We present a new algorithm for manifold learning and nonlinear dimensionality reduction. Based on a set of unorganized da-ta points sampled with noise from a parameterized manifold, the local geometry of the manifold is learned by constructing an approxi-mation for the tangent space at each point, and those tangent spaces are then aligned to give the global coordinates of the data pointswith respect to the underlying manifold. We also present an error analysis of our algorithm showing that reconstruction errors can bequite small in some cases. We illustrate our algorithm using curves and surfaces both in 2D/3D Euclidean spaces and higher dimension-al Euclidean spaces. We also address several theoretical and algorithmic issues for further research and improvements.

Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

How deep learning extracts and learns leaf features for plant classification

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.

https://cmup.fc.up.pt/cmup/engmat/2012/seminario/artigos2012/PedroSilva/Plant%20species%20identification%20using%20digital%20morphometrics:%20A%20review.pdf

Review: Plant species identification using digital morphometrics: A review

A recognition method for cucumber diseases using leaf symptom images based on deep convolutional neural network

Species knowledge is essential for protecting biodiversity. The identification of plants by conventional keys is complex, time consuming, and due to the use of specific botanical terms frustrating for non-experts. This creates a hard to overcome hurdle for novices interested in acquiring species knowledge. Today, there is an increasing interest in automating the process of species identification.
 The availability and ubiquity of relevant technologies, such as, digital cameras and mobile devices, the remote access to databases, new techniques in image processing and pattern recognition let the idea of automated species identification become reality. This paper is the first systematic literature review with the aim of a thorough analysis and comparison of primary studies on computer vision approaches for plant species identification. We identified 120 peer-reviewed studies, selected through a multi-stage process, published in the last 10 years (2005–2015). After a careful analysis of these studies, we describe the applied methods categorized according to the studied plant organ, and the studied features, i.e., shape, texture, color, margin, and vein structure. Furthermore, we compare methods based on classification accuracy achieved on publicly available datasets. Our results are relevant to researches in ecology as well as computer vision for their ongoing research. The systematic and concise overview will also be helpful for beginners in those research fields, as they can use the comparable analyses of applied methods as a guide in this complex activity.

/pdf/plant-species-identification-using-computer-vision-50ff22bjdd.pdf

Plant Species Identification Using Computer Vision Techniques: A Systematic Literature Review

Plant has plenty use in foodstuff, medicine and industry, and is also vitally important for environmental protection. So, it is important and urgent to recognize and classify plant species. Plant classification based on leaf images is a basic research of botanical area and agricultural production. Due to the high nature complexity and high dimensionality of leaf image data, dimensional reduction algorithms are useful and necessary for such type of data analysis, since it can facilitate fast classifying plants, and understanding and managing plant leaf features. Supervised locally linear embedding (SLLE) is a powerful feature extraction method, which can yield very promising recognition results when coupled with some simple classifiers. In this paper, a semi-SLLE is proposed and is applied to plant classification based on leaf images. The experiment results show that the proposed algorithm performs very well on leaf image data which exhibits a manifold structure.

Dimension reduction using semi-supervised locally linear embedding for plant leaf classification

Tumor classification by combining PNN classifier ensemble with neighborhood rough set based gene reduction

In this paper, we propose a new approach for plant leaf classification, which treat histogram of oriented gradients (HOG) as a new representation of shape, and use the Maximum Margin Criterion (MMC) for dimensionality reduction. We compare this algorithm with a classic shape classification method Inner-Distance Shape Context (IDSC) on Swedish leaf dataset and ICL dataset. The proposed method achieves better performance compared with IDSC.

HOG-based approach for leaf classification

Fusion of superpixel, expectation maximization and PHOG for recognizing cucumber diseases

As one of the most important morphological taxonomy features, plant leaf with many strong points has significant influence on research. In this paper, we propose a novel method of plant classification from leaf image set based on wavelet transforms and support vector machines (SVMS). Firstly, the leaf images are converted into the time-frequency domain image by wavelet transforms without any further preprocessing such as image enhancement and texture thinning, and then feature extraction vector is conducted. Then the effectiveness of the proposed method is evaluated by the classification accuracy of SVM classifier. The experimental results about the data set with 300 leaf images show that the method has higher recognition rate and faster processing speed.

Shanwen Zhang

Papers

Dimension reduction using semi-supervised locally linear embedding for plant leaf classification

Tumor classification by combining PNN classifier ensemble with neighborhood rough set based gene reduction

HOG-based approach for leaf classification

Fusion of superpixel, expectation maximization and PHOG for recognizing cucumber diseases

A method of plant classification based on wavelet transforms and support vector machines