Plant Recognition Research Articles

Polish Palaeobotany: 750 Million Years of Plant History as Revealed in a Century of Studies. Palaeozoic Macrofossils

During the Palaeozoic Era, plants conquered the land and covered greater and greater areas from coastal lowlands to highlands. Palaeobotanical data based on macroremains from Polish Palaeozoic strata complete and enrich the picture of these processes. Knowledge about Polish Palaeozoic macrofloras developed significantly in the last hundred years but is very unevenly distributed among successive geological periods. Ordovician and Silurian macrofossils are single finds. Cores from deep boreholes provided significant material for recognition of Early Devonian plants. Carboniferous floras, especially from coal measures, are best known, as they are most numerous in taxa and specimens. Permian floras are very rare. Based on Devonian and Carboniferous fossils, many new, evolutionarily important taxa were proposed and have entered world science.

Using deep learning to detect an indicator arid shrub in ultra-high-resolution UAV imagery

Effective monitoring of arid and semi-arid rangelands around the world is essential to understand and combat degradation caused by anthropogenic use and facilitate effective management practices. Remote sensing technologies provide ideal approaches for enhancing traditional on-ground monitoring. However, while broad-scale monitoring of vegetation in rangelands using satellites has been widely adopted, there has been far less uptake of remote sensing for measuring fine-scale indicators of ecosystem condition. This study demonstrates the feasibility of using ultra-high-resolution UAV (Uncrewed Aerial Vehicle) imagery and deep-learning-based object detection models to provide plant recognition and survey information relevant for operational monitoring programmes in arid and semi-arid ecosystems. Seven different object detectors using varying convolutional neural network (CNN) architectures are tested at three image resolutions to detect a widespread, dominant arid shrub species (pearl bluebush, Maireana sedifolia) that serves as a key indicator of overall site condition in southern Australian rangelands. To maximise the strength of statistical analysis, each method is trained on six different training datasets (each using 2,000 to 3,000 training samples) at six widely dispersed sites. This results in 90 trained models, each validated at two sites. To test model generalisability, training and validation data was always sourced from separate vegetation monitoring sites. The influence of variability between sites on detection accuracy is also considered.The best performing models achieved F1 scores (overall accuracy) of around 75% for pearl bluebush detection, a level of accuracy that provides useful monitoring information to land managers. Information extracted from UAV imagery using this approach relates directly to indicators of ecological condition measured in ground-based monitoring; including dominant plant species count, location and density. Continued development and eventual implementation of this method would provide objective conservation-relevant information at broad scales in a far reduced time and at a lower cost than is currently achievable using on-ground approaches.

PAPILIO DEMOLEUS L. AND PAPILIO POLYTES L. (LEPIDOPTERA: PAPILIONIDAE) REARED ON SOME HOST PLANTS AT BUTTERFLY RESEARCH FACILITY, LIPI - CIBINONG, WEST JAVA, INDONESIA

Papilio demoleus L. and P. polytes L. are common butterflies and distribute almost throughout Indonesia. Both species are attractive in butterfly gardens, but may be considered as pests in Citrus plantations. This research aimed to obtain data on their biology, on how the species thrive in captivity, and to assess the alternative host plants. Captive breeding research on these two species was conducted at the butterfly research facility within the period of September 2016 to February 2019, with 482 individuals of P. demoleus and 2,334 individuals of P. polytes reared, of which 292 individuals of P. demoleus and 560 individuals of P. polytes have complete informative data. The average duration of eggs was 3.7 days for P. demoleus on Citrus spp., 3.68 days for P. polytes on Citrus spp., and 3.48 days for P. polytes on Micromelum minutum. The duration of larvae varied between 13–19 days for both species. Prepupal stage lasted for 1 day for all observed individuals. Incidental observation at home during the pandemic COVID-19 added some insights that the pupation happened between 18:00-19:00. The duration of pupae varied between 9–14 days for both species. The total duration of pre-adult stages for both species was between 26–38 days. Adults at the butterfly dome could live up to 19 days for P. demoleus and 39 days for P. polytes. Recognition of alternative host plants is very useful for the improvement of species management in butterfly gardens and in Citrus plantations.

