Guang Deng

La Trobe University · Department of Engineering

Generalized linear image processing systems have been developed from physical image formation models , human visual perception models, and mathematical models. Although there have been many papers on the extension, parameterization, and symmetrization of some of these systems, what is lacking is a unified framework such that the development and stu...

There has been continuous research in edge-aware filters which have found many applications in computer vision and image processing. In this paper, we propose a principledapproach for the development of edge-aware filters. The proposed approach is based on two well established principles: optimal parameter estimation and Bayesian model averaging (B...

In this paper, we consider a signal/parameter estimation problem that is based on a linear model structure and a given setting of statistical models with unknown hyperparameters. We consider several combinations of Gaussian and Laplacian models. We develop iterative algorithms based on two typical machine learning methods - the evidence-based metho...

Describes a new implementation of Lee's (1980) image enhancement algorithm. This approach, based on the logarithmic image processing (LIP) model, can simultaneously enhance the overall contrast and the sharpness of an image. A normalized complement transform has been proposed to simplify the analysis and the implementation of the LIP model-based al...

A study is presented of a maximum likelihood based framework for second-level adaptive prediction which is formed from a group of predictors. It is a natural extension to first-level prediction which is formed directly from a group of pixels. The proposed framework offers a greater degree of freedom for adaptation and tackles the problem of model u...

Marine snow, the floating particles in underwater images, severely degrades the visibility and performance of human and machine vision systems. This paper proposes a novel method to reduce the marine snow interference using deep learning techniques. We first synthesize realistic marine snow samples by training a Generative Adversarial Network (GAN)...

Internet of Things (IoT) applications continue to expand into new applications with a growing need for image processing on the edge. Many edge devices are resource limited microcontrollers, which significantly prohibits many of the mature image processing algorithms. This paper proposes an approach optimized, for resource constrained processors rem...

Iterative reverse filters have been recently developed to address the problem of removing effects of a black box image filter. Because numerous iterations are usually required to achieve the desired result, the processing speed is slow. In this paper, we propose to use fixed-point acceleration techniques to tackle this problem. We present an interp...

Depth information is useful in many image processing applications. However, since taking a picture is a process of projection of a 3D scene onto a 2D imaging sensor, the depth information is embedded in the image. Extracting the depth information from the image is a challenging task. A guiding principle is that the level of blurriness due to defocu...

In this paper, we study the problem of reverse image filtering. An image filter denoted g(.), which is available as a black box, produces an observation b = g(x) when provided with an input x. The problem is to estimate the original input signal x from the black box filter g(.) and the observation b. We study and re-develop state-of-the-art methods...

Background Color distortion is an inherent problem in image-based phenotyping systems that are illuminated by artificial light. This distortion is problematic when examining plants because it can cause data to be incorrectly interpreted. One of the leading causes of color distortion is the non-uniform spectral and spatial distribution of artificial...

In this paper, a new problem of reverse image filtering is addressed. The problem is to reverse the effect of an image filter given the observation b = g(x) . The filter g is modelled as an available black box. An inverse method is proposed to recover the input image x . The key idea is to formulate this inverse problem as minimizing a loca...

ABSTRACT: In this paper, we address a new problem of reversing the effect of an image filter, which can be linear or nonlinear. The assumption is that the algorithm of the filter is unknown and the filter is available as a black box. We formulate this inverse problem as minimizing a local patch-based cost function and use total derivative to approx...

Edge-aware smoothing is an essential tool for computer vision, graphics and photography. In this paper, we develop a new and efficient local weighted average filter for edge-aware smoothing. The proposed filter can use guidance information which permits an iterative filtering process. Since the weights of the proposed filter depend on the local var...

The depth information is useful in many image processing applications. However, since taking a picture is a process of projection of a 3D scene onto a 2D imaging sensor, the depth information is embedded in the image. Extracting the depth information from the image is a challenging task. A guiding principle is that the level of blurriness due to de...

Smoothing and sharpening are two fundamental image processing operations. The latter is usually related to the former through the unsharp masking algorithm. In this paper, we develop a new type of filter which performs smoothing or sharpening via a tuning parameter. The development of the new filter is based on (1) a new Laplacian-based filter form...

Smoothing and sharpening are two fundamental image processing operations. The latter is usually related to the former through the unsharp masking algorithm. In this paper, we develop a new type of filter which performs smoothing or sharpening via a tuning parameter. The development of the new filter is based on (1) a new Laplacian-based filter form...

Cancelable biometrics is an important biometric template protection technique. However, many existing cancelable fingerprint templates suffer post-transformation performance deterioration and the attacks via record multiplicity (ARM). In this paper, we design alignment-free cancelable fingerprint templates with dual protection, which is composed of...

