Skip to main content

Dr Dengsheng Zhang

Senior Lecturer, Information Technology

School of Engineering, IT and Phys. Sci.

Section/Portfolio:

Information Technology (Gippsland)

Location:

Gippsland Campus, Online

Biography

Dr Dengsheng Zhang has over 25 years of research experience in the field of artificial intelligence and big data, with specific research interests in image classification, object detection, deep learning and music classification.

Dr Zhang has published more than 100 refereed papers and has completed two ARC Discovery projects on image and music classification. Dengsheng is author of the multiple award-winning book, Fundamentals of Image Data Mining (Springer, 2019). He currently serves as an associate editor of World Scientific and Engineering Academy and Society’s Transactions on Signal Processing.

Dengsheng obtained his PhD in Computing in 2002 from Monash University (now Federation University Australia), where he worked as senior lecturer. He is currently a Senior Lecturer in information technology at Federation University and a Guest Professor of Xi'an University of Posts & Telecommunications, China.

A novel fusion approach in the extraction of kernel descriptor with improved effectiveness and efficiency

Image representation using feature descriptors is crucial. A number of histogram-based...

An Enhancement to the Spatial Pyramid Matching for Image Classification and Retrieval

Spatial pyramid matching (SPM) is one of the widely used methods to incorporate spatial...

Key viral immune genes and pathways identify elite athletes with URS

PURPOSE: Habitual intense exercise may increase the incidence of upper respiratory symptoms (URS)...

  • Journals

A Rotation Invariant HOG Descriptor for Tire Pattern Image Classification

Texture feature is important in describing tire pattern image which provides useful clue in...

Distortion Robust Image Classification Using Deep Convolutional Neural Network with Discrete Cosine Transform

Convolutional Neural Networks are highly effective for image classification. However, it is still...

A Kernel-Based Approach for Content-Based Image Retrieval

Content-based image retrieval (CBIR)is a popular approach to retrieve images based on a query. In...

A Novel Perceptual Dissimilarity Measure for Image Retrieval

Similarity measure is an important research topic in image classification and retrieval. Given a...

Enhancing the Effectiveness of Local Descriptor Based Image Matching

Image registration has received great attention from researchers over the last few decades. SIFT...

Image Clustering Using a Similarity Measure Incorporating Human Perception

Clustering similar images is an important task in image processing and computer vision. It...

A Hybrid Data Dependent Dissimilarity Measure for Image Retrieval

In image retrieval, an effective dissimilarity (or similarity) measure is required to retrieve...

Improved Kernel Descriptors for Effective and Efficient Image Classification

Kernel descriptors have been proven to outperform existing histogram based local descriptors as...

Improved Tamura Features for Image Classification Using Kernel Based Descriptors

Tamura features are based on human visual perception and have huge potential in image...

Integrating object ontology and region semantic template for crime scene investigation image retrieval

Crime Scene Investigation (CSI) image retrieval plays an important role in solving crimes by...

Multi-Feature Fusion for Crime Scene Investigation Image Retrieval

Based on a large scale crime scene investigation (CSI) image database, an effective and efficient...

Combining Pyramid Match Kernel and Spatial Pyramid for Image Classification

This paper proposes a new approach for image classification by combining pyramid match...

Extracting road centrelines from binary road images by optimizing geodesic lines

Binary road images can be obtained from remotely sensed images with the aid of classification and...

Rotation Invariant Spatial Pyramid Matching for Image Classification

Efficient nonlinear classification via low-rank regularised least squares

We revisit the classical technique of regularised least squares (RLS) for nonlinear...

Learning Sparse Kernel Classifiers for Multi-Instance Classification

We propose a direct approach to learning sparse kernel classifiers for multi-instance (MI)...

Optimizing cepstral features for audio classification

  • Conference Proceedings

Structural image retrieval using automatic image annotation and region based inverted file

Image retrieval has lagged far behind text retrieval despite more than two decades of intensive...

A class centric feature and classifier ensemble selection approach for music genre classification

An annotation rule extraction algorithm for image retrieval

Automatic image annotation can be used to facilitate semantic search in large image databases....

A novel automatic hierachical approach to music genre classification

A review on automatic image annotation techniques

Nowadays, more and more images are available. However, to find a required image for an ordinary...