Nutrient regulation of lipochitooligosaccharide recognition in plants via NSP1 and NSP2

Many plants associate with arbuscular mycorrhizal fungi for nutrient acquisition, while legumes also associate with nitrogen-fixing rhizobial bacteria. Both associations rely on symbiosis signaling and here we show that cereals can perceive lipochitooligosaccharides (LCOs) for activation of symbiosis signaling, surprisingly including Nod factors produced by nitrogen-fixing bacteria. However, legumes show stringent perception of specifically decorated LCOs, that is absent in cereals. LCO perception in plants is activated by nutrient starvation, through transcriptional regulation of Nodulation Signaling Pathway (NSP)1 and NSP2. These transcription factors induce expression of an LCO receptor and act through the control of strigolactone biosynthesis and the karrikin-like receptor DWARF14-LIKE. We conclude that LCO production and perception is coordinately regulated by nutrient starvation to promote engagement with mycorrhizal fungi. Our work has implications for the use of both mycorrhizal and rhizobial associations for sustainable productivity in cereals.

Plant and Animal Species Recognition Based on Dynamic Vision Transformer Architecture

Automatic prediction of the plant and animal species most likely to be observed at a given geo-location is useful for many scenarios related to biodiversity management and conservation. However, the sparseness of aerial images results in small discrepancies in the image appearance of different species categories. In this paper, we propose a novel Dynamic Vision Transformer (DViT) architecture to reduce the effect of small image discrepancies for plant and animal species recognition by aerial image and geo-location environment information. We extract the latent representation by sampling a subset of patches with low attention weights in the transformer encoder model with a learnable mask token for multimodal aerial images. At the same time, the geo-location environment information is added to the process of extracting the latent representation from aerial images and fused with the token with high attention weights to improve the distinguishability of representation by the dynamic attention fusion model. The proposed DViT method is evaluated on the GeoLifeCLEF 2021 and 2022 datasets, achieving state-of-the-art performance. The experimental results show that fusing the aerial image and multimodal geo-location environment information contributes to plant and animal species recognition.

Developing an Algorithm for Robotic Precision Application of Crop Protection Products

The existing range of plant identification methods and tools is considered limited in real agrotechnical tasks. The image parameters tend to differ significantly in applied solutions. (Research purpose) To develop an algorithm for crop plant recognition by a robotic device using a state-of-the-art convolutional neural network (R-CNN) and deep learning technology. (Materials and methods) A robotic device has been developed for variable rate application of plant protection products able to recognize both useful crops and weeds, determine the area of processing, namely the coordinates of the processing center and the processing radius. Mask R-CNN and Deeplabv3 plus segmenting neural networks were chosen for crop (white head cabbage) detection. The network-based algorithm detects, segments, and positions plants based on a dataset collected in the image-mask and COCO dataset formats. The data set was formed by aerial photography using an unmanned aircraft. The original images are taken by Xiaovv HD Web USB 150 degree Full HD 1080P webcam and Logitech C270 HD 720p webcam. The trained neural network for the robotic device was installed on the Nvidia Jetson AGX Xavier platform. (Results and discussion) As a result of assessing the accuracy of the model on the test data, the following values were obtained: the number of plants detected is 98 percent, the accuracy of contour detection is 94 percent. (Conclusions) It is proved that the trained neural network can be applied to any cultivated crops, taking into account the heterogeneity of their location in the field, soil types, and the percentage of weeds. As a result, the model is trained to extract the bounding box coordinates and the object (cabbage) location by pixels with the required accuracy for both synthetic and real data.

Research Progress of Pectin Methylesterase and its Inhibitors.

As an important pectin enzyme, pectin methylesterase (PME) can hydrolyze methyl esters, release methanol and reduce esterification. It is essential in regulating pollen tube development, root extension, and fruit ripening. Pectin methylesterase inhibitors (PMEI) can specifically bind PME and inhibit its activity, which jointly determines the esterification degree of pectin. PMEI has important application prospects in plant pest control, fruits and vegetable processing fields. In this paper, the gene families, crystal structures, molecular recognition, and applications in plants and industry are reviewed for the PME and PMEI systems. Finally, the semi-rational design of PMEI is discussed and discussed prospected.

