Leaf Contours Research Articles

Adaptive loss-guided multi-stage residual ASPP for lesion segmentation and disease detection in cucumber under complex backgrounds

BackgroundIn complex agricultural environments, the presence of shadows, leaf debris, and uneven illumination can hinder the performance of leaf segmentation models for cucumber disease detection. This is further exacerbated by the imbalance in pixel ratios between background and lesion areas, which affects the accuracy of lesion extraction.ResultsAn original image segmentation framework, the LS-ASPP model, which utilizes a two-stage Atrous Spatial Pyramid Pooling (ASPP) approach combined with adaptive loss to address these challenges has been proposed. The Leaf-ASPP stage employs attention modules and residual structures to capture multi-scale semantic information and enhance edge perception, allowing for precise extraction of leaf contours from complex backgrounds. In the Spot-ASPP stage, we adjust the dilation rate of ASPP and introduce a Convolutional Attention Block Module (CABM) to accurately segment lesion areas.ConclusionsThe LS-ASPP model demonstrates improved performance in semantic segmentation accuracy under complex conditions, providing a robust solution for precise cucumber lesion segmentation. By focusing on challenging pixels and adapting to the specific requirements of agricultural image analysis, our framework has the potential to enhance disease detection accuracy and facilitate timely and effective crop management decisions.

Diving into the Water: Amphibious Plants as a Model for Investigating Plant Adaptations to Aquatic Environments.

Amphibious plants can grow and survive in both aquatic and terrestrial environments. This review explores the diverse adaptations that enable them to thrive in such contrasting habitats. Plants with amphibious lifestyles possess fascinating traits, and their phenotypic plasticity plays an important role in adaptations. Heterophylly, the ability to produce different leaf forms, is one such trait, with submerged leaves generally being longer, narrower, and thinner than aerial leaves. In addition to drastic changes in leaf contours, amphibious plants display significant anatomical and physiological changes, including a reduction in stomatal number and cuticle thickness and changes in photosynthesis mode. This review summarizes and compares the regulatory mechanisms and evolutionary origins of amphibious plants based on molecular biology studies actively conducted in recent years using novel model amphibious plant species. Studying amphibious plants will enhance our understanding of plant adaptations to aquatic environments.

The use of automated system-cognitive analysis (ASC-analysis) and the intelligent system “Aidos” for identifying genotypes Actinidia deliciosa (kiwi) on the outer contour of the leaf

The content of this publication reveals the results of the selection and selection of options for solving tasks regarding selection and varietalization of kiwi (Actinidia deliciosa). The “tool” is identified by individual varieties according to the leaves available in the leaf contours, because in their form the information data characterizing the variety (on the phenotype and genotype) are stored in their form. In the context of this research work, an analysis of the signs of the morphological order was carried out, which are inherent in kiwi leaves on the sheet circuit. For this, a system called “Aidos” was used, and the targets were the establishment of (indirect) gender of kiwi plants and the identification of varieties based on the contour of the leaves. The information obtained using the ASC-complex (automated system-cognitive analysis) and the “Aidos” smart system, into which the scanned leaves of leaves, was loaded with it, are disclosed. A evaluative procedure was performed using the quantitative method of the relative sheet circuit of 10 varieties of kiwi. According to the information received, class samples of analyzed genotypes based on the sheet configuration were compiled systematizing. The effect of the characteristic values of the genotypic nature in the most accurate INF4-model of the second iteration in the conditions of the integral order (“sum of knowledge”). Clastorization of the cognitive nature of classes made it possible to differentiate four key cluster structures consisting of subcategories, allocated according to the quantitative features of determinants of the sheet circuit.

Digital morphometrics: Application of MorphoLeaf in shape visualization and species delimitation, using Cucurbitaceae leaves as a model.

PremisePlant leaves are one of the most important organs for plant identification due to their variability across different taxonomic groups. While traditional morphometrics has contributed tremendously to reducing the problems accompanying plant identification and morphology‐based species delimitation, image‐analysis digital solutions have made it easy to detect more characters to complement existing leaf data sets.MethodsHere, we apply MorphoLeaf to generate a morphometric data set from 140 leaf specimens of seven Cucurbitaceae species via landmark extraction, the reparameterization of leaf contours, and data quantification and normalization. A statistical analysis was performed on the resulting data set.ResultsA principal component analysis revealed that leaf blade area, blade perimeter, tooth area, tooth perimeter, the measure of the distance from tooth position to the tip, and the measure of the distance from tooth position to the base are important and informative landmarks that contribute to the variation within the species studied.DiscussionMorphoLeaf can be applied to quantitatively track leaf diversity, thereby functionally integrating morphometrics and shape visualization into the digital identification of plants. The success of digital morphometrics in leaf outline analyses presents researchers with opportunities to carry out more accurate image‐based research in areas such as plant development, evolution, and phenotyping.

