Jarosław Gocławski

Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses

Abstract The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant’s reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow–Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.

Cuda Based Fuzzy C-Means Acceleration for the Segmentation of Images with Fungus Grown in Foam Matrices

Abstract In the paper authors verify the advantages of GPU computing applied to fuzzy c-means segmentation. Three different algorithms implementing FCM method have been compared by their execution times. All tests refer to the images of polyurethane foam matrices filled with fungus (mould). They are aimed at separating mould regions from the matrix base. The authors proposed a method using CUDA programming tools, which significantly speedsup FCM computations with multiple cores built in a graphic card.

The method of solid-liquid contact angle measurement using the images of sessile drops with shadows on substratum

This paper presents the method of liquid-solid contact angle measurement for the images of sessile droplets, including drop shadows on substratum materials, instead of usual horizontal bottom level lines. ADSA-P trajectory and its skew projection are used to approximate drop profile and shadow boundaries respectively. The intersections of both trajectories determine contact points and localize the bottom line. This implies contact angles between the bottom and profile trajectory.

Alleviation of nickel toxicity in wheat (Triticum aestivum L.) seedlings by selenium supplementation

Abstract Hydroponically grown wheat seedlings were treated with 50 μM N i and/or 15 μM Se. After a 7-day culture period, their growth parameters, N i, Se, F e, and M g contents, electrolyte leakage, photosynthetic pigment concentrations, and photochemical activity of photosystem II were determined. Exposure of wheat seedlings to N i alone resulted in reduction in the total shoot and root lengths, by 22% and 50%, respectively. Addition of Se to the N i-containing medium significantly improved the growth of these organs, compared to the seedlings subjected to N i alone. Application of Se decreased the accumulation of N i in shoots and roots and partially alleviated the N i-induced decrease in F e and M g concentations in shoots. Electrolyte leakage increased in response to N i stress, but in shoots it was diminished by Se supplementation. Exposure to N i led to a decrease in chlorophyll a and b contents and enhancement of chlorophyll a/b ratio, but did not influence the concentration of carotenoids. Enrichment of the N i-containing medium with Se significantly increased chlorophyll b content, compared to the seedlings treated with N i alone. Photochemical activity, estimated in terms of the maximum quantum yield of photosystem II , decreased in response to N i treatment but was significantly improved by simultaneous addition of Se. Results of our study suggest that alleviation of N i toxicity in wheat seedlings by Se supplementation may be related to limitation of N i uptake.

Automated image analysis for quantification of reactive oxygen species in plant leaves

The paper presents an image processing method for the quantitative assessment of ROS accumulation areas in leaves stained with DAB or NBT for H2O2 and O2- detection, respectively. Three types of images determined by the combination of staining method and background color are considered. The method is based on the principle of supervised machine learning with manually labeled image patterns used for training. The methods algorithm is developed as a JavaScript macro in the public domain Fiji (ImageJ) environment. It allows to select the stained regions of ROS-mediated histochemical reactions, subsequently fractionated according to the weak, medium and intense staining intensity and thus ROS accumulation. It also evaluates total leaf blade area. The precision of ROS accumulation area detection is validated by the Dice Similarity Coefficient in the case of manual patterns. The proposed framework reduces the computation complexity, once prepared, requires less image processing expertise than the competitive methods and represents a routine quantitative imaging assay for a general histochemical image classification.

An automatic segmentation method for scanned images of wheat root systems with dark discolourations

An automatic segmentation method for scanned images of wheat root systems with dark discolourations The analysis of plant root system images plays an important role in the diagnosis of plant health state, the detection of possible diseases and growth distortions. This paper describes an initial stage of automatic analysis—the segmentation method for scanned images of Ni-treated wheat roots from hydroponic culture. The main roots of a wheat fibrous system are placed separately in the scanner view area on a high chroma background (blue or red). The first stage of the method includes the transformation of a scanned RGB image into the HCI (Hue-Chroma-Intensity) colour space and then local thresholding of the chroma component to extract a binary root image. Possible chromatic discolourations, different from background colour, are added to the roots from blue or red chroma subcomponent images after thresholding. At the second stage, dark discolourations are extracted by local fuzzy c-means clustering of an HCI intensity image within the binary root mask. Fuzzy clustering is applied in local windows around the series of sample points on roots medial axes (skeleton). The performance of the proposed method is compared with hand-labelled segmentation for a series of several root systems.

The Segmentation of 3D Images Using the Random Walking Technique on a Randomly Created Image Adjacency Graph

This paper considers the problem of image segmentation using the random walker algorithm. In the case of 3D images, the method uses an extreme amount of memory and time resources. These are required in order to represent the corresponding enormous image graph and to solve the resulting sparse linear system. Having in mind these limitations, this paper proposes techniques for the optimization of the random walker approach. The optimization is obtained by processing supervoxels representing homogeneous image regions rather than single voxels. A fast and efficient method for supervoxel determination is introduced. A method for the creation of an image adjacency graph from an irregular grid of supervoxels is also proposed. The results of applying the introduced approach to segmentation of 3D CT data sets are presented and compared with the results of the original random walker approach and other state-of-the-art methods. The accuracy and the computational overhead is regarded in the comparison. The analysis of results shows that the modified method can be successfully applied for the segmentation of volumetric images and provides results in a reasonable time without a significant loss in the image segmentation accuracy. It also outperforms the state-of-the-art methods considered in the comparison.