Plant recognition by AI: Deep neural nets, transformers, and kNN in deep embeddings.

The article reviews and benchmarks machine learning methods for automatic image-based plant species recognition and proposes a novel retrieval-based method for recognition by nearest neighbor classification in a deep embedding space. The image retrieval method relies on a model trained via the Recall@k surrogate loss. State-of-the-art approaches to image classification, based on Convolutional Neural Networks (CNN) and Vision Transformers (ViT), are benchmarked and compared with the proposed image retrieval-based method. The impact of performance-enhancing techniques, e.g., class prior adaptation, image augmentations, learning rate scheduling, and loss functions, is studied. The evaluation is carried out on the PlantCLEF 2017, the ExpertLifeCLEF 2018, and the iNaturalist 2018 Datasets—the largest publicly available datasets for plant recognition. The evaluation of CNN and ViT classifiers shows a gradual improvement in classification accuracy. The current state-of-the-art Vision Transformer model, ViT-Large/16, achieves 91.15% and 83.54% accuracy on the PlantCLEF 2017 and ExpertLifeCLEF 2018 test sets, respectively; the best CNN model (ResNeSt-269e) error rate dropped by 22.91% and 28.34%. Apart from that, additional tricks increased the performance for the ViT-Base/32 by 3.72% on ExpertLifeCLEF 2018 and by 4.67% on PlantCLEF 2017. The retrieval approach achieved superior performance in all measured scenarios with accuracy margins of 0.28%, 4.13%, and 10.25% on ExpertLifeCLEF 2018, PlantCLEF 2017, and iNat2018–Plantae, respectively.

CYP6FD5, an antenna-specific P450 gene, is potentially involved in the host plant recognition in Locusta migratoria

Cytochrome P450 monooxygenases (P450s) are a large superfamily of heme-thiolate proteins and play a vital role in the biosynthesis and inactivation of endogenous substances as well as the detoxification of exogenous substances. They also function as odor-degrading enzymes (ODEs) in insect olfactory sensory systems. In the present study, a P450 gene was obtained from the antennae of Locusta migratoria and named as CYP6FD5. Multiple alignment of P450 proteins revealed that LmCYP6FD5 contained five conserved motifs, including the helix C motif, an oxygen-binding site, helix K motif, a meander region, and the haem-binding motif. The expression of LmCYP6FD5 in various tissues and antennal development stages was determined by using RT-qPCR. Our results showed that LmCYP6FD5 was antenna-specific and highly expressed throughout the antennal developmental stages of female and male locusts. Furthermore, the role of LmCYP6FD5 in the perception of host plant volatiles was assessed using RNAi in combination with electroantennogram (EAG) and behavioral responses. Our findings showed that after silencing LmCYP6FD5, the EAG responses of female and male locusts to the main volatiles of gramineous plants, including trans-2-Hexen-1-al, cis-3-Hexenyl acetate, and decanal, were significantly diminished. Moreover, a significant decrease in EAG response of male antennae to benzaldehyde was also observed. In addition, behavioral assay showed that the locust response to single volatile from host plant or wheat remained unchanged after the silencing of LmCYP6FD5. Antenna-specific expression and EAG responses of locusts to host plant volatiles still suggested that LmCYP6FD5 was potentially involved in host plant recognition, although no behavioral changes were observed.

Discrimination of tea plant variety using in-situ multispectral imaging system and multi-feature analysis

Discrimination of tea plant (Camellia sinensis L.) varieties is of significant value for the efficient management of cultivation and resources optimization of tea industry. Phenotypic and spectral characteristics of tea plants are important indicators for determining the quality of tea cultivars to a certain extent. However, few studies have used spectral image information to identify tea plant varieties. The aim of this research was the discrimination of 16 types of high-yield tea plant varieties using a multispectral camera. This methodology involved image registration, calibration, segmentation, information extraction, and data fusion. The hue (H), saturation (S), and value (V), texture information, and several spectral vegetation indices were acquired from the multispectral image of the tea plant canopy. The successive projection algorithm (SPA) was used to analyze the original parameters. Three classification methods were applied to tea plant variety discrimination: Bayes discriminant analysis (BDA), support vector machine (SVM), and extreme learning machine (ELM). The results indicated that SPA based on fusing data combined with the SVM classification model, achieved a feasible method to identify tea plant varieties. Additionally, the method achieved accuracy in the training, test, and validation sets, reaching 97.00%, 90.52%, and 88.67%, respectively. This study proposed a new perspective on multispectral image information as an identifier of tea plant varieties. The explored model will be helpful for the development of portable instruments for commercial applications in variety identification and phenotype recognition of tea plants.

