Matthew Kyan

Feature extraction of chromosomes from 3-D confocal microscope images

An investigation of local energy surface detection integrated with neural network techniques for image segmentation is presented, as applied in the feature extraction of chromosomes from image datasets obtained using an experimental confocal microscope. Use of the confocal microscope enables biologists to observe dividing cells (living or preserved) within a three-dimensional (3-D) volume, that can be visualised from multiple aspects, allowing for increased structural insight. The Nomarski differential interference contrast mode used for imaging translucent specimens, such as chromosomes, produces images not suitable for volume rendering. Segmentation of the chromosomes from this data is, thus, necessary. A neural network based on competitive learning, known as Kohonens self-organizing feature map (SOFM) was used to perform segmentation, using a collection of statistics or features defining the image. Our past investigation showed that standard features such as the localized mean and variance of pixel intensities provided reasonable extraction of objects such as mitotic chromosomes, but surface detail was only moderately resolved. In this current work, a biologically inspired feature known as local energy is investigated as an alternative image statistic based on phase congruency in the image. This, along with different combinations of other image statistics, is applied in a SOFM, producing 3-D images exhibiting vast improvement in the level of detail and clearly isolating the chromosomes from the background. Index Terms-DIC, differential interference contrast, feature extraction, feature space, image segmentation, local energy, Morlet wavelet, phase congruency, self organizing feature map, SOFM.

Improving shape-based CBIR for natural image content using a modified GFD

We present a modified version of the Generic Fourier Descriptor (GFD) that operates on edge information within natural images from the COREL image database for the purpose of shape-based image retrieval. By incorporating an edge-texture characterization (ETC) measure, we reduce the complexity inherent in oversensitive edge maps typical of most gradient-based detectors that otherwise tend to contaminate the shape feature description. We find that the proposed techniques not only improve overall retrieval in terms of shape, but more importantly, provide for a more accurate similarity ranking of retrieved results, demonstrating greater consideration for dominant internal and external shape details.

2005 Special Issue: Refining competition in the self-organising tree map for unsupervised biofilm image segmentation

The Self Organising Tree Map (SOTM) neural network is investigated as a means of segmenting micro-organisms from confocal microscope image data. Features describing pixel and regional intensities, phase congruency and spatial proximity are explored in terms of their impact on the segmentation of bacteria and other micro-organisms. The significance of individual features is investigated, and it is proposed that, within the context of micro-biological image segmentation, better object delineation can be achieved if certain features are more dominant in the initial stages of learning. In this way, other features are allowed to become more/less significant as learning progresses: as more knowledge is acquired about the data being segmented. We argue that the efficiency and flexibility of the SOTM in adapting to, and preserving the topology of input space, makes it an appropriate candidate for implementing this idea. We propose a refinement to the competitive search strategy that allows for a more appropriate fusion of signal and proximal features, thereby promoting a segmentation that is more sensitive to the regional associations of different microbial matter. A refined stop criterion is also suggested such that the dynamically generated number of classes becomes more data dependant. Preliminary experiments are presented and it is found that favouring intensity characteristics in the early phases of learning, whilst relaxing proximity constraints in later phases of learning, offers a general mechanism through which we can improve the segmentation of microbial constituents.

Local Variance Driven Self-Organization for Unsupervised Clustering

We propose a new, novel unsupervised clustering technique based on traditional Kohonen self organization, competitive Hebbian learning (CHL), and the Hebbian based maximum eigenfilter (HME). This method fits into the family of dynamic self-generating, self-organizing map (SOM) algorithms. The approach uses a vigilance based, global parsing strategy as a guide for the hierarchical partitioning of an underlying data distribution into a set of dominant prototypes: each consisting of a dual memory element for the online estimation of both position and maximal local variance. A co-operative scheme exploits the interplay between global vigilance and maximal local variance such that an informed choice may be made regarding insertion sites for new nodes into the map. The network is related to self-organizing tree maps (SOTM), growing neural gas (GNG) and their variants. A framework is presented and performance demonstrated against GNG

Application of image visual characterization and soft feature selection in Content-Based Image Retrieval

