Using the periodic wavelet descriptor of plant leaf to identify plant species

Leaf is one of the most important organs of plant. Leaf contour or outline, usually a closed curve, is a fundamental morphological feature of leaf in botanical research. In this paper, a novel shape descriptor based on periodic wavelet series and leaf contour is presented, which we name as Periodic Wavelet Descriptor (PWD). The PWD of a leaf actually expresses the leaf contour in a vector form. Consequently, the PWD of a leaf has a wide range in practical applications, such as leaf modeling, plant species identification and classification, etc. In this work, the plant species identification and the leaf contour reconstruction, as two practical applications, are discussed to elaborate how to employ the PWD of a plant leaf in botanical research.

Download Full-text

Plant leaf recognition with shallow and deep learning: A comprehensive study

Intelligent Data Analysis ◽

10.3233/ida-194821 ◽

2020 ◽

Vol 24 (6) ◽

pp. 1311-1328

Author(s):

Jozsef Suto

Keyword(s):

Machine Learning ◽

Plant Species ◽

Research Area ◽

Research Papers ◽

Plant Leaf ◽

Leaf Characteristics ◽

The Past ◽

The Earth ◽

Test Sets ◽

Comprehensive Study

Nowadays there are hundreds of thousands known plant species on the Earth and many are still unknown yet. The process of plant classification can be performed using different ways but the most popular approach is based on plant leaf characteristics. Most types of plants have unique leaf characteristics such as shape, color, and texture. Since machine learning and vision considerably developed in the past decade, automatic plant species (or leaf) recognition has become possible. Recently, the automated leaf classification is a standalone research area inside machine learning and several shallow and deep methods were proposed to recognize leaf types. From 2007 to present days several research papers have been published in this topic. In older studies the classifier was a shallow method while in current works many researchers applied deep networks for classification. During the overview of plant leaf classification literature, we found an interesting deficiency (lack of hyper-parameter search) and a key difference between studies (different test sets). This work gives an overall review about the efficiency of shallow and deep methods under different test conditions. It can be a basis to further research.

Download Full-text

Analysis of plant leaf metabolites reveals no common response to insect herbivory by Pieris rapae in three related host-plant species

Journal of Experimental Botany ◽

10.1093/jxb/erv045 ◽

2015 ◽

Vol 66 (9) ◽

pp. 2547-2556 ◽

Cited By ~ 8

Author(s):

A. C. Riach ◽

M. V. L. Perera ◽

H. V. Florance ◽

S. D. Penfield ◽

J. K. Hill

Keyword(s):

Host Plant ◽

Plant Species ◽

Pieris Rapae ◽

Insect Herbivory ◽

Plant Leaf ◽

Host Plant Species ◽

Common Response

Download Full-text

Pemanfaatan Tumbuhan Obat Masyarakat Marind yang Bermukim di Taman Nasional Wasur, Merauke

JURNAL BIOLOGI PAPUA ◽

10.31957/jbp.573 ◽

2018 ◽

Vol 1 (2) ◽

pp. 58-64

Author(s):

Dwi Haryanto ◽

Rosye H.R. Tanjung ◽

Konstantina M.B. Kameubun

Keyword(s):

Medicinal Plants ◽

Literature Review ◽

Medicinal Plant ◽

Key Words ◽

Plant Species ◽

National Park ◽

Medicinal Plant Species ◽

Root Bark ◽

Plant Leaf ◽

Ipomoea Triloba

Study on the used of medicinal plants by Marind people who lived at Wasur National Park, Merauke was conducted by using descriptive methods which include observation, interview, documentation, literature review techniques, as well as emic and ethic approaches. During the study there were 46 species which belong to 26 families plants found as medicinal plants used by Marind people to cure about 30 diseases. Among 46 species, there were 7 potential medicinal plant species which known and used by most Marind people. The seven potential medicinal plant species were Ipomoea triloba L., Bauhinia sp., Pittosporum sp., Kingiodendron platycarpum Bent., Sophora tool mentosa L.Cyrtandra sp., dan Tinopspora disstiflora L. Part of plant used vary from leaf, root, bark, fruit and other part of plant. Compare to other part of plant, leaf was the most common used as traditional medicinal plant. Key words: traditional medicinal plant, Marind people, Wasur National Park

Download Full-text

Plant Species Identification based on Plant Leaf Using Computer Vision and Machine Learning Techniques

Journal of Multimedia Information System ◽

10.33851/jmis.2019.6.2.49 ◽

2019 ◽

Vol 6 (2) ◽

pp. 49-60 ◽

Cited By ~ 1

Author(s):

Surleen Kaur ◽

Prabhpreet Kaur

Keyword(s):

Machine Learning ◽

Computer Vision ◽

Species Identification ◽

Plant Species ◽

Machine Learning Techniques ◽

Plant Leaf ◽

Learning Techniques ◽

Plant Species Identification

Download Full-text

Machine Learning and Convolution Neural Network Approaches to Plant Leaf Recognition

Advances in Data Mining and Database Management - Handbook of Research on Automated Feature Engineering and Advanced Applications in Data Science ◽

10.4018/978-1-7998-6659-6.ch013 ◽

2021 ◽

pp. 234-248

Author(s):

Rajesh K. V. N. ◽

Lalitha Bhaskari D.

