Review on Techniques for Plant Leaf Classification and Recognition

Azlah, Muhammad Azfar Firdaus; Chua, Lee Suan; Rahmad, Fakhrul Razan; Abdullah, Farah Izana; Alwi, Sharifah Rafidah Wan

doi:10.3390/computers8040077

Cited by 107 publications

(57 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It was also stated that the image analysis combined with genetic analysis is a useful method for explaining the main processes that influence salinity tolerance in plants. In this context, − recent studies have been looking for simple, accurate and non-destructive methods to evaluate how abiotic stressors affect plants’ growth [ 7 , 19 , 30 , 32 ]. Regarding plant architecture, fractal dimension has been proven to be a good indicator for analysing plant foliage changes due to salinity.…”

Section: Introductionmentioning

confidence: 99%

Image and fractal analysis as a tool for evaluating salinity growth response between two Salicornia europaea populations

et al. 2020

View full text Add to dashboard Cite

Background This study describes a promising method for understanding how halophytes adapt to extreme saline conditions and to identify populations with greater resistance. Image and colour analyses have the ability to obtain many image parameters and to discriminate between different aspects in plants, which makes them a suitable tool in combination with genetic analysis to study the plants salt tolerance. To the best of our knowledge, there are no publications about the monitoring of halophytic plants by non-destructive methods for identifying the differences between plants that belong to different maternal salinity environments. The aim is to evaluate the ability of image analysis as a non-destructive method and principal component analysis (PCA) to identify the multiple responses of two S. europaea populations, and to determine which population is most affected by different salinity treatments as a preliminary model of selection. Results Image analysis was beneficial for detecting the phenotypic variability of two S. europaea populations by morphometric and colour parameters, fractal dimension (FD), projected area (A), shoot height (H), number of branches (B), shoot diameter (S) and colour change (ΔE). S was found to strongly positively correlate with both proline content and ΔE, and negatively with chlorophyll content. These results suggest that proline and ΔE are strongly linked to plant succulence, while chlorophyll decreases with increased succulence. The negative correlation between FD and hydrogen peroxide (HP) suggests that when the plant is under salt stress, HP content increases in plants causing a reduction in plant complexity and foliage growth. The PCA results indicate that the greater the stress, the more marked the differences. At 400 mM a shorter distance between the factorial scores was observed. Genetic variability analysis provided evidence of the differences between these populations. Conclusions Our non-destructive method is beneficial for evaluating the halophyte development under salt stress. FD, S and ΔE were relevant indicators of plant architecture. PCA provided evidence that anthropogenic saline plants were more tolerant to saline stress. Furthermore, random amplified polymorphic DNA analysis provided a quick method for determining genetic variation patterns between the two populations and provided evidence of genetic differences between them.

show abstract

Section: Introductionmentioning

confidence: 99%

Image and fractal analysis as a tool for evaluating salinity growth response between two Salicornia europaea populations

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It has been previously reported that image processing and computer vision techniques can help to identify plant diseases ( Golhani et al, 2018 ). The accuracy of the classification along with the image pre-processing could yield 90.5% recognition rate ( Azlah et al, 2019 ). Thus far, only a few studies have been carried out to predict the charcoal rot disease development onset ( Nagasubramanian et al, 2018 ).…”

Section: Discussionmentioning

confidence: 99%

Machine Learning Techniques for Soybean Charcoal Rot Disease Prediction

et al. 2020

View full text Add to dashboard Cite

Early prediction of pathogen infestation is a key factor to reduce the disease spread in plants. Macrophomina phaseolina (Tassi) Goid, as one of the main causes of charcoal rot disease, suppresses the plant productivity significantly. Charcoal rot disease is one of the most severe threats to soybean productivity. Prediction of this disease in soybeans is very tedious and non-practical using traditional approaches. Machine learning (ML) techniques have recently gained substantial traction across numerous domains. ML methods can be applied to detect plant diseases, prior to the full appearance of symptoms. In this paper, several ML techniques were developed and examined for prediction of charcoal rot disease in soybean for a cohort of 2,000 healthy and infected plants. A hybrid set of physiological and morphological features were suggested as inputs to the ML models. All developed ML models were performed better than 90% in terms of accuracy. Gradient Tree Boosting (GBT) was the best performing classifier which obtained 96.25% and 97.33% in terms of sensitivity and specificity. Our findings supported the applicability of ML especially GBT for charcoal rot disease prediction in a real environment. Moreover, our analysis demonstrated the importance of including physiological featured in the learning. The collected dataset and source code can be found in https://github.com/Elham-khalili/Soybean-Charcoal-Rot-Disease-Prediction-Dataset-code.

show abstract

“…CNN is better than other classifiers as it identifies and extracts the image features at the same time. Because of this reason, it is faster than other neural networks [6].…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Classification and Recognition of Urban Tree Defects in a Small Dataset using Convolutional Neural Network, Resnet-50 Architecture, and Data Augmentation

Dixit¹,

Nain²

2021

Journal of Forests

View full text Add to dashboard Cite

Identifying hazard trees in urban setup is a time-consuming and tedious task and therefore concerned organizations and homeowner associations may not identify and fix such hazard trees in time. The purpose of this study was to identify the type of defects in the trees with the use of convolutional neural networks. This technology could speed up the process of identifying hazard trees. The study used the Image Processing Toolbox of MATLAB 2019a to process and classifies the images into one of the seven most prominent types of tree defects. The CNN used for this classification was ResNet-50. The Tree Defects dataset was prepared from images from publicly available sources. Further, the accuracy of the classification of these images into each of the defect categories was tested by obtaining a confusion matrix. The performance of ResNet-50 architecture was compared on three more publicly available and common research datasets Caltech101, Flower, and Dogs. The novel Tree Defects dataset was very small and had only 298 images. For its effectiveness on smaller datasets, ResNet-50 architecture was used along with data augmentation of tree defects images by rotating them 90-degrees clockwise and anti-clockwise. The effect of the proportion of the training dataset on model performance was also evaluated by training the model on 70%, 80%, and 90% of the total images in the dataset. The augmented Tree Defects dataset had 894 images. The model performance improves by 43.56% on the augmented Tree Defects dataset. The augmented model achieved the highest classification accuracy of 91.48%. Contribution/Originality:This study is one of the very few studies that have investigated the ways to find an image classification model that delivers high accuracy on smaller datasets. Mostly, a machine learning model is believed to perform better on vast datasets but building large datasets is costly and time-consuming. them weak and turn them into a hazard. A tree becomes a "hazard tree" when it has structural defects that could lead them to damage the property and lives. Therefore, timely management of hazard trees can save them.

show abstract

Review on Techniques for Plant Leaf Classification and Recognition

Cited by 107 publications

References 51 publications

Image and fractal analysis as a tool for evaluating salinity growth response between two Salicornia europaea populations

Image and fractal analysis as a tool for evaluating salinity growth response between two Salicornia europaea populations

Machine Learning Techniques for Soybean Charcoal Rot Disease Prediction

Classification and Recognition of Urban Tree Defects in a Small Dataset using Convolutional Neural Network, Resnet-50 Architecture, and Data Augmentation

Contact Info

Product

Resources

About