A Review Paper on Plant Disease Detection and Recognition by Using Deep Learning

Abstract: We living being are mostly dependent on plant and animals as well. We don’t have much food that can even sustain for even some years for we are not the only consumers on this earth. 29% of the land where the whole living eco-system exists is not apt. to feed such a huge population. Had we no plants eaters’ bacteria’s or locust, then we might have enough resource that would last for year. My project that is PLANT DISEASE DETECTION AND RECOGNOZATION is all about that. This system will enable us to recognize the type of disease the plants are suffering from and how to diagnose and treat them as well. This system depicts us an appropriate outcome. It will enable us to five a fill depiction of the kind of disease the plant are suffering from. We can even recognize the kind of medication that will be effective in totally eradication of the disease. Plant diseases are one of the foremost important reasons that destroy plants and trees. Detecting those disease at early stages enable us to beat and treat them appropriately. It is quite more important to find the kind of disease first the to treat then unknowingly. The outcomes were 92% accurate and thus we can work on the plant right way to help our plants live even longer. After multiple test, we have come forward with such and initiative that will be a boon for the humankind. Farmers are the backbone of any nation. We cannot survive until they do not get the right price for their yields and our system will play a significant role in that.

Volatile-Mediated Induced and Passively Acquired Resistance in Sagebrush (Artemisia tridentata)

Plants produce a diversity of secondary metabolites including volatile organic compounds. Some species show discrete variation in these volatile compounds such that individuals within a population can be grouped into distinct chemotypes. A few studies reported that volatile-mediated induced resistance is more effective between plants belonging to the same chemotype and that chemotypes are heritable. The authors concluded that the ability of plants to differentially respond to cues from related individuals that share the same chemotype is a form of kin recognition. These studies assumed plants were actively responding but did not test the mechanism of resistance. A similar result was possible through the passive adsorption and reemission of repellent or toxic VOCs by plants exposed to damage-induced plant volatiles (DIPVs). Here we conducted exposure experiments with five chemotypes of sagebrush in growth chambers; undamaged receiver plants were exposed to either filtered air or DIPVs from mechanically wounded branches. Receiver plants exposed to DIPVs experienced less herbivore damage, which was correlated with increased expression of genes involved in plant defense as well as increased emission of repellent VOCs. Plants belonging to two of the five chemotypes exhibited stronger resistance when exposed to DIPVs from plants of the same chemotypes compared to when DIPVs were from plants of a different chemotype. Moreover, some plants passively absorbed DIPVs and reemitted them, potentially conferring associational resistance. These findings support previous work demonstrating that sagebrush plants actively responded to alarm cues and that the strength of their response was dependent on the chemotypes of the plants involved. This study provides further support for kin recognition in plants but also identified volatile-mediated associational resistance as a passively acquired additional defense mechanism in sagebrush.

Constitutive activation of a nuclear-localized calcium channel complex in Medicago truncatula

Nuclear Ca2+ oscillations allow symbiosis signaling, facilitating plant recognition of beneficial microsymbionts, nitrogen-fixing rhizobia, and nutrient-capturing arbuscular mycorrhizal fungi. Two classes of channels, DMI1 and CNGC15, in a complex on the nuclear membrane, coordinate symbiotic Ca2+ oscillations. However, the mechanism of Ca2+ signature generation is unknown. Here, we demonstrate spontaneous activation of this channel complex, through gain-of-function mutations in DMI1, leading to spontaneous nuclear Ca2+ oscillations and spontaneous nodulation, in a CNGC15-dependent manner. The mutations destabilize a hydrogen-bond or salt-bridge network between two RCK domains, with the resultant structural changes, alongside DMI1 cation permeability, activating the channel complex. This channel complex was reconstituted in human HEK293T cell lines, with the resultant calcium influx enhanced by autoactivated DMI1 and CNGC15s. Our results demonstrate the mode of activation of this nuclear channel complex, show that DMI1 and CNGC15 are sufficient to create oscillatory Ca2+ signals, and provide insights into its native mode of induction.

