Stan Miklavcic

High-throughput 3D modelling of plants for phenotypic analysis

In this paper we propose a twin mirror-based system for reconstructing 3D models of real plants for subsequent phenotypic analysis. The method is based on the visual hull concept: multiple reflections of the object from the mirrors give different views of the object and are interpreted as taken from virtual cameras. The epipolar geometry of the object and its four reflections is determined without relying on information of the positions of the camera and mirrors. This alleviates the usual camera calibration step. Two simultaneous images of object mirror scene give ten different and simultaneous views of the plant, without requiring any plant or camera movement. Visual hull algorithms are sensitive to segmentation of the object from the scene. We propose a novel machine learning approach to segment a plant from its background. The plant colours are represented using a Gaussian mixture model (GMM), while the background colours are represented by a separate GMM, learnt using an Expectation Maximisation (EM) algorithm. A Bayes classification rule that satisfies the Neymann-Pearson criteria is used to classify the pixels and thus segment the five plant silhouette from each image. We show results of 3D models of wheat, grass, and a lavender shoot reconstructed using the proposed segmentation and 3D visual hull method.

Improved ellipse fitting by considering the eccentricity of data point sets

Ellipse and conic fitting is a highly researched and mature topic in image processing and computer vision. Surprisingly, however, none of the methods have thus far considered eccentricity of data point sets in the fitting of an ellipse. In this paper we show that irrespective of the method used to fit ellipses, the root mean square error (RMSE) of an algorithm increases with the eccentricity of the data point set. We propose a novel way of weighting data points based on their eccentricity to improve the results of ellipse fitting. Data points with higher weights are repeated and data points with insignificant weights are dropped. We empirically demonstrate that the proposed method improves the accuracy of ellipse fitting. Almost all methods of ellipse fitting irrespective of whether they minimize algebraic error or geometric error will benefit by the proposed method of pre-processing the data points.

Automated Detection of Root Crowns Using Gaussian Mixture Model and Bayes Classification

In this paper a method for automatic detection of root crowns in root images, are designed, implemented and quantitatively compared. The approach is based on the theory of statistical learning. The root images are preprocessed with algorithms for intensity normalization, segmentation, edge detection and scale space corner detection. The features used in the experiments are the Zernike moments of the bi-level image patch centered around high curvature detections. Zernike moments are orthogonal and thus can be rightly assumed to be independent. The densities of the feature vectors for different classes are modelled with Gaussian mixture model (GMM), with a diagonal covariance matrix. The parameters for the features distribution densities for different classes are learnt by expectation maximization. Bayes rule and Neymann-Pearson criteria is used to design the classification method. We experiment with different orders of Zernike moments and different number of Gaussians in the GMM. The experiments are done on a real dataset with images of rice, corn, and grass roots. Pattern classification results are quantitatively analyzed using Receiver Operating Characteristic (ROC) curves and area under the ROC curves. We quantitatively compare the results of the proposed method with that of support vector machine (SVM) which is another very popular statistical learning method for pattern classification.

The extended-domain?eigenfunction method for solving elliptic boundary value problems with annular domains

Standard analytical solutions to elliptic boundary value problems on asymmetric domains are rarely, if ever, obtainable. In this paper, we propose a solution technique wherein we embed the original ...

Segmentation of Cereal Plant Images Using Level Set Methods - A Comparative Study

In this paper we evaluate the quality of segmentation of plant images achieved by different level set methods commonly used in the literature. The plants of study are narrow-leaf cereal plants at different growth stages and the segmentation quality measure was considered to be the boundary, leaf tips, and axils. The results show that region-based level set methods can perform the segmentation of plants with high accuracy when the plants are at either early or mature stages of growth. The results also show that contour based level set algorithms are not applicable to the segmentation of narrow leaf plants because the front being computed does not advance to the high curvature features, such as sharp tips and axils. A typical image of a mature plant has isolated regions from the interlacing of leaves. Only region-based methods can perform the segmentation with good accuracy. Level set methods are sensitive to initialization and parameter selection.

