A5010870517- Image Retrieval and Classification Techniques
- Medical Image Segmentation Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Vision and Imaging
- Computer Graphics and Visualization Techniques
- Human Motion and Animation
- Image and Signal Denoising Methods
- AI in cancer detection
- 3D Shape Modeling and Analysis
- Computational Geometry and Mesh Generation
- Robotics and Sensor-Based Localization
- Advanced Image Processing Techniques
- Advanced Image Fusion Techniques
- Advanced Numerical Analysis Techniques
- Image Enhancement Techniques
- Face recognition and analysis
- Cell Image Analysis Techniques
- Radiomics and Machine Learning in Medical Imaging
- Space Satellite Systems and Control
- Inertial Sensor and Navigation
- Advanced Data Compression Techniques
- Augmented Reality Applications
- Human Pose and Action Recognition
- Robotic Path Planning Algorithms
- Digital Imaging for Blood Diseases
University of Canterbury
2015-2024
Christ University
2007
Multimedia University
2000-2001
Indian Space Research Organisation
1986-1996
Clarkson University
1996
This paper introduces a new set of orthogonal moment functions based on the discrete Tchebichef polynomials. The moments can be effectively used as pattern features in analysis two-dimensional images. implementation proposed this does not involve any numerical approximation, since basis is domain image coordinate space. property makes superior to conventional such Legendre and Zernike moments, terms preserving analytical properties needed ensure information redundancy set. also details...
Discrete orthogonal moments have several computational advantages over continuous moments. However, when the moment order becomes large, discrete (such as Tchebichef moments) tend to exhibit numerical instabilities. This paper introduces orthonormal version of moments, and analyzes some their aspects. The recursive procedure used for polynomial evaluation can be suitably modified reduce accumulation errors. proposed set representing image shape features reconstructing an from its with a high...
Evaluating expression of the human epidermal growth factor receptor 2 (HER2) by visual examination immunohistochemistry (IHC) on invasive breast cancer (BCa) is a key part diagnostic assessment BCa due to its recognized importance as predictive and prognostic marker in clinical practice. However, scoring HER2 subjective, consequently prone interobserver variability. Given therapeutic implications scoring, more objective method required. In this paper, we report recent automated contest, held...
Background—In the field of aviation, maintenance and inspections engines are vitally important in ensuring safe functionality fault-free aircrafts. There is value exploring automated defect detection systems that can assist this process. Existing effort has mostly been directed at artificial intelligence, specifically neural networks. However, approach critically dependent on large datasets, which be problematic to obtain. For more specialised cases where data sparse, image processing...
Pseudo-Zernike moments have better feature representation capability, and are more robust to image noise than those of the conventional Zernike moments. However, due computation complexity pseudo-Zernike polynomials, yet be extensively used as descriptors compared In this paper, we propose two new algorithms, namely coefficient method p-recursive method, accelerate Coefficient calculates polynomial coefficients recursively. It eliminates need using factorial functions. Individual order or...
The discrete Tchebichef transform (DTT) is a method based on orthogonal polynomials, which have applications recently found in image analysis and compression. This letter introduces new fast 4 x forward DTT algorithm. algorithm requires only 32 multiplications 66 additions, while the best-known using two properties of 64 96 additions. proposed could be used as base case for recursive computation coefficients. Experimental results showing performance improvement over existing techniques are presented.
This study introduces a new set of orthogonal polynomials and moments the set's application in signal image processing. polynomial is derived from two well-known polynomials: Tchebichef Krawtchouk polynomials. attempts to present following: (i) mathematical theoretical frameworks for definition this including modelling signals with various analytical properties it contains, as well as, recurrence relations transform equations that need be addressed; (ii) results empirical tests compare...
The evaluation of breast cancer grades in immunohistochemistry (IHC) slides takes into account various types visual markers and morphological features stained membrane regions. Digital pathology algorithms using whole slide images (WSIs) histology have recently been finding several applications such computer-assisted evaluations. Features that are directly related to biomarkers used by pathologists generally preferred over the pixel values entire images, even though latter has more...
This paper presents the mathematical framework of radial Tchebichef moment invariants, and investigates their feature representation capabilities for pattern recognition applications. The moments are constructed using discrete orthogonal polynomials as kernel, they have a radial-polar form similar to that Zernike moments. transforms make them particularly suitable image processing tasks. Experimental results showing primary attributes such invariance orthogonality proposed functions also given.
Multifractal analysis has recently found applications in the field of automatic classification and content based retreival tissue cell images. The accuracy such methods largely depends on invariant characteristics spectra computed for a chosen intensity measure. It is therefore necessary to carry out detailed suitable measures invariance resulting spectra. This paper discusses some key implementation aspects multifractal techniques, gives comparative different types measures, presents...
Orthogonal moment functions have long been used in image analysis. This paper proposes a novel approach based on discrete orthogonal Tchebichef Moment for efficient compression. The method incorporates simplified mathematical framework techniques using matrices, as well block-wise reconstruction technique to eliminate possible occurrences of numerical instabilities at higher orders. comparison between compression and JPEG has done. results show significant advantages terms its quality rate....
This paper presents novel feature descriptors and classification algorithms for the automated scoring of HER2 in Whole Slide Images (WSI) breast cancer histology slides. Since a large amount processing is involved analyzing WSI images, primary design goal has been to keep computational complexity minimum possible level use simple, yet robust that can provide accurate We propose two types encode important information about staining patterns percentage present ImmunoHistoChemistry...
In this paper we present a new method for automatically constructing 3D meshes from single input image. With the increasing content demands of modern digital entertainment and expectation involvement users, automatic artist-free systems are an important step in allowing user generated rapid game prototyping. Our system proposes novel heuristic creation mesh piece non-occluding 2D concept art. By extracting skeleton structure, approximating orientation analysing line curvature properties,...