Leaf Recognition Based on Elliptical Half Gabor and Maximum Gap Local Line Direction Pattern

Plant identification via leaf images is very meaningful to agricultural information. The existing methods were based on one or two kinds of the three distinct characteristics in leaf images including leaf contours, textures and veins. This limits their recognition performance and scope of application. This paper describes a novel counting-based leaf recognition method, which can directly and effectively combine all of the three kinds of significant characteristics in leaf images. In order to obtain the stable and independent local line responses from leaf contour, texture and vein, elliptical half Gabor is introduced and convoluted with the raw grayscale leaf images, and then maximum gap local line direction patterns are extracted from the local line responses and normalized in direction by cyclically right shifting these patterns until the most numerous bit plane with a value of 1 to the left bit. The histogram of the normalized patterns is calculated and regarded as the counting-based local structure descriptor, and support vector machine is utilized as the classifier. Experimental results on three frequently used leaf databases show that the proposed approach yields a better performance in terms of the classification accuracy, applicability and feasibility in comparison with the state of the art methods.

Unified multi‐scale method for fast leaf classification and retrieval using geometric information

Leaf image identification is a significant and challenging research work. Here, a unified multi-scale method is proposed to capture leaf geometric information for plant leaf classification and image retrieval. For each point on the leaf contour, the unified multi-scale method utilises a simple yet effective three-step strategy to locate corresponding neighbour points. The descriptor extracted using these neighbour points can provide a coarse-to-fine description of leaf contours and is of multi-scale characteristic intrinsically. More importantly, there is no scale parameter to be adjusted in the method, and hence no optimisation procedure is required. The proposed method is applied to three well-known contour features to capture geometric information of leaves, including angle, arch-height, and triangle-area representation. FFT is applied on the features in unified multi-scale method for convenient and fast leaf matching. Leaf classification and image retrieval experiments are conducted on four challenging leaf datasets to test the proposed method and evaluated using three standard performance evaluation metrics. The experimental results and comparisons with the state-of-art methods indicate that the unified multi-scale method has remarkable performance.

Leaf recognition using contour unwrapping and apex alignment with tuned random subspace method

The variation in scale, translation and rotation pose the main challenges to automatic leaf recognition. This paper introduces an automatic leaf recognition method which uses generalised Procrustes analysis (GPA) to mutually align all leaf contours of each of the known classes with respect to scale, translation, rotation and reflection. A mean contour is computed as a representative of each known class. A test leaf is subjected to ordinary Procrustes analysis to be aligned with the mean contour with respect to scale, translation, rotation and reflection. However, experimental analyses show that in the cases where the leaf contours are significantly rotated with respect to each other, generalised Procrustes analysis fails to correctly align. To overcome this, we introduce a novel leaf apex detection algorithm based on Newton's divided method of interpolation and second order differentiation for critical point analysis. The 2-dimensional GPA-transformed contours are unwrapped by computing the distances between the contour points and the centre-of-mass of the contour starting from the leaf apex in an anticlockwise direction to generate a 1-dimensional distance signal. Principal component analysis is used for dimensionality reduction and linear discriminant analysis is used to achieve optimal class separability. The paper extends the use of random subspace method as an ensemble classifier in leaf recognition to exploit the high dimensionality of the feature space for improved identification by avoiding overlearning. Experimental analyses using two publicly available datasets demonstrate the effectiveness of the proposed method.

Image segmentation of overlapping leaves based on Chan–Vese model and Sobel operator

To improve the segmentation precision of overlapping crop leaves, this paper presents an effective image segmentation method based on the Chan–Vese model and Sobel operator. The approach consists of three stages. First, a feature that identifies hues with relatively high levels of green is used to extract the region of leaves and remove the background. Second, the Chan–Vese model and improved Sobel operator are implemented to extract the leaf contours and detect the edges, respectively. Third, a target leaf with a complex background and overlapping is extracted by combining the results obtained by the Chan–Vese model and Sobel operator. To verify the effectiveness of the proposed algorithm, a segmentation experiment was performed on 30 images of cucumber leaf. The mean error rate of the proposed method is 0.0428, which is a decrease of 6.54% compared with the mean error rate of the level set method. Experimental results show that the proposed method can accurately extract the target leaf from cucumber leaf images with complex backgrounds and overlapping regions.