Edge-aware smoothing has proved to be a fundamental technique for various image processing and computer vision tasks. In this study, the authors introduce a local, non-iterative, and effective edge-preserving filter namely guided adaptive interpolation filter (GAIF). GAIF can be used as a post-processing step after any smoothing filter to improve i...

Background: Sowing time is commonly used as the temporal reference for Arabidopsis thaliana (Arabidopsis) experiments in high throughput plant phenotyping (HTPP) systems. This relies on the assumption that germination and seedling establishment are uniform across the population. However, individual seeds have different development trajectories eve...

Background Sowing time is commonly used as the temporal reference for Arabidopsis thaliana (Arabidopsis) experiments in high throughput plant phenotyping (HTPP) systems. This relies on the assumption that germination and seedling establishment are uniform across the population. However, individual seeds have different development trajectories even...

Fractional calculus has increased in popularity in recent years, as the number of its applications in different fields has increased. Compared to the traditional operations in calculus (integration and differentiation) which are uniquely defined, the fractional-order operators have numerous definitions. Furthermore, a consensus on the most suitable...

Distortion classification is an important step in blind image quality assessment. In this paper, a new image distortion classification algorithm is presented. Classification is based on features extracted from the distribution of the first digit of transform coefficients of the image. The generalized Benford’s law is used to model the distribution....

This paper deals with a practical signal processing problem where the filter is zero-phase and is specified by the frequency response. We show that if the signal is symmetrically extended, then the FFT-based algorithm can be efficiently implemented by using the DCT without signal extension. We extend the proposed algorithm to 2D filters and show th...

Structure-texture decomposition smoothing has been extensively studied due to its wide range of applications in computational photography and image processing. In this paper, we propose a new structure-texture decomposition algorithm which is based on two fundamental ideas: (1) guidance image and (2) iterative smoothing. The guidance image is gener...

The aim of structure extraction is to decompose an image into prominent structures and textures. In this paper, we present a new structure extraction method which has two main steps. First, high-frequency components due to the texture information in the orig- inal image are alleviated by a pre-smoothing filter. The result is then processed by a new...

This paper deals with an inverse problem in which the observed signal is produced by passing the original signal through a filter that is derived from a convex minimization problem. The filter is available as a black box. It is shown that the Bregman iteration, which is a tool for convex optimization, can be used to solve this inverse problem. This...

Matlab code for reproduction of results in "Bregman inverse filter" , accepted Electronics Letters, Nov. 2018

Kernel smoothing methods, including the bilateral filter, are commonly used in data processing/modeling and edge-aware image smoothing. Due to their nonlinear nature, these filters require significant computational time. In this paper, we address this problem by studying a practical case in which the data to be processed are integers. The basic ide...

The goal of blind image quality assessment (IQA) is to predict the quality of an image as perceived by human observers without using a reference image. In this paper, we explore a new approach which predicts the image quality based on the conformity of the first digit distribution (FDD) of natural images in the transform domain with Benford’s law....

The goal of edge-aware filtering is to smooth out small-scale structures while preserving large object boundaries. A fundamental idea to design such filters is to avoid smoothing across strong edges. In this paper, we explore a new approach which iteratively adds the edge information back to a smoothed image. We study the smoothed image as the star...

A new edge-aware filter called the empirical Bayes filter (EBF) is presented. It is shown that the bilateral filter (BF), being a special case of the EBF, is an optimal filter in terms of Bayesian linear least square estimation. An adaptive EBF (AEBF), which is an adaptive combination of the BF output and the original image, is developed. Experimen...

The bilateral filter (BF) is a non-linear filter that spatially smooths images with awareness of large structures such as edges. The level of smoothness applied to a pixel is constrained by a photometric weight, which can be obtained from the same image to be filtered (in case of the original BF) or from a guided image (in case of the joint/cross B...

The goal of automatic white balance (AWB) is to maintain color constancy of an image by removing color cast caused by un-canonical illuminant. In this paper, we address two limitations associated with a class of AWB algorithms and propose a technique to estimate the illuminant which takes into consideration of internal illumination and all pixels o...

In this letter, we derive a fast algorithm for the compressive bilateral filter (CBF) by representing the bilateral filter in a new way. This representation allows us to use the property of the Gaussian function to reduce the number of Gaussian filters required by the CBF by a factor of 2. Producing the same results as that of the CBF, the fast alg...

Edge-aware smoothing has been extensively studied due to its wide range of applications in computer vision and graphics.Most published works have been focused on formulating the smoothing problem in the spatial domain. In this paper, we propose a new edge-aware smoothing framework called guided wavelet shrinkage (GWS) which is formulated in the wav...

