storing, processing, and analyzing large-scale datasets has become an essential tool for the industry. The advent of distributed computing frameworks such as Hadoop and Spark offers efficient solutions to analyze vast amounts of data. Due to the application programming interface (API) availability and its performance, Spark beco...
This work presents an extension to a graph-based evolutionary algorithm, called Genetic Network Programming with Reinforcement Learning (GNP-RL) to make it more amenable for solving coordinated multi-agent path-planning tasks in dynamic environments. We improve the algorithm's ability to evolve meta-level reasoning strategies in three aspects: gene...
In this paper we use machine learning to study the application of Local Tchebichef Moments (LTM) to the problem of texture classification. The original LTM method was proposed by Mukundan (2014). The LTM method can be used for texture analysis in many different ways, either using the moment values directly, or more simply creating a relationship be...
Human action recognition is one of the raison d'être for doing human-computer interaction research, as it is highly vital in meeting the demands of modern society, such as automatic video surveillance for security, patient monitoring for recovery, content-based video retrieval, etc. In line with this, deep learning systems are fast becoming the def...
This paper presents a hybrid Fuzzy-D*lite algorithm for smoothly navigating robots in an unknown terrain, in real-time. D*lite is a clever optimal, incremental and heuristic search algorithm that is known to be capable of achieving a speed up of one to two orders of magnitude over repeated A* searches. Given a target destination and an incomplete m...
The accuracy of feature selection methods is affected by both the nature of the underlying datasets and the actual machine learning algorithms they are combined with. The role these factors have in the final accuracy of the classifiers is generally unknown in advance. This paper presents an ensemble-based feature selection approach that addresses t...
This research explores a new hybrid evolutionary learning methodology for multi-behaviour robot control. The new approach is an extension of the Fuzzy Genetic Network Programming algorithm with Reinforcement learning presented in [1]. The new learning system allows for the utilisation of any pre-trained intelligent systems as processing nodes compr...
The automation of post-harvest fruit grading in the industry is a problem that is receiving considerable attention in the realm of computer vision and machine learning. Classification accuracy with automated systems in this domain is a challenge given the inherent variability in the visual appearance of fruit and its quality-determining features. W...
This chapter sets out to explore the intricacies behind developing a hybrid system for real-time autonomous robot navigation, with target pursuit and obstacle avoidance behaviour, in a dynamic environment. Three complete systems are described, namely, a cascade of four fuzzy systems, a hybrid fuzzy A* system, and a hybrid fuzzy A* with a Voronoi di...
This paper proposes a multi-camera system approach to real-time colour segmentation using a cascade of AdaBoost colour classifiers with error-correcting codes (AdaBoost ECC) trained on arbitrary low-dynamic range cameras. As compared to traditional High-Dynamic Range systems that require the consolidation of multiple low-dynamic range (LDR) images...
Automated grading of fruit is an important industrial task that is expanding rapidly in its uptake. Machine learning-based techniques are increasingly being applied to this domain in order to formulate effective solutions for complex classification tasks. The inherent variability in the visual appearance of fruit and its quality-determining feature...
This chapter sets out to explore the intricacies behind developing a hybrid system for real-time autonomous robot navigation, with target pursuit and obstacle avoidance behaviour, in a dynamic environment. Three complete systems are described, namely, a cascade of four fuzzy systems, a hybrid fuzzy A* system, and a hybrid fuzzy A* with a Voronoi di...
We present a novel approach for the tuning and assessment of a cascade of fuzzy logic systems, working cohesively for robot soccer navigation. We generate calibration maps to comprehensively examine the performance of the cascades, allowing for both the visualisation and quantification of the overall system performance. The experiments demonstrate...
In this work we report the study of a copper capacitive MEMS (Micro-Electro-Mechanical Systems) as a sensor to analyze the quality of automotive fuel such as hydrated ethanol and gasoline used in Brazil. Fuel adulteration is a frequent problem in some countries, including Brazil. The standard Brazilian gasoline ranges from 20 to 25% of dehydrated e...