Simulation and visualization of adapting venation patterns

AbstractThis paper suggests a procedural biologically motivated method to simulate the development of leaf contours and the generation of different levels of leaf venation systems. Leaf tissue is regarded as a viscous, incompressible fluid whose 2D expansion is determined by a spatially varying growth rate. Visually realistic development is described by a growth function relative elementary growth rate that reacts to hormone (Auxin) sources embedded in the leaf blade. The shape of the leaf is determined by a set of feature points at the leaf contour. The contour is extracted from images utilizing the curvature scale space corner detection algorithm. Auxin transport is described by an initial Auxin flow from a source to a sink that is gradually channelized into cells with large amounts of highly polarized transporters. The proposed model simulates leaf forms ranging from simple shapes to lobed leaves. The third level of venation system is generated using centroidal Voronoi tessellations and minimum spanning trees, whereas the size of each cell within the Voronoi‐diagram is related to the involved quantity of Auxin. Copyright © 2016 John Wiley & Sons, Ltd.

Plant identification through images: Using feature extraction of key points on leaf contours(1.).

• Premise of the study: Because plant identification demands extensive knowledge and complex terminologies, even professional botanists require significant time in the field for mastery of the subject. As plant leaves are normally regarded as possessing useful characteristics for species identification, leaf recognition through images can be considered an important research issue for plant recognition.• Methods: This study proposes a feature extraction method for leaf contours, which describes the lines between the centroid and each contour point on an image. A length histogram is created to represent the distribution of distances in the leaf contour. Thereafter, a classifier is applied from a statistical model to calculate the matching score of the template and query leaf.• Results: The experimental results show that the top value achieves 92.7% and the first two values can achieve 97.3%. In the scale invariance test, those 45 correlation coefficients fall between the minimal value of 0.98611 and the maximal value of 0.99992. Like the scale invariance test, the rotation invariance test performed 45 comparison sets. The correlation coefficients range between 0.98071 and 0.99988.• Discussion: This study shows that the extracted features from leaf images are invariant to scale and rotation because those features are close to positive correlation in terms of coefficient correlation. Moreover, the experimental results indicated that the proposed method outperforms two other methods, Zernike moments and curvature scale space.

Diallel Analysis of Leaf Shape Variations of Citrus Varieties Based on Elliptic Fourier Descriptors.

The inheritance of citrus leaf shape was investigated by analyzing a diallel set of crosses of five citrus varieties/selections. Leaf contours were extracted by image processing, and described by elliptic Fourier descriptors. Mathematically independent shape characteristics were then identified by principal component analysis of the descriptors. The 1st, 2nd, 3rd and 4th components accounted for 51%, 20%, 10% and 6% of the total shape variation, and were good measures of the ratio of length to width, the position of the centroid, the curvature and the leaf wing size, respectively. Diallel analyses indicated that these components differed substantially in their mode of inheritance. The broad sense heritability was fairly high (>0.90) in the 2nd and 4th components and high (>0.70) in the 1st component, whereas the narrow sense heritability was high only in the 2nd component. There was no significant genetic effect in the 3rd component. The 1st, 2nd and 4th components showed over-, incomplete- and complete- dominance, respectively. The results indicate that elliptic Fourier descriptors can be successfully applied to the quantitative genetic analysis of citrus leaf shape.

Quantitative Evaluation of Soybean (Glycine max L. Merr.) Leaflet Shape by Principal Component Scores Based on Elliptic Fourier Descriptor.

Leaflet shape of thirty-nine soybean cultivars/strains selected to cover the possible diversity of leaf shape, was quantitatively evaluated by principal components scores based on the elliptic Fourier descriptor of contours. After central leaflets of fully expanded compound-leaves of the cultivars/strains were videotaped, binary images of the leaflets were obtained from those video images by image processing. Then, the closed contour of each leaflet was extracted from the binary images and chain-coded by image processing. Because the first twenty harmonics could sufficiently represent soybean leaf contours, 77 elliptic Fourier coefficients were calculated for each chain-coded contour. Then, the Fourier coefficients were standardized so that the coefficients were invariant of the size, rotation, shift and chain-code starting-point of any contour. The principal component analysis about the standardized Fourier coefficients, showed that the cumulative contribution at the fifth principal component was about 96 o/o' Moreover, the effect of each principal component on the leaf shape was clarified by drawing the contours of leaflets using the Fourier coefficients inversely estimated under some typical values of the principal component scores. Consequently, it was indicated that the principal components scores about the standardized elliptic Fourier coefficients gave us powerful quantitative measures to evaluate soybean leaf shape. The analysis of variance and multiple comparison indicated that the genotypic differences on the first, the second and the fifth principal components were significantly large. Because the variations of those principal components were con-tinuous, the effects of the polygenes on the (size-invariant) shape were also suggested.