Root crown detection using statistics of Zernike moments

In this paper an automatic method for detecting root crowns in root images for plants growing in gellan gum is proposed. In the proposed approach statistics of Zernike moments (ZMs) are used to model the bi-level root crown images and non root crown images. Bi-level image are generated by a process of normalization and segmentation. The statistics of the ZMs for the classes of root crowns and non root crowns are learnt from a labelled training data set. For classification of a new image patch into a root crown or non root crown class, a likelihood is computed assuming the orthogonal ZMs to be independent and normally distributed. The ratio of these two class likelihoods is used for classification. The results of classification are quantitatively analysed using Receiver Operating Characteristic (ROC) curves. The area under the ROC curve is used for deciding the order of ZMs to be used for detection of the root crowns. We evaluate the results of the proposed methodology both quantitatively and qualitatively. Results of root crown detection on real different plant roots are shown.

Novel Image Segmentation Based on Machine Learning and Its Application to Plant Analysis

A novel algorithm is proposed for background estimation using machine learning and statistical pattern recognition. Usually the segmentation of objects in images is achieved by identifying homogeneous regions in individual images or by finding motions of objects in videos. In this paper, we combine the advantages of these approaches for the estimation of background using only two images. The proposed algorithm uses the difference between images to obtain initial estimation of background and then to refine the estimation using machine learning and statistical pattern recognition. Experimental results have shown that the proposed algorithm can achieve promising performance in terms of accuracy and speed.

The Actual Dielectric Response Function for a Colloidal Suspension of Spherical Particles

In this paper, we present a theoretical analysis of the dielectric response of a dense suspension of spherical colloidal particles based on a self-consistent cell model. Particular attention is paid to (a) the relationship between the dielectric response and the conductivity response and (b) the connection between the real and imaginary parts of these responses based on the Kramers-Kronig relations. We have thus clarified the analysis of Carrique et al. (Carrique, F.; Criado, C.; Delgado, A. V. J. Colloid Interface Sci. 1993, 156, 117). We have shown that both the conduction and displacement current components are complex quantities with both real and imaginary parts being frequency dependent. The dielectric response exhibits characteristics of two relaxation phenomena: the Maxwell-Wagner and the alpha-relaxations, with the imaginary part being the more sensitive instrument. The inverse Fourier transform of the simulated dielectric response is compared with a phenomenological, two-exponential response function with good agreement obtained. The two fitted decay times also compare well with times extracted from the explicit simulations.

The equilibrium shape of an axisymmetric sessile drop subject to local stresses

The exact equation describing the shape of a fluid drop under the action of local surface stresses induced by colloidal interactions is derived without resorting to any of the approximations inherent in the profile equation currently employed in the literature. The exact equation implies, and numerical examples confirm, that repulsive external (i.e. positive) surface energies assist in stabilizing the drop against deformation, while attractive (i.e. negative) energies destabilize the drop, promoting or enhancing deformation. An inherent singularity in the governing differential equation (absent from the approximate equations currently used) when the surface energy (surface tension) is identically matched by an external attractive energy represents an instability limit. Explicit bounds are established for a further instability criterion and for the hydrostatic pressure difference across the interface. An exact equation for the radial extent of the sessile drop and some numerical examples are also presented.

Sufficient conditions for the stability and instability of a fluid boundary subjected to local stress

Sufficient conditions for either stability or instability of the interface of a fluid drop subject to localized surface stresses are presented. The stated conditions pertain to the case of an axisymmetric sessile drop having a fixed contact line and subject to axisymmetric forces acting on the surface of the drop. These conditions, appearing for the first time in the literature, are in the form of pointwise inequalities. They have quite general applicability, as they do not rely on explicit knowledge of the specific nature of an externally applied surface force. Supplementary integral inequalities are also provided and discussed.