We propose a general method applicable to existing multiclass boosting-algorithms for creating cascaded classifiers. The motivation is to introduce more tractability to machine learning tasks which require large datasets and involve complex decision boundaries, by way of separate-and-conquer strategies that reduce both the training and detection-ph...
In the context of a Fuzzy-Genetic system, auto-calibration of colour classifiers, under spatially varying illumination conditions, to produce near perfect object recognition accuracy requires a balancing act for the fitness function. One general approach would be to maximise the true positives while minimising the false positives. This has been fou...
In the field of robot navigation, a number of different approaches have been proposed. One of these is Hybrid Fuzzy A* (HFA), which uses the A* algorithm to determine the long term path from the robot to some target, and fuzzy logic to move the robot to each waypoint along the path. This algorithm has been shown to be fast and effective in simulati...
We propose an adaptive learning algorithm for cascades of boosted ensembles that is designed to handle the problem of concept drift in nonstationary environments. The goal was to create a real-time adaptive algorithm for dynamic environments that exhibit varying degrees of drift in high-volume streaming data. This we achieved using a hybrid of dete...
We present a novel approach to multiclass learning using an ensemble-based cascaded learning framework. By implementing a multiclass cascaded classifier with AdaBoost, we show how detection runtimes are accelerated since only a subset of the ensemble is executed, thus making the classifiers suitable for computer vision applications. We also propose...
It usually takes a fusion of image processing and machine learning algorithms in order to build a fully-functioning computer vision system for hand gesture recognition. Fortunately, the complexity of developing such a system could be alleviated by treating the system as a collection of multiple sub-systems working together, in such a way that they...
The aim of this paper is to present an alternative ensemble-based drift learning method that is applicable to cascaded ensemble
classifiers. It is a hybrid of detect-and-retrain and constant-update approaches, thus being equally responsive to both gradual and abrupt concept drifts. It is designed to address the issues
of concept forgetting, experie...
This paper contributes in colour classification under dynamically changing illumination, extending further the capabilities
of our previous works on Fuzzy Colour Contrast Fusion (FCCF), FCCF-Heuristic Assisted Genetic Algorithm (HAGA) for automatic
colour classifier calibration and Variable Colour Depth (VCD). All the aforementioned algorithms were...
Building on the ideas of Viola-Jones [1] we present a framework for training cascades of boosted ensembles (CoBE) which introduces
further modularity and tractability to the training process. It addresses the challenges faced by CoBE frameworks such as
protracted runtimes, slow layer convergences and classifier optimization. The framework possesses...
Under extreme light conditions, a conventional colour CCD camera would fail to render the colours of an object properly as the visible spectrum is either faintly observable in the scene or the presence of glare corrupts the colours sensed. On the other hand, for darkly-illuminated areas, a near-infrared (NIR) camera would sense stronger more discri...
We present a novel method for efficiently training a face detector using large positive datasets in a cascade of boosted ensembles. We extend the successful Viola-Jones (1) framework which achieved low false acceptance rates through bootstrapping negative samples with the capability to also bootstrap large positive datasets thereby capturing more i...
A novel automated blemish detection system for ripe and unripe oranges is proposed in this paper. The algorithm is unique
in that it does not rely on the global variations between pixels depicting the colours of an orange. By utilizing a priori
knowledge of the properties of rounded convex objects, we introduce a set of colour classes that effectiv...
This paper introduces an IO bandwidth reduction technique for real-time moment invariant classifier systems running on both CPUs and GPUs. This system can run in real time on commodity general purpose graphics processor unit (GPGPU) systems. The output IO is reduced by calculating the locations of objects of interest using a projection of the 2D cl...
This paper introduces a general purpose graphics processing unit (GPGPU) stream processing implementation of moment invariants using an integral image or summed area table approach. Summed area tables have been used to help attain real-time performance for some classifier systems, however due to the computational complexity of moment invariants, a...