New accelerated graph-based method of image segmentation applying minimum spanning tree

In this paper problem of graph based image segmentation is considered. In particular, attention is paid to minimal spanning tree based algorithm proposed by Felzenszwalb and Huttenlocher (FH). Although the method yields high quality results for various classes of images, its application is limited mainly to off-line processing. Its due to the very long execution time of the FH method, which in the case of high resolution images, requires processing of millions of vertices and edges contained within the resulting graph. Therefore, some improvements to the FH method are proposed in this paper. The modifications aim at the reduction of algorithm execution time and the usage of computer host memory. These goals are achieved both by reducing the size of input image graph and by applying the methods of GPU parallel computing at initial stages of the algorithm. As the reduction of graph size is obtained by processing meta-pixels representing homogenous regions, the new method is most suitable for the segmentation of images including rare, structurally complex objects distributed over nonuniform background. Results obtained by the introduced approach are compared with the results of the original FH method and other popular graph-based approaches to image segmentation. The comparison includes both the accuracy of image segmentation and the execution time. Analysis of the results clearly shows, that the proposed approach in many cases can significantly accelerate segmentation process without a noticeable loss of image segmentation quality.

Interaction between salt stress and angular leaf spot (Pseudomonas syringae pv lachrymans) in cucumber.

Summary We studied the effects of sequentially applied salt stress and Pseudomonas syringae pv lachrymans (Psl) infection in cucumber (Cucumis sativus L.). Infection development, shoot and root growth potential, the concentrations of chlorophyll and proline as well as electrolyte leakage, lipid peroxidation and H2O2 production were determined. Cucumber plants were first exposed to salt stress and irrigated for seven days with 50 or 100 mM NaCl and thereafter inoculated by Psl. Abiotic stress compromised the defence response to pathogen and disease severity was the highest in 100 mM NaCl-treated plants. The reduced performance of salinized plants under biotic stress could be related to salt stressinduced plant growth inhibition with leaf expansion being the most sensitive to salinity, decreased chlorophyll content, increased electrolyte leakage and prolonged H2O2 accumulation in leaves implying perturbations in redox homeostasis. The response of NaCl-treated and control plants to bacterial infection differed in terms of H2O2 generation and lipid peroxidation. This study confirmed that proline is an important component of local and systemic responses to salt stress and infection. The results contribute to our knowledge of the nature of plant response to a combination of abiotic and biotic stresses Streszczenie W pracy badano efekty sekwencyjnego działania stresu solnego i infekcji Pseudomonas syringae pv. lachrymans (Psl) u ogórka (Cucumis sativus). Analizowano rozwój infekcji, wzrost pędu i korzeni, stężenie chlorofilu i proliny oraz wyciek elektrolitów, peroksydację lipidów i generowanie H2O2. Rośliny ogórka poddawano stresowi solnemu, podlewając je przez siedem dni roztworem NaCl o stężeniu 50 mM lub 100 mM, a następnie zakażano zawiesiną bakterii Psl. Stres abiotyczny osłabiał odpowiedź obronną ogórka na infekcję. Największe nasilenie choroby stwierdzono u roślin traktowanych wcześniej 100 mM NaCl. Słabsze funkcjonowanie roślin zasolonych NaCl w warunkach stresu biotycznego mogło być spowodowane negatywnymi skutkami stresu solnego w postaci zahamowania wzrostu, a zwłaszcza rozwoju blaszki liściowej, obniżenia stężenia chlorofilu, zwiększenia wycieku elektrolitów i wydłużonego w czasie gromadzenia H2O2 w liściach, wskazującego na zaburzenia homeostazy redoks. Różnice w odpowiedzi roślin kontrolnych i traktowanych NaCl na infekcję bakteryjną dotyczyły generowania H2O2 i peroksydacji lipidów. Badania potwierdziły, że prolina jest ważnym elementem lokalnej i systemicznej odpowiedzi na stres solny i infekcję. Uzyskane wyniki poszerzają naszą wiedzę na temat odpowiedzi roślin na stres abiotyczny i biotyczny, działające w połączeniu

A New Idea of Fast Three-Dimensional Median Filtering for Despeckling of Optical Coherence Tomography Images

Abstract Median filtering has been widely used in image processing for noise removal because it can significantly reduce the power of noise while limiting edge blurring. This filtering is still a challenging task in the case of three-dimensional images containing up to a billion of voxels, especially for large size filtering windows. The authors encountered the problem when applying median filter to speckle noise reduction in optical coherence tomography images acquired by the Spark OCT systems. In the paper a new approach to the GPU (Graphics Processing Unit) based median smoothing has been proposed, which uses two-step evaluation of local intensity histograms stored in the shared memory of a graphic device. The solution is able to output about 50 million voxels per second while processing the neighbourhood of 125 voxels by Quadro K6000 graphic card configured on the Kepler architecture.