ECAENet: EfficientNet with efficient channel attention for plant species recognition

It is an essential and challenging task to accurately identify unknown plants from images without professional knowledge due to the large intra-class variance and small inter-class variance. Aiming at the problem of low accuracy and model complexity, a lightweight plant species recognition algorithm using EfficientNet with Efficient Channel Attention (ECAENet) is proposed. The proposed approach is based on EfficientNet, which used neural architecture search to gain a baseline network and uniformly scales all dimensions of depth, width, and resolution using a compound coefficient. To overcome Squeeze-and-Excitation block complexity, the proposed method replaces all the two fully-connected layers in the channel attention modules with a fast one-dimensional convolution with an adaptive kernel, which avoids dimensionality reduction and effectively learns the discriminative features. The experimental results demonstrate that our ECAENet achieves 99.56%, 99.75%, 98.40%, and 93.79% accuracy on the well-known Swedish Leaf, Flavia Leaf, Oxford Flowers, and Leafsnap datasets, respectively. In particular, our method achieves 3.6x fewer network parameters and 8.4x FLOPs than others with similar accuracy. Therefore, our method achieves better recognition performance compared to most of the existing plant recognition methods.

Development of plant systemic resistance by beneficial rhizobacteria: Recognition, initiation, elicitation and regulation.

A plant growing in nature is not an individual, but it holds an intricate community of plants and microbes with relatively stable partnerships. The microbial community has recently been demonstrated to be closely linked with plants since their earliest evolution, to help early land plants adapt to environmental threats. Mounting evidence has indicated that plants can release diverse kinds of signal molecules to attract beneficial bacteria for mediating the activities of their genetics and biochemistry. Several rhizobacterial strains can promote plant growth and enhance the ability of plants to withstand pathogenic attacks causing various diseases and loss in crop productivity. Beneficial rhizobacteria are generally called as plant growth-promoting rhizobacteria (PGPR) that induce systemic resistance (ISR) against pathogen infection. These ISR-eliciting microbes can mediate the morphological, physiological and molecular responses of plants. In the last decade, the mechanisms of microbial signals, plant receptors, and hormone signaling pathways involved in the process of PGPR-induced ISR in plants have been well investigated. In this review, plant recognition, microbial elicitors, and the related pathways during plant-microbe interactions are discussed, with highlights on the roles of root hair-specific syntaxins and small RNAs in the regulation of the PGPR-induced ISR in plants.

Smart Gardening: A Solution to Your Gardening Issues

The technology which could make our lives prosper within the four walls could also help to create our own corner of nature nourish. In this paper, we propose a smart gardening system that utilizes the concept of the Internet of Things (IoT) [1]. The major goal of this project is to reduce water consumption when gardening and to maintain the garden remotely. Important plant data, like temperature, relative humidity, and soil moisture, are continuously stored in a relational database in this gardening system. Artificial Intelligence (AI) based planning [2] is used for watering the plants at regular intervals and providing appropriate illumination in the garden area for aesthetics and overall plant growth. Our proposed system reduces the effort due to manual intervention by around 59.3%. The real-time sensor status can be monitored which in turn allows the end-users of the garden to control the surrounding conditions optimal for plant growth, using the Telegram application. A plant recognition model has been introduced in this system, where a Convolutional Neural Network (CNN) [3] based deep learning algorithm classifies the plant categories with 95% accuracy. Moreover, an 98% accurate, deep learning-based, plant health identification model integrated with this gardening system also informs the end-user about the health of the plant.