This paper introduces an extended set of Haar- like features beyond the standard vertically and horizontally aligned Haar-like features (Viola and Jones, 2001a; 2001b) and the 45o twisted Haar-like features (Lienhart and Maydt, 2002; Lienhart et al., 2003a; 2003b). The extended rotated Haar-like features are based on the standard Haar-like features...
This paper introduces the hardware architecture for the BeSTGRID (Broadband Enabled Science and Technology GRID) supercomputer system. This system is a high performance cluster supercomputer with infiniband interconnect. The system has been benchmarked for compute and file IO and is shown to be scalable. The infiniband interconnect provides high ba...
In the first part of this paper, we present a brief review on catadioptric omnidirectional systems. The special case of the hyperbolic omnidirectional system is analysed in depth. The literature shows that a hyperboloidal mirror has two clear advantages over alternative geometries. Firstly, a hyperboloidal mirror has a single projection centre [1]....
We train a face detection system using the PSL framework (1) which combines the AdaBoost learning algorithm and Haar-like features. We demonstrate the ability of this framework to overcome some of the challenges inherent in training classifiers that are structured in cascades of boosted ensembles (CoBE). The PSL classifiers are compared to the Viol...
This paper introduces a stream programming based design of the zero and higher order central moments that use an integral
image or summed area data structure of geometric moments. The stream programming algorithm runs on a general purpose graphics
processing unit (GPGPU) that are becoming commodity hardware, giving real-time performance even for la...
This paper addresses the problem of excessively long classifier training times associated with using the Adaboost algorithm
within the framework of a cascade of boosted ensembles (CoBE). We present new test results confirming the acceleration of
the training phase and the robustness of the Parallel
Strong classifier within the same Layer (PSL) trai...
Classifier based approaches to stereo vision reduce the ambiguity associated with low level texture and feature based image registration, however there are challenges associated with providing accurate object positioning for good depth estimation using these high level approaches. This paper investigates the performance of stereo based systems that...
We propose a mixed structure to form cascades for AdaBoost classifiers, where parallel strong classifiers are trained for each layer. The structure allows for rapid training and guarantees high hit rates without changing the original threshold. We implemented and tested the approach for two datasets from UCI [1], and compared results of binary clas...
This paper presents the design and evaluation of the stream processing implementation of the Integral Image algorithm. The Integral Image is a key component of many image processing algorithms in particular the Haar-like feature based systems. Modern GPUs provide a large number of processors with a peak floating point performance that is significan...
This paper presents a new high precision integral image algorithm that can execute in real-time on a commodity graphics processing unit (GPU). This system makes use of the general processing GPU (GPGPU) paradigm via a stream computing abstraction. The stream computing language used is Brook which allows portability across GPGPUs from multiple manuf...
We present a robust fuzzy colour processing system with automatic rule extraction and colour descriptors calibration for accurate
colour object recognition and tracking in real-time. The system is anchored on the fusion of fuzzy colour contrast rules that
operate on the red, green and blue channels independently and adaptively to compensate for the...
We introduce a mobile and/ or remote sensor framework for computationally fast rotationally invariant feature detection. The sensor and computational system is small enough to be carried by a mobile robot platform with a relatively low power requirement allowing the system to be deployed without the need for frequent recharges of the batteries. The...
This short paper compares the performance between a InfiniBand based Cluster and an older Gigabit-based cluster. The InfiniBand interconnect provides high bandwidth, low latency links between both compute nodes and storage system which gives good parallel scalability. The linpack benchmark scales linearly up to the full 208 processors. Although Inf...
In this paper a feature extraction method based on moment invariants was applied to handwritten digits' recognition. The features are computed using 15 special Summed-area Tables (SATs), which allows for fast computation at different positions and angles. The feature extraction method uses moments up to the 4 th order, it can increase the number of...