Comparison of curvelet and wavelet texture features for content based image retrieval

Learning sparse kernel classifiers in the primal

Rotation Invariant Curvelet Features for Region Based Image Retrieval

There have been much interest and a large amount of research on content based image retrieval...

A Survey of Audio-Based Music Classification and Annotation

Music information retrieval (MIR) is an emerging research area that receives growing attention...

Automatic image search based on improved feature descriptors and decision tree

There has been a growing interest in implementing image search engine at the semantic level....

Building sparse support vector machines for multi-instance classification

Building sparse support vector machines for multi-instance classification

We propose a direct approach to learning sparse Support Vector Machine (SVM) prediction models...

Image re-ranking based on extraction of semantic regions

It is difficult for current image search engines to accurately grasp the real intention of users....

Improved spatial pyramid matching for image classification

Music classification via the bag-of-features approach

A central problem in music information retrieval is audio-based music classification. Current...

On low-rank regularized least squares for scalable nonlinear classification

An enhancement to closed-form method for natural image matting

Connectivity-based shape descriptors

In this paper, we propose a method for indexing and retrieval of images based on shapes of...

GrowMatting: A GPU-based real-time interactive method for image matting

Learning naive Bayes classifiers for music classification and retrieval

In this paper, we explore the use of naive Bayes classifiers for music classification and...

Novel spectral descriptor for object shape

In this paper, we propose a novel descriptor for shapes. The proposed descriptor is obtained from...

On feature combination for music classification

Region based color image retrieval using curvelet transform

Region based image retrieval has received significant attention from recent researches because it...

Spectral shape descriptor using spherical harmonics

In this paper, we discuss the problems associated with the present contention resolution...

Automatic image annotation based on decision tree machine learning

With the rapid development of digital imaging technology, image annotation is an important and...

Evaluation of face recognition techniques

  • Conference Proceedings

Rotation invariant curvelet features for texture image retrieval

Effective texture feature is an essential component in any content based image retrieval system....

Semantic image retrieval using region based inverted file

Image data is as common as textual data in this digital world. There is an urgent demand of image...

Spherical harmonics and distance transform for image representation and retrieval

In this paper, we have proposed a method for 2D image retrieval based on object shapes. The...

A geometric method to compute directionality features for texture images

Automatic categorization of image regions using dominant color based vector quantization

This paper proposes a dominant color based vector quantization algorithm that automatically...

Complementing a region descriptor for shape retrieval

  • Journals

Composite feature modeling and retrieval

Feature-based intelligent design and manufacturing systems in the Internet environment are an...

Content based image retrieval using curvelet transform

Feature extraction is a key issue in content-based image retrieval (CBIR). In the past, a number...

Corners-based composite descriptor for shapes

In this paper, a composite descriptor for shape retrieval is proposed. The composite descriptor...

Digital image retrieval using intermediate semantic features and multistep search

Image retrieval based on semantics of intra-region color properties

Traditional image retrieval systems are content based image retrieval systems which rely on...

Region-based image retrieval with high-level semantics using decision tree learning

  • Journals

A composite descriptor for shape retrieval

In this paper, a composite descriptor for shape retrieval has been proposed. The proposed...

Comparison of retrieval effectiveness of different region based image representations

The choice for low level representation of images makes a significant difference in image...

SIEVE - Search images effectively through visual elimination

Existing Web image search engines index images by textual descriptions including filename, image...

A new approach to texture retrieval

The texture retrieval approach based on Gabor filters has been shown to be very useful for...

Multiresolution analysis of connectivity

Multiresolution histograms have been used for indexing and retrieval of images. Multiresolution...

Performance study of gabor filters and rotation invariant gabor filters

Gabor filters have been proven to be very useful for texture retrieval and are widely adopted (1,...

Spherical harmonics descriptor for 2D-image retrieval

In this paper, spherical harmonics are proposed as shape descriptors for 2d images. We introduce...

An efficient texture feature extraction algorithm for arbitrary-shaped regions

  • Conference Proceedings

Effects of different Gabor Filter parameters on image retrieval by texture

Multi-scale analysis of connectivity for image retrieval

Review of shape representation and description techniques

A comparative study of curvature scale space and Fourier descriptors for shape-based image retrieval

Evaluation of similarity measurement for image retrieval

Shape-based image retrieval using generic Fourier descriptor

A comparison of shape retrieval using fourier descriptors and short-time fourier descriptors

  • Book Chapters