scholarly journals Research on leaf image identification based on improved AlexNet neural network

2021 ◽  
Vol 2031 (1) ◽  
pp. 012014
Author(s):  
Wenkun Zhang ◽  
Juanjuan Wen
Keyword(s):  
Neural Network ◽  
Image Identification ◽  
Leaf Image

scholarly journals An SDP Characteristic Information Fusion-Based CNN Vibration Fault Diagnosis Method

2019 ◽  
Vol 2019 ◽  
pp. 1-14 ◽  
Author(s):  
Xiaoxun Zhu ◽  
Jianhong Zhao ◽  
Dongnan Hou ◽  
Zhonghe Han
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Information Fusion ◽  
Fault Identification ◽  
High Complexity ◽  
Test Rig ◽  
Rotor Vibration ◽  
Vibration Signals ◽  
Image Identification ◽  
Diagnosis Method

This study proposes a symmetrized dot pattern (SDP) characteristic information fusion-based convolutional neural network (CNN) fault diagnosis method to resolve issues of high complexity, nonlinearity, and instability in original rotor vibration signals. The method was used to conduct information fusion of real modal components of vibration signals and SDP image identification using CNN in order to achieve vibration fault diagnosis. Compared with other graphic processing methods, the proposed method more fully expressed the characteristics of different vibration signals and thus presented variations between different vibration states in a simpler and more intuitive way. The proposed method was experimentally investigated using simulation signals and rotor test-rig signals, and its validity and advancements were demonstrated using experimental analysis. By using CNN through deep learning to adaptively extract SDP characteristic information, vibration fault identification was ultimately realized.

scholarly journals Artificial intelligence for the detection of vertebral fractures on plain spinal radiography

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Kazuma Murata ◽  
Kenji Endo ◽  
Takato Aihara ◽  
Hidekazu Suzuki ◽  
Yasunobu Sawaji ◽  
...  
Keyword(s):  
Neural Network ◽  
Sensitivity And Specificity ◽  
Vertebral Fractures ◽  
Early Identification ◽  
Delayed Diagnosis ◽  
Diagnostic Errors ◽  
Diagnostic Strategy ◽  
Image Identification ◽  
Orthopedic Surgeons

AbstractVertebral fractures (VFs) cause serious problems, such as substantial functional loss and a high mortality rate, and a delayed diagnosis may further worsen the prognosis. Plain thoracolumbar radiography (PTLR) is an essential method for the evaluation of VFs. Therefore, minimizing the diagnostic errors of VFs on PTLR is crucial. Image identification based on a deep convolutional neural network (DCNN) has been recognized to be potentially effective as a diagnostic strategy; however, the accuracy for detecting VFs has not been fully investigated. A DCNN was trained with PTLR images of 300 patients (150 patients with and 150 without VFs). The accuracy, sensitivity, and specificity of diagnosis of the model were calculated and compared with those of orthopedic residents, orthopedic surgeons, and spine surgeons. The DCNN achieved accuracy, sensitivity, and specificity rates of 86.0% [95% confidence interval (CI) 82.0–90.0%], 84.7% (95% CI 78.8–90.5%), and 87.3% (95% CI 81.9–92.7%), respectively. Both the accuracy and sensitivity of the model were suggested to be noninferior to those of orthopedic surgeons. The DCNN can assist clinicians in the early identification of VFs and in managing patients, to prevent further invasive interventions and a decreased quality of life.

scholarly journals GRADING WARNA DAUN TEMBAKAU BAWAH NAUNGAN MENGGUNAKAN JARINGAN SARAF TIRUAN. (Color Grading of Shaded Tobacco Leaves Using Artificial Neural Network)

2017 ◽  
Vol 12 (1) ◽  
pp. 43-57
Author(s):  
Aneke Rintiasti ◽  
Ikhwan Krisnadi
Keyword(s):  
Neural Network ◽  
Raw Material ◽  
Classification Model ◽  
Tobacco Leaves ◽  
Tobacco Leaf ◽  
Leaf Analysis ◽  
Color Grading ◽  
Leaf Image ◽  
Rgb Model

Various cigars, which are present in the community among the elite and prestigious venues, the raw material is a Java Tabak cigars, tobacco from Java, especially Klaten and Jember. Recent years, the availability of labor more difficult with increasing costs skyrocketing, so it must start leading to mechanization. The purpose of this research was to Generate Design of Tobacco Leaf Analysis Applications, Getting Segmentation Model for pixel readout from tobacco leaves, Generate classification models that can be used for the separation of tobacco leaves which is expected to ease the process of evaluation and classification of color in the first sorting Tobacco leaves. Tobacco Leaf used is The Under Shade Tobacco leaf (TBN) consisted