This thesis studies rapid object detection, focusing on feature-based methods. Firstly, modifications of training and detection of the Viola-Jones method are made to improve performance and overcome some of the current limitations such as rotation, occlusion and articulation. New classifiers produced by training and by converting existing classifie...
This thesis studies rapid object detection, focusing on feature-based methods. Firstly, modifications of training and detection of the Viola-Jones method are made to improve performance and overcome some of the current limitations such as rotation, occlusion and articulation. New classifiers produced by training and by converting existing classifie...
This paper introduces an extended set of Haar-like features beyond the standard vertically and horizontally aligned Haar-like features [Viola and Jones, 2001a; 2001b] and the 45 o twisted Haar-like features [Lienhart and Maydt, 2002; Lienhart et al., 2003a; 2003b]. The extended rotated Haar-like features are based on the standard Haar-like features...
This paper presents an Adaboost learning based Fuzzy colour contrast fusion colour classification algorithm. The system is able to learn colour discrimination knowledge during training that accounts for hue and saturation drift of target colours. The performance of the system is compared to a pure Fuzzy System using colour contrast rules, a pure Ad...
This paper proposes a new approach to detect rotated objects at distinct angles using the Viola-Jones detector. The use of additional Integral Images makes an approximation the Haar-like features for any given angle. The proposed approach uses dieren t types of Haar-like features, including features that compute areas at 45o, 26.5o and 63.5o of rot...
In this paper, we discuss the importance of the choice of features in digital image object recognition. The features can be classified as invariants or non-invariants. Invariant features are robust against one or more modifications such as rotations, translations, scaling and different light (illumination) conditions. Noninvariant features are usua...
In this paper we discuss the importance of the choice of features in digital image object recognition. The features can be classified as invariants or non-invariants. Invariant features are robust against one or more modifications such as rotations, translations, scaling and different light (illumination) conditions. Non-invariant features are usua...
This paper proposes a new approach to detect rotated objects at distinct angles using the Viola-Jones detector. The approach uses different types of Haar-like features, including twisted features which compute areas at 45 o of rotation. A conversion algorithm takes an original feature from the classifier and computes two features to find an equival...
This paper describes the use of parallel classifiers in real-time object recognition. Based on preliminary results we propose a mobile platform built with off-the-shelf components (hardware and software). This platform could be fitted in a robot, car, backpack etc. A model of the performance of the platform using the Viola-Jones detector is present...
With the increase of research activities in vision-based hand posture and gesture recognition, new methods and algorithms are being developed. Although less attention is being paid to developing a standard platform for this purpose. Developing a database of hand gesture images is a necessary first step for standardizing the research on hand gesture...
This paper presents further evaluation of the rapid object detection scheme developed by Viola and Jones and later extended
by Lienhart et al. In this work the hypothesis that it is possible to train a classifier to find partially occluded objects
was tested experimentally.
This paper evaluates the rapid object detection scheme developed by Viola and Jones (2001) in the presence of partial occlusions. It also discusses problems related to the choice of the image sets and the way they are used in the training process. The hypothesis that it is possible to train a single classier to nd partial occluded objects was teste...
This paper presents some performance results obtained from a new Beowulf cluster, the Helix, built at Massey University, Auckland
funded by the Allan Wilson Center for Evolutionary Ecology. Issues concerning network latency and the effect of the switching
fabric and network topology on performance are discussed. In order to assess how the system pe...
In the past many minimum zone center (MZC) algorithms have been developed.
In opposition, many coordinate measuring machines (CMM) still use
least-squares center (LSC) algorithms. A MZC algorithm that uses
a computational geometry approach through the Voronoi diagrams to
determine circularity can be compared with LSC. Both algorithms are
compared b...
The precise assessment of out-of-roundness is an important issue in
metrology. There are always errors associated with these measurements,
caused by different sources. The computer aided measuring machines
have an additional source of error, the algorithm itself. This subject
was only considered important in recent times. The main objective
in this...