Skip to main content

Associate Professor Shyh Teng

Deputy Dean

School of Engineering, IT and Phys. Sci.

Section/Portfolio:

School Leadership

Location:

Gippsland Campus, Online

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...

Rice Freshness Identification Based on Visible Near-Infrared Spectroscopy and Colorimetric Sensor Array

In this work, two methods, which were visible near-infrared spectroscopy (VNIRS) and visible...

An Enhanced Local Texture Descriptor for Image Segmentation

Texture is an indispensable property to develop many vision based autonomous applications....

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...

Network representation learning: From traditional feature learning to deep learning

Network representation learning (NRL) is an effective graph analytics technique and promotes...

Rectified Softmax Loss with All-Sided Cost Sensitivity for Age Estimation

In Convolutional Neural Network (ConvNet) based age estimation algorithms, softmax loss is...

BackNet: An Enhanced Backbone Network for Accurate Detection of Objects with Large Scale Variations

Deep Convolutional Neural Networks (CNNs) have induced significant progress in the field of...

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...

Enhanced Transfer Learning with ImageNet Trained Classification Layer

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained...

Hierarchical Colour Image Segmentation by Leveraging RGB Channels Independently

In this paper, we introduce a hierarchical colour image segmentation based on cuboid partitioning...

Improved Image Analysis Methodology for Detecting Changes in Evidence Positioning at Crime Scenes

This paper proposed an improved methodology to assist forensic investigators in detecting...

A detector of structural similarity for multi-modal microscopic image registration

This paper presents a Detector of Structural Similarity (DSS) to minimize the visual differences...

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...

COREG: a corner based registration technique for multimodal images

This paper presents a COrner based REGistration technique for multimodal images (referred to as...

Cuboid Colour Image Segmentation using Intuitive Distance Measure

In this paper, an improved algorithm for cuboid image segmentation is proposed. To address the...

Enhanced Colour Image Retrieval with Cuboid Segmentation

In this paper, we further investigate our recently proposed cuboid image segmentation algorithm...

Enhancing image registration performance by incorporating distribution and spatial distance of local descriptors

A data dependency similarity measure called mp-dissimilarity has been recently proposed. Unlike...

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...

Cuboid Segmentation for Effective Image Retrieval

Region-based image retrieval has been proven to be effective in finding relevant images. In this...

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...

A New Building Mask Using the Gradient of Heights for Automatic Building Extraction

A number of building detection methods have been proposed in the literature. However, they are...

A Robust Gradient Based Method for Building Extraction from LiDAR and Photogrammetric Imagery

Existing automatic building extraction methods are not effective in extracting buildings which...

Combining Pyramid Match Kernel and Spatial Pyramid for Image Classification

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

Enhancing SIFT-based image registration performance by building and selecting highly discriminating descriptors

In this paper we will investigate the gradient utilization in building SIFT ( Scale Invariant...

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...

A novel multi-modal image registration method based on corners

Effective and efficient contour-based corner detectors

Corner detection is an essential operation in many computer vision applications. Among the...

Multimodal image registration technique based on improved local feature descriptors

Multimodal image registration has received significant research attention over the past decade,...

Rotation Invariant Spatial Pyramid Matching for Image Classification

Automatic extraction of buildings in an urban region

An improved building detection in complex sites using the LIDAR height variation and point density

Detection of structural similarity for multimodal microscopic image registration

Maximizing structural similarity in multimodal biomedical microscopic images for effective registration

Achieving high multi-modal registration performance using simplified Hough-transform with improved symmetric-SIFT

An effective method of estimating scale-invariant interest region for representing corner features

A general stochastic clustering method for automatic cluster discovery

Finding clusters in data is a challenging problem. Given a dataset, we usually do not know the...

An effective and efficient contour-based corner detector using simple triangular theory

  • Conference Proceedings

Clustering gene expression data using ant-based heuristics

  • Conference Proceedings

Feature-subspace aggregating: ensembles for stable and unstable learners

This paper introduces a new ensemble approach, Feature-Subspace Aggregating (Feating), which...

Improved symmetric-SIFT for Multi-modal image registration

Improving SIFT's performance by incorporating appropriate gradient information

  • Conference Proceedings

Simplifying and improving ant-based clustering

Texture classification using multimodal invariant Local binary pattern

A comparative study of a practical stochastic clustering method with traditional methods

In many real-world clustering problems, there usually exist little information about the clusters...

An enhancement to SIFT-based techniques for image registration

Image registration using modified local ternary pattern

PTP1B regulates Eph receptor function and trafficking

Degree of differential prioritization

  • Journals

FaSS: Ensembles for stable learners

  • Conference Proceedings

A study on the importance of differential prioritization in feature selection using toy datasets

  • Conference Proceedings

Issues of grid-cluster retrievals in swarm-based clustering

Characteristics of predictor sets found using differential prioritization

Background: Feature selection plays an undeniably important role in classification problems...

Examining dissimilarity scaling in ant colony approaches to data clustering

In this paper, we provide the reasons why the dissimilarity-scaling parameter (α) in the...

Image indexing and retrieval based on vector quantization

To effectively utilize information stored in a digital image library, effective image indexing...

Differential prioritization between relevance and redundancy in correlation-based feature selection techniques for multiclass gene expression data

Background: Due to the large number of genes in a typical microarray dataset, feature selection...

Investigating the class-specific relevance of predictor sets obtained from DDP-based feature selection technique

Feature selection is crucial to tumor classification due to the high dimensionality of microarray...

Comparison of retrieval effectiveness of colour-based techniques on MPEG-7 common colour dataset

Effects of codebook sizes, codeword dimensions, and colour spaces on retrieval performance of image retrieval using vector quantization

An evaluation of the robustness of image retrieval based on vector quantization