Recognition system of leaf images based on neuronal network

In forest variety registration, visual traits of the plants appearance are widely used to discern different tree species. The new recognition system of leaf image strategy which based on neural network established to administrate a hierarchical list of leaf images, some sorts of edge detection can be performed to identify the individual tokens of every image and the frame of the leaf can be got to differentiate the tree species. An approach based on back-propagation neuronal network is proposed and the programming language for the implementation is also Riven by using Java. The numerical simulations results have shown that the proposed leaf strategt is effective and feasible.

A new multi-scale analytic algorithm for edge extraction of strawberry leaf images in natural light

In this study,a new algorithm was proposed for edge extraction of greenhouse strawberry leaf in natural light based on the 4-level daubechies 5(‘db5’)wavelet decomposition.This algorithm adopts different segmentation methods for the reconstructed images at different scales to erase the external background and the internal leaf vein interference.There were two advantages of this method.One was that it can provide the abstraction from different spaces to express a same image.The other one was that some image features are hard to be acquired in some scale spaces,while the features are easy to be obtained in other scale spaces.In this image process methods,the Otsu threshold segmentation was to obtain the binary image areas,and the Canny segmentation is to obtain the accurate gradient edges,then the morphological methods and the logical calculus methods were to avoid the fragments inside the leaf area and the adhesions outside the leaf area.Since the strawberry leaf images were different respectively,and the greenhouse optical radiation and reflection may cause local non-uniform illumination of leaf image,the pseudo canny edges of leaf image ere divided into three categories in this research.The first category was the external pseudo canny edges area of the first layer reconstructed leaf image,the second category was the internal pseudo canny edges area in highlight of the third layer reconstructed leaf image,the third category was the internal pseudo canny edges area of significantly different grayscale of the third layer reconstructed leaf image.The different processing methods were constructed for the three kinds of different texture features based on the multi scale reconstructed images,then the complete and the accurate leaf edges without interference were obtained.Finally,the multi scale method was simplified and a remarkably effective segmentation algorithm was deduced for the greenhouse strawberry leaf in natural light.

A new approach to learning and recognizing leaf diseases from individual lesions using convolutional neural networks

Leaf disease recognition using image processing and deep learning techniques is currently a vibrant research area.Most studies have focused on recognizing diseases from images of whole leaves.This approach limits the resulting models’ability to estimate leaf disease severity or identify multiple anomalies occurring on the same leaf.Recent studies have demonstrated that classifying leaf diseases based on individual lesions greatly enhances disease recognition accuracy.In those studies,however,the lesions were laboriously cropped by hand.This study proposes a semi-automatic algorithm that facilitates the fast and efficient preparation of datasets of individual lesions and leaf image pixel maps to overcome this problem.These datasets were then used to train and test lesion classifier and semantic segmentation Convolutional Neural Network(CNN)models,respectively.We report that GoogLeNet’s disease recognition accuracy improved by more than 15%when diseases were recognized from lesion images compared to when disease recognition was done using images of whole leaves.A CNN model which performs semantic segmentation of both the leaf and lesions in one pass is also proposed in this paper.The proposed KijaniNet model achieved state-of-the-art segmentation performance in terms of mean Intersection over Union(mIoU)score of 0.8448 and 0.6257 for the leaf and lesion pixel classes,respectively.In terms of mean boundary F1 score,the KijaniNet model attained 0.8241 and 0.7855 for the two pixel classes,respectively.Lastly,a fully automatic algorithm for leaf disease recognition from individual lesions is proposed.The algorithm employs the semantic segmentation network cascaded to a GoogLeNet classifier for lesion-wise disease recognition.The proposed fully automatic algorithm outperforms competing methods in terms of its superior segmentation and classification performance despite being trained on a small dataset.

A leaf image localization based algorithm for different crops disease classification

Agricultural crop production is a major contributing element to any country’s economy.To maintain the economic growth of any country plants disease detection is a leading factor in agriculture.The contribution of the proposed algorithm is to optimize the extracted infor-mation from the available resources for the betterment of the result without any additional complexity.The proposed technique basically localizes the leaf region prior to the image classification into healthy and diseased.The novelty of this work is to fuse the information extracted from the available resources and optimize it to enhance the expected outcome.The leaf colors are analyzed using color transformation for the seed region identification.The mapping of a low-dimensional RGB color image into L*a*b color space provides an expansion of the spectral range.The neighboring pixels-based leaf region growing is applied on the initial seeds.In order to refine the leaf boundary and the disease-affected areas,we employed a random sample consensus(RANSAC)for suitable curve fitting.The feature sets using bag of visual words,Fisher vectors,and handcrafted features are extracted followed by classification using logistic regression,multilayer perceptron model,and support vector machine.The performance of the proposal is analyzed through PlantVillage datasets of apple,bell pepper,cherry,corn,grape,potato,and tomato.The simulation-based analysis of the proposed contextualization-based image categorization process outperforms as compared with the state of arts.The proposed approach provides average accuracy and area under the curve of 0.932 and 0.903,respectively.

Development of a mobile application for identification of grapevine(Vitis vinifera L.)cultivars via deep learning

Traditional vine variety identification methods usually rely on the sampling of vine leaves followed by physical,physiological,biochemical and molecular measurement,which are destructive,time-consuming,labor-intensive and require experienced grape phenotype analysts.To mitigate these problems,this study aimed to develop an application(App)running on Android client to identify the wine grape automatically and in real-time,which can help the growers to quickly obtain the variety information.Experimental results showed that all Convolutional Neural Network(CNN)classification algorithms could achieve an accuracy of over 94%for twenty-one categories on validation data,which proves the feasibility of using transfer deep learning to identify grape species in field environments.In particular,the classification model with the highest average accuracy was GoogLeNet(99.91%)with a learning rate of 0.001,mini-batch size of 32,and maximum number of epochs in 80.Testing results of the App on Android devices also confirmed these results.

Multifractal methods for rapeseed nitrogen nutrition qualitative diagnosis modeling

Nutrition diagnosis plays a key role in the crop＇s growth, which has mainly been car- ried out in the field by agricultural workers. Currently, automatic nutrition recognition technologies have been widely used in this field. A procedure is proposed in this paper to diagnose nitrogen nutrition non-destructively for rapeseed qualitatively based on the multifractal theory. Twelve texture parameters are given by the method of multifractal detrended fluctuation （MF-DFA）, which contains six generalized Hurst exponents and six relative multifractal parameters that are used as features of the rapeseed leaf images for identifying the two nitrogen levels, namely, the N-mezzo and the N-wane. For the base leaves, central leaves and top leaves of the rapeseed plant and the three-section mixed samples, three parameters combinations are selected to conduct the work. Five classifiers of Fisher＇s linear discriminant algorithm （LDA）, extreme learning machine （ELM）, support vector machine and kernel method （SVMKM）, random decision forests （RF） and K-nearest neighbor algorithm （KNN） are employed to calculate the diagno- sis accuracy. An interesting finding is that the best diagnose accuracy is from the base leaves of the rapeseed plant. It is explained that the base leaf is the most sensitive to the nitrogen deficiency. The diagnose effect by the base leaves samples is outshining the existing result significantly for the same leaves samples. For the mixed samples, the aver- aged discriminant accuracy reaches 97.12% and 97.56% by SVMKM and RF methods with the 10-fold cross-validation respectively. The resulting high accuracy on N-levels identification shows the feasibility and efficiency of our method.