The theory and applications of the logarithmic image processing (LIP) have been studied by many researchers. In this work, we develop a symmetric generalized LIP (SGLIP) model. The development is based on a comparative study of recent theoretical development which include the original LIP model, the generalized LIP model (GLIP), the symmetric LIP (...

Traditional contrast enhancement techniques were developed to enhance the dynamic range of images with narrow histograms. However, it is not unusual that an image with a broad histogram still suffers from low contrast in both the shadow and highlight areas. In this paper, we first develop a unified framework called the generalized gamma correction...

A new computationally efficient algorithm for two-dimensional sliding-window least-squares prediction is presented in this study. The fast algorithm is based on a recursive update of the Cholesky decomposition. Compared with the state-of-the-art algorithm, the proposed algorithm reduces the computational complexity from O(D³) to O(D²h), where D is...

In this paper, a systematic review of relevant published studies on computer-based speech therapy systems or virtual speech therapists (VSTs) for people with speech disorders is presented. We structured this work based on the PRISMA framework. The advancements in speech technology and the increased number of successful real-world projects in this a...

In radar applications, target velocity is commonly determined using the Doppler effect. By comparing the transmit-receive differential frequency the Doppler frequency shift can be measured and as a result the target velocity can be determined. The Tasman International Geospace Environment Radars (TIGER) form part of an international network of simi...

In radar applications, the target velocity is commonly determined using the Doppler effect. By comparing the transmit-receive differential frequency, the Doppler frequency shift can be measured, and as a result, the target velocity can be determined.

Adaptive Predictor Combination (APC) is a framework for combining multiple predictors for lossless image compression and is often at the core of state of the art algorithms. In this paper, a Bayesian parameter estimation scheme is proposed for APC. Extensive experiments using natural, medical and remote sensing images of 8 to 16 bit/pixel have conf...

Noise reduction is often essential for cochlear implant (CI) recipients to achieve acceptable speech perception in noisy environments. Most noise reduction algorithms applied to audio signals are based on time-frequency representations of the input, such as the Fourier transform. Algorithms based on other representations may also be able to provide...

In this paper, a new extension of logarithmic image processing (LIP) model, called Symmetric Logarithmic Image Processing (SLIP), is proposed. Inspired by the previously developed symmetric models, the SLIP model defines a vector space on a symmetric bounded set. The development is aimed at (1) maintaining the physical interpretation of the LIP mod...

Image enlargement is a typical application of image processing. Many algorithms have been proposed and have found successful applications. Most of these algorithms are based on the theory of interpolation and make use of local structure of natural images. In this paper, we propose a new algorithm which is inspired by a new imaging sensor called the...

Recently, genome wide DNA markers have been used in breeding value estimation of livestock species. The computational technique is known as genomic selection. Typically, a large number of marker effects are estimated from a small number of animals, which presents an under-determined problem. In this paper, we propose sparse marker selection methods...

By using the triangular norm we first propose two methods for the construction of generalized linear systems and show new insights into the relationship between typical systems. Using the Hamacher and Frank t-norm, we propose a parametric log-ratio model which is a generalization of the log-ratio model and is more flexible in algorithmic developmen...

Real-time frame rate is an important factor for practical deployment of computer vision systems. Field programmable gate array (FPGA) technology has been considered for many applications due to its parallel computing capability. FPGA implementations of computer vision algorithms normally involve buffering data on external memory devices, which cou...

The logarithmic image processing (LIP) model is a mathematical theory providing generalized linear operations for image processing. The gigavision sensor (GVS) is a new imaging device that can be described by a statistical model. In this paper, by studying these two seemingly unrelated models, we develop a generalized LIP (GLIP) model. With the LIP...

The authors study an iterative algorithm for learning a linear Gaussian observation model with an exponential power scale mixture prior (EPSM). This is a generalisation of previous study based on the Gaussian scale mixture prior. The authors use the principle of majorisation minimisation to derive the general iterative algorithm which is related to...

Enhancement of contrast and sharpness of an image is required in many applications. Unsharp masking is a classical tool for sharpness enhancement. We propose a generalized unsharp masking algorithm using the exploratory data model as a unified framework. The proposed algorithm is designed to address three issues: (1) simultaneously enhancing contra...

Integral images or integral map (IMap) is one of the major techniques that has been used to improve the speed of computer vision systems. It has been used to compute Haar features and histograms of oriented gradient features. Some modifications have been proposed to the original IMap algorithm, but most proposed systems use IMap as it was first int...

The logarithmic image processing (LIP) model is a mathematical theory that provides new operations for image processing. The contrast definition has been shown to be consistent with some important physical laws and characteristics of human visual system. In this paper, we establish an information-theoretic interpretation of the contrast definition....