Gas Turbine Model Parameter Classification During Abnormal Operation Using Support Vector Machine For Maintenance

When there is a contingency in a major transmission system, it is crucial to locate and detect abnormal parameters using an accurately modeled gas turbine (GT) generator. In this paper, a new method was proposed to model, a GT generator system. Firstly, MATLAB/Simulink was used to rebuild GT-based model which was validated using a model in PSS/E. Secondly, an artificial intelligence (AI) based approach, namely Support Vector Machine (SVM) was used for problem recognition in GT power plant. The results showed that, under steady-state, the electrical power of the rebuilt GT model was the same as the model in PSS/E. The advantage of having the MATLAB / Simulink GT model was the ability to visually observe the output from each block which was not possible in PSS/E. In addition, the average training accuracy was over 90% for the detection of GT governor parameter during abnormal behavior. As an implication, the developed model should be considered to apply in real-world grids for operation engineers to detect abnormal governor parameters in GT in the next stage. In turn, it assists in the restoration of GT to its operating condition and minimizes troubleshooting time.

An IoT based authentication system for therapeutic herbs measured by local descriptors using machine learning approach

The work aims to develop an automatic recognition model to classify medicinal plants using machine learning techniques to enrich the traditional medical system of India. Though many countries have accepted conventional medicine as the best alternative to synthetic drugs, there exists limitations such as lack of awareness among general public and unavailability of easy access to its source evidences that has led to its limited acceptance and usability. Herein, an intelligent system is proposed to use Raspberry Pi 3 Model B+ (RPi) and the RPi camera to capture the leaf images of Indian medicinal herbs and reveal their medical properties. Five types of models implemented to identify the medicinal plants. One of the models proposed as Herbmodel extracts a feature map from a captured medicinal leaf by combining three different feature extraction techniques, namely, Scale Invariant Feature Transform (SIFT), Oriented FAST and Rotated BRIEF (ORB) and histogram of oriented gradients on support vector machine as a classifier, predicts an average accuracy of 96.22% over a custom medicinal leaf dataset of 40 different species containing 2515 samples. Generate Bag of Visual Words (BoVW) by applying K-Means clustering on both SIFT and ORB descriptors to reduce the dimensionality. The combined feature vector is further analysed using random forest and k-nearest neighbor classifier. The efficacy of the proposed approach is benchmarked using Flavia dataset and artificial neural network (ANN) as a classifier. Our findings prove that the combination of local descriptors is an efficient measurement approach that benefits automatic recognition of plants based on leaf images. Also, a reliable source of medicinal leaf datasets with good quality leaf images is necessary to establish a machine learning model for medicinal plants.

Advanced Technology in Agriculture Industry by Implementing Image Annotation Technique and Deep Learning Approach: A Review

The implementation of intelligent technology in agriculture is seriously investigated as a way to increase agriculture production while reducing the amount of human labor. In agriculture, recent technology has seen image annotation utilizing deep learning techniques. Due to the rapid development of image data, image annotation has gained a lot of attention. The use of deep learning in image annotation can extract features from images and has been shown to analyze enormous amounts of data successfully. Deep learning is a type of machine learning method inspired by the structure of the human brain and based on artificial neural network concepts. Through training phases that can label a massive amount of data and connect them up with their corresponding characteristics, deep learning can conclude unlabeled data in image processing. For complicated and ambiguous situations, deep learning technology provides accurate predictions. This technology strives to improve productivity, quality and economy and minimize deficiency rates in the agriculture industry. As a result, this article discusses the application of image annotation in the agriculture industry utilizing several deep learning approaches. Various types of annotations that were used to train the images are presented. Recent publications have been reviewed on the basis of their application of deep learning with current advancement technology. Plant recognition, disease detection, counting, classification and yield estimation are among the many advancements of deep learning architecture employed in many applications in agriculture that are thoroughly investigated. Furthermore, this review helps to assist researchers to gain a deeper understanding and future application of deep learning in agriculture. According to all of the articles, the deep learning technique has successfully created significant accuracy and prediction in the model utilized. Finally, the existing challenges and future promises of deep learning in agriculture are discussed.

The Analysis of Plants Recognition Based on Deep Learning and Artificial Neural Network

Abstract: Classification and identification of plants are helpful for people to effectively understand and safeguard plants. The leaves of plants are the most important identifying organs. With the development of artificial intelligence and machine vision technology, plants leaf recognition technology based on image analysis is used to ameliorate the knowledge of plant classification and protection. Deep learning is the condensation of deep neural network learning method and belongs to neural network structure. The main content of this paper is to extract plant leaf features and identify plant species based on image analysis.