Dr Jonathan Clark
About
Research interests
My main interest is bioinformatics in the broad sense, the interface between computing and biology, with emphasis on classification and pattern recognition, especially with regard to botanical taxonomy and systematics. This is a natural consequence of my BSc (Botany), MSc (Plant Taxonomy) and PhD (Cybernetics) studies. I am particularly interested in biological identification and classification techniques, especially those involving the use of artificial neural networks. My current teaching areas are Intelligent Information Systems, Information Systems Development and Computer Logic.
Research collaborations
- Royal Botanic Gardens, Kew
- University of York
- University of Reading
- Cardiff University
- Kingston University
Publications
During the last three decades, the area of expert systems has attracted enormous research interest, and a multitude of systems, tackling all kinds of applications, have been designed and implemented. An area where expert systems have been extensively applied is medical care; however, despite the very large number of systems implemented, no system for the special care required for wheelchair users with spinal injury has been developed. The purpose of this report is to present the design and implementation methodology of the DIMITRA expert system, an online consultation system under development for the special caring procedure of such patients. This system is considered to be of value for virtual healthcare in the home, because it is designed for remote access by carers and their patients. Copyright © 2006 Inderscience Enterprises Ltd.
This paper describes a method of training an artificial neural network, specifically a multilayer perceptron (MLP), to act as a tool to help identify plants using morphological characters collected automatically from images of botanical herbarium specimens. A methodology is presented here to provide a practical way for taxonomists to use neural networks as automated identification tools, by collating results from a population of neural networks. A case study is provided using data extracted from specimens of the genus Tilia in the Herbarium of the Royal Botanic Gardens, Kew, UK. A classification accuracy of 44% was achieved on this challenging multiclass problem.
Plants are of fundamental importance to life on Earth. The shapes of leaves, petals and whole plants are of great significance to plant science, as they can help to distinguish between different species, to measure plant health, and even to model climate change. The growing interest in biodiversity and the increasing availability of digital images combine to make this topic timely. The global shortage of expert taxonomists further increases the demand for software tools that can recognize and characterize plants from images. A robust automated species identification system would allow people with only limited botanical training and expertise to carry out valuable field work. We review the main computational, morphometric and image processing methods that have been used in recent years to analyze images of plants, introducing readers to relevant botanical concepts along the way. We discuss the measurement of leaf outlines, flower shape, vein structures and leaf textures, and describe a wide range of analytical methods in use. We also discuss a number of systems that apply this research, including prototypes of hand-held digital field guides and various robotic systems used in agriculture. We conclude with a discussion of ongoing work and outstanding problems in the area. © 2011 Elsevier Ltd. All rights reserved.
Herbarium specimens are a vital resource in botanical taxonomy. Many herbaria are undertaking large-scale digitization projects to improve access and to preserve delicate specimens, and in doing so are creating large sets of images. Leaf characters are important for describing taxa and distinguishing between them and they can be measured from herbarium specimens. Here, we demonstrate that herbarium images can be analysed using suitable software and that leaf characters can be extracted automatically. We describe a low-cost digitization process that we use to create a set of 1,895 images of Tilia L. specimens, and novel botanical image processing software. The output of the software is a set of leaf characters. As a demonstration of this approach, we extract the length and width of a large number of leaves automatically from images of whole herbarium specimens. We show that the lengths and widths that we extract are very strongly correlated with values in a published account of cultivated species, but are also consistently smaller. We discuss some particular features of herbarium specimens that may affect the results of this form of analysis, and consider further applications to extract characters such as leaf shape and margin characters.
This paper describes a method of training an artificial neural network, specifically a multilayer perceptron (MLP), to act as a tool to help identify plants using morphological characters collected automatically from images of botanical herbarium specimens. A methodology is presented here to provide a practical way for taxonomists to use neural networks as automated identification tools, by collating results from a collection of neural networks. A case study is provided using data extracted from specimens of the genus Tilia in the Herbarium of the Royal Botanic Gardens, Kew, UK.
Many species of plants produce leaves with distinct teeth around their margins. The presence and nature of these teeth can often help botanists to identify species. Moreover, it has long been known that more species native to colder regions have teeth than species native to warmer regions. It has therefore been suggested that fossilized remains of leaves can be used as a proxy for ancient climate reconstruction. Similar studies on living plants can help our understanding of the relationships. The required analysis of leaves typically involves considerable manual effort, which in practice limits the number of leaves that are analyzed, potentially reducing the power of the results. In this work, we describe a novel algorithm to automate the marginal tooth analysis of leaves found in digital images. We demonstrate our methods on a large set of images of whole herbarium specimens collected from Tilia trees (also known as lime, linden or basswood). We chose the genus Tilia as its constituent species have toothed leaves of varied size and shape. In a previous study we extracted [Formula: see text] leaves automatically from a set of [Formula: see text] images. Our new algorithm locates teeth on the margins of such leaves and extracts features such as each tooth's area, perimeter and internal angles, as well as counting them. We evaluate an implementation of our algorithm's performance against a manually analyzed subset of the images. We found that the algorithm achieves an accuracy of 85% for counting teeth and 75% for estimating tooth area. We also demonstrate that the automatically extracted features are sufficient to identify different species of Tilia using a simple linear discriminant analysis, and that the features relating to teeth are the most useful.