The DNA microarray may contain missing expression data. Estimation of missing values is a necessary step in microarray analysis, because data mining procedures require a complete expression as their input. In this paper, we propose a missing data estimation algorithm, named KPCAimpute, based on kernel principal component analysis. We consider a fam...

In this paper, we study several grayscale-based image segmentation methods for real-time road sign recognition applications on an FPGA hardware platform. The performance of different image segmentation algorithms in different lighting conditions are initially compared using PC simulation. Based on these results and analysis, suitable algorithms are...

Every year, many pedestrians are killed or seriously injured due to car accidents. A pedestrian recognition and warning system could save lives by warning the driver about a possible pedestrian hazard. Although significant progress in research for such systems has been reported, these systems are yet to be implemented in vehicles. In this paper, we...

The LMS algorithm is one of the most popular learning algorithms for identifying an unknown system. Many variants of the algorithm have been developed based on different problem formulations and principles. In this paper, we use the penalized maximum likelihood (PML) as a principled and unified approach for developing LMS-type algorithms. We study...

The M-estimate of a linear observation model has many important engineering applications such as identifying a linear system under non Gaussian noise. Batch algorithms based on the EM algorithm or the iterative reweighted least squares algorithm have been widely adopted. In recent years, several sequential algorithms have been proposed. In this pap...

Abstract A fundamental,problem,in signal processing is to estimate signal from noisy observations. This is usually formulated,as an optimization,problem. Optimizations,based on variational lower bound,and,minorization-maximization,have,been,widely used,in machine,learning research, signal processing and statistics. In this paper, we study iterative...

Many fatal accidents have happened due to drivers failing to stop at stop signs. A stop sign recognition system could be used to reduce the risk of accidents by warning the driver when a vehicle approaches a stop sign at an unexpected speed. In this paper, we describe the implementation of a real-time vision-based stop sign recognition system on a...

A fundamental problem in signal processing is to estimate signal from noisy observations. This is usually formulated as an optimization problem. Optimizations based on variational lower bound and minorization-maximization have been widely used in machine learning research, signal processing, and statistics. In this paper, we study iterative algorit...

The M-estimate of a linear observation model has many important engineering applications such as identifying a linear system under non-Gaussian noise. Batch algorithms based on the EM algorithm or the iterative reweighted least squares algorithm have been widely adopted. In recent years, several sequential algorithms have been proposed. In this pap...

This paper presents a successive mean splitting algorithm for both contrast enhancement and dynamic range reduction of digital images. The proposed algorithm is an extension to the recently published successive mean quantization transform (SMQT) for contrast enhancement. We explore the conditions under which the proposed algorithm is "optimal". We...

Alerting the driver of the speed limit is an important measure to keep the road safe. It is a challenging engineering problem to develop an automatic system which can detect speed limit signs under ever changing road conditions. In this paper, a robust algorithm for detecting speed limit sign is developed based on the traditional framework of pre-p...

This paper presents a study of sequential parameter estimation based on a linear non-Gaussian observation model. To develop robust algorithms, we consider a family of heavy-tailed distributions that can be expressed as the scale mixture of Gaussian and extend the development to include some robust penalty functions. We treat the problem as a Bayesi...

In this paper we propose an alternative way to developing a robust and adaptive sequential algorithm for estimating the unknown impulse response of a linear system. Our approach is based on formulating the problem as a maximum penalized likelihood (MPL) problem. We use the Fair penalty function as the generalized log-likelihood and a quadratic func...

In this paper, we propose a simple signal estimation algorithm based on multiple wavelet representations and Gaussian observation models. The proposed algorithm has two major steps: a joint-optimum estimation of the wavelet coefficients and an averaging of the denoised images. Experimental results show that the denoising performance of proposed alg...

There has been increasing research interest in developing adaptive filters with partial update (PU) and adaptive filters for sparse impulse responses. On the basis of maximum a posteriori (MAP) estimation, new adaptive filters are developed by determining the update when a new set of training data is received. The MAP estimation formulation permits...

In this paper, we propose a fast watermarking system that works on the H.264/AVC motion vectors. By restricting access to DCT coefficients and pixel information, the computational complexity of the watermark embedder/extractor is kept low and much lower than that of the H.264 decoder. The error propagation due to motion prediction compensation is m...

We develop an iterative algorithm based on minorization-maximization optimization to determine the maximum a posteriori estimate of the signal. We focus on linear Gaussian signal model with a family of heavy-tailed prior distributions which can be represented as scale mixture of Gaussian. We then modify the proposed algorithm for wavelet domain ima...