Fourier descriptors (FFT) and Hus seven moment invariants (HSMI) are among the most popular shape-based image descriptors and have been used in various applications, such as recognition, indexing, and retrieval. In this work, we propose to use the invariance properties of Hus seven moment invariants, as shape feature descriptors, for relevance identification in content-based image retrieval (CBIR) systems. The purpose of relevance identification is to find a collection of images that are statistically similar to, or match with, an original query image from within a large visual database. An automatic relevance identification module in the search engine is structured around an unsupervised learning algorithm, the self-organizing tree map (SOTM). In this paper we also proposed a new ranking function in the structure of the SOTM that exponentially ranks the retrieved images based on their similarities with respect to the query image. Furthermore, we propose to extend our studies to optimize the contribution of individual feature descriptors for enhancing the retrieval results. The proposed CBIR system is compatible with the different architectures of other CBIR systems in terms of its ability to adapt to different similarity matching algorithms for relevance identification purposes, whilst offering flexibility of choice for alternative optimization and weight estimation techniques. Experimental results demonstrate the satisfactory performance of the proposed CBIR system.

Dynamic feature fusion in the self organising tree map-applied to the segmentation of biofilm images

The self organising tree map (SOTM) neural network is investigated as a means of segmenting microorganisms from confocal microscope image data. Features describing pixel & regional intensities, phase congruency and spatial proximity are explored in terms of their impact on the segmentation of bacteria and other micro-organisms. The significance of individual features is investigated, and it is proposed that, within the context of micro-biological image segmentation, better object delineation can be achieved if certain features dominate the initial stages of learning. In this way, other features are allowed to become more/less significant as learning progresses: as the network gains more knowledge about the data being segmented. The efficiency and flexibility of the SOTM in adapting to, and preserving the topology of input space, makes it an appropriate candidate for implementing this idea. Preliminary experiments are presented and it is found that favouring intensity characteristics in the early phases of learning, whilst relaxing proximity constraints in later phases of learning, offers a general mechanism through which we can improve the segmentation of microbial constituents

Computational Intellegence Techniques and their Applications in Content-Based Image Retrieval

The main focus of this paper is to present a methodology for optimizing relevance identification in content-based image retrieval (CBIR) systems through the principle of feature weight detection. The purpose of relevance identification is to find a collection of images that are statistically similar to, or match with, an original query image within a large visual database. The novelty of this scheme is two-fold: using a base-10 genetic algorithm method to accurately determine the contribution of individual feature vectors for a successful retrieval in the so-called feature weight detection process, and defining a new unsupervised learning algorithm, the directed self-organizing tree map (DSOTM), for the purpose of classification in the automatic relevance identification module of the search engine. Comprehensive experiments demonstrate feasibility of the proposed methodology

Microbiological Image Analysis Using Self-Organization

This chapter considers the potential and flexibility of self-organizing tree map (SOTM) based and self-organizing hierarchical variance map (SOHVM) based learning for tasks in microbiological image analysis. As a demonstration of the SOHVMs ability to mine topological information from an input space, the chapter describes with an example for how such information can be used to simplify the task of visualizing a large three-dimensional (3D) stack of phase-contrast acquired plant chromosomes imaged during an advanced state of mitosis (cell division). The chapter considers two types of microbiological image data in order to demonstrate the potential for the proposed algorithm to achieve unsupervised, fully automatic segmentations. It shows examples of utilizing this automated property of the SOHVM to seek more natural segmentations of gray-level and higher order, multidimensional feature descriptions, with examples for the clustering of texture information and Local gray-level-based statistics.

Feature extraction and 3D reconstruction of Nomarski DIC microscope images using local energy and neural net techniques

The Nomarski differential interference contrast (DIC) mode is commonly used for imaging translucent biological specimens and it exhibits several major advantages over other phase contrast techniques, including a boost in high spatial frequencies in the region of focus. However, DIC images (unlike confocal) are limited by the presence of low spatial frequency blur and also by a differential shading gradient at feature boundaries, which make normal confocal visualization techniques unsuitable for feature extraction or for 3D volume rendering of focus- series datasets. To remedy this problem, we employ a neural network technique based on competitive learning, known as Kohonens self-organizing feature map (SOFM), to perform segmentation, using a collection of statistics (know as features) defining the image. Our past investigation showed that standard features such as the localized mean and variance of pixel intensities provided reasonable extraction of objects such asmitotic chromosomes, but surface detail was only moderately resolved. In this current work, local energy is investigated as an alternative image statistic based on phase congruency in the image. This, along with different combinations of other image statistics, is applied in a SOFM, producing 3D images exhibiting vast improvement in the level of detail and clearly isolating the chromosomes from the background.