Medicinal and poisonous plants classification from visual characteristics of leaves using computer vision and deep neural networks

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102683 - 102683

Опубликована: Июнь 12, 2024

Poisonous plants are the third largest category of poisons known globally, which pose a risk poisoning and death to humans. Currently, identification medicinal poisonous is done by humans using experimental methods, not accurate associated with many errors, also use laboratory methods requires experts this method very costly time-consuming. Therefore, distinguishing between important emerging, non-destructive, fast such as computer vision artificial intelligence. In study, we propose robust generalized model spatial attention (SA) channel (CA) modules for classification different plants. A dataset containing 900 confirmed images three plant classes (oregano, weed) was used. The mechanisms enhance efficiency deep learning (DL) networks allowing them precisely focus on all relevant input elements. order performance proposed model, CA implemented based four pooling operations including global average pooling-based (GAP-CA), mixed (Mixed-CA), gated (Gated-CA), tree (Tree-CA) operations. results showed that DL Tree-CA had promising outperformed other state-of-the-art models, achieving values 99.63%, 99.38%, 99.52%, 99.74%, 99.42%, accuracy, precision, recall, specificity, F1-score, respectively. findings support our model's success in identifying from similar Recent advancements computer-based technologies intelligence enable automatic detection plants, revolutionizing traditional methods.

Язык: Английский

---

On the importance of integrating convolution features for Indian medicinal plant species classification using hierarchical machine learning approach

Ecological Informatics, Год журнала: 2024, Номер 81, С. 102611 - 102611

Опубликована: Апрель 22, 2024

This work proposes a novel hierarchical classification framework designed to categorize hundred Indian medicinal plant species. The innovation lies in introducing comprehensive feature representation by integrating convolutional features with geometric, texture, shape, and multispectral for tasks. In this study, two-level model is proposed address the challenges of inter-class similarity intra-class variations. first level classifies 100 species into 11 groups based on visual similarities among plants. At two, specific containing each group are predicted using Random Forest classifier. evaluation performed at two levels analyze effectiveness model. performance analysis compares individual types against composite Performance also evaluated that demonstrate high between classes variations separately. Furthermore, generality tested self-created datasets-RTL80 RTP40, requiring more than 300 man-hours collect. Experimental results promising accuracy 94.54% GSL100 leaf dataset 75.46% RTL80 RTP40 real-time datasets reflecting superiority over state-of-the-art methods.

Язык: Английский

---

Inferring the relationship between soil temperature and the normalized difference vegetation index with machine learning

Ecological Informatics, Год журнала: 2024, Номер 82, С. 102730 - 102730

Опубликована: Июль 20, 2024

Язык: Английский

---

Research on species identification of wild grape leaves based on deep learning

Scientia Horticulturae, Год журнала: 2024, Номер 327, С. 112821 - 112821

Опубликована: Янв. 6, 2024

Язык: Английский

---

A deep learning method for differentiating safflower germplasm using optimal leaf structure features

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 102998 - 102998

Опубликована: Янв. 1, 2025

Язык: Английский

---

A novel lightweight model for tea disease classification based on feature reuse and channel focus attention mechanism

Engineering Science and Technology an International Journal, Год журнала: 2025, Номер 61, С. 101940 - 101940

Опубликована: Янв. 1, 2025

Язык: Английский

---

Wood species classification using prototypical networks: a few shot learning model

Journal of the Indian Academy of Wood Science, Год журнала: 2025, Номер unknown

Опубликована: Янв. 17, 2025

Язык: Английский

---

Multiscale feature fusion and enhancement in a transformer for the fine-grained visual classification of tree species

Ecological Informatics, Год журнала: 2025, Номер unknown, С. 103029 - 103029

Опубликована: Янв. 1, 2025

Язык: Английский

---

Harnessing Spectral Libraries From AVIRIS‐NG Data for Precise PFT Classification: A Deep Learning Approach

Plant Cell & Environment, Год журнала: 2025, Номер unknown

Опубликована: Янв. 27, 2025

ABSTRACT The generation of spectral libraries using hyperspectral data allows for the capture detailed signatures, uncovering subtle variations in plant physiology, biochemistry, and growth stages, marking a significant advancement over traditional land cover classification methods. These enable improved forest accuracy more precise differentiation species functional types (PFTs), thereby establishing sensing as critical tool PFT classification. This study aims to advance monitoring PFTs Shoolpaneshwar wildlife sanctuary, Gujarat, India Airborne Visible/Infrared Imaging Spectrometer‐Next Generation (AVIRIS‐NG) machine learning techniques. A comprehensive library was developed, encompassing from 130 species, with focus on their features support were collected AVIRIS‐NG imaging ASD Handheld Spectroradiometer, capturing wide range wavelengths (400–1600 nm) encompass key physiological biochemical traits plants. Plant grouped into five distinct Fuzzy C‐means clustering. Key features, including band reflectance, vegetation indices, derivative/continuum properties, identified through combination ISODATA clustering Jeffries‐Matusita (JM) distance analysis, enabling effective feature selection To assess utility library, three advanced classifiers—Parzen Window (PW), Gradient Boosted Machine (GBM), Stochastic Descent (SGD)—were rigorously evaluated. GBM classifier achieved highest accuracy, an overall (OAA) 0.94 Kappa coefficient 0.93 across PFTs.

Язык: Английский

---

Feature Extraction and Machine Learning in Plant Disease Detection: A Survey

Lecture notes in networks and systems, Год журнала: 2025, Номер unknown, С. 363 - 374

Опубликована: Янв. 1, 2025

Язык: Английский

---