Keyword(s):

Neural Network ◽

Machine Learning ◽

Plant Species ◽

Intelligent Systems ◽

Human Life ◽

Species Recognition ◽

Convolution Neural Network ◽

Plant Leaf ◽

Network Approaches ◽

Number Of Plant Species

Plants are very important for the existence of human life. The total number of plant species is nearing 400 thousand as of date. With such a huge number of plant species, there is a need for intelligent systems for plant species recognition. The leaf is one of the most important and prominent parts of a plant and is available throughout the year. Leaf plays a major role in the identification of plants. Plant leaf recognition (PLR) is the process of automatically recognizing the plant species based on the image of the plant leaf. Many researchers have worked in this area of PLR using image processing, feature extraction, machine learning, and convolution neural network techniques. As a part of this chapter, the authors review several such latest methods of PLR and present the work done by various authors in the past five years in this area. The authors propose a generalized architecture for PLR based on this study and describe the major steps in PLR in detail. The authors then present a brief summary of the work that they are doing in this area of PLR for Ayurvedic plants.

Download Full-text

Identification of Plant Types by Leaf Textures Based on the Backpropagation Neural Network

International Journal of Electrical and Computer Engineering (IJECE) ◽

10.11591/ijece.v8i6.pp5389-5398 ◽

2018 ◽

Vol 8 (6) ◽

pp. 5389 ◽

Cited By ~ 1

Author(s):

Taufik Hidayat ◽

Asyaroh Ramadona Nilawati

Keyword(s):

Neural Network ◽

Feature Extraction ◽

Plant Species ◽

Recognition Accuracy ◽

Backpropagation Neural Network ◽

Training Set ◽

Plant Resources ◽

Plant Leaf ◽

Tropical Plant ◽

Texture Characteristics

The number of species of plants or flora in Indonesia is abundant. The wealth of Indonesia's flora species is not to be doubted. Almost every region in Indonesia has one or some distinctive plant(s) which may not exist in other countries. In enhancing the potential diversity of tropical plant resources, good management and utilization of biodiversity is required. Based on such diversity, plant classification becomes a challenge to do. The most common way to recognize between one plant and another is to identify the leaf of each plant. Leaf-based classification is an alternative and the most effective way to do because leaves will exist all the time, while fruits and flowers may only exist at any given time. In this study, the researchers will identify plants based on the textures of the leaves. Leaf feature extraction is done by calculating the area value, perimeter, and additional features of leaf images such as shape roundness and slenderness. The results of the extraction will then be selected for training by using the backpropagation neural network. The result of the training (the formation of the training set) will be calculated to produce the value of recognition accuracy with which the feature value of the dataset of the leaf images is then to be matched. The result of the identification of plant species based on leaf texture characteristics is expected to accelerate the process of plant classification based on the characteristics of the leaves.

Download Full-text

Multiscale Convolutional Neural Networks with Attention for Plant Species Recognition

Computational Intelligence and Neuroscience ◽

10.1155/2021/5529905 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Xianfeng Wang ◽

Chuanlei Zhang ◽

Shanwen Zhang

Keyword(s):

Neural Network ◽

Plant Species ◽

High Frequency ◽

Species Recognition ◽

Low Frequency ◽

Plant Leaf ◽

Network Training ◽

Feature Based ◽

The Rich ◽

Frequency Features

Plant species recognition is a critical step in protecting plant diversity. Leaf-based plant species recognition research is important and challenging due to the large within-class difference and between-class similarity of leaves and the rich inconsistent leaves with different sizes, colors, shapes, textures, and venations. Most existing plant leaf recognition methods typically normalize all leaf images to the same size and then recognize them at one scale, which results in unsatisfactory performances. A novel multiscale convolutional neural network with attention (AMSCNN) model is constructed for plant species recognition. In AMSCNN, multiscale convolution is used to learn the low-frequency and high-frequency features of the input images, and an attention mechanism is utilized to capture rich contextual relationships for better feature extraction and improving network training. Extensive experiments on the plant leaf dataset demonstrate the remarkable performance of AMSCNN compared with the hand-crafted feature-based methods and deep-neural network-based methods. The maximum accuracy attained along with AMSCNN is 95.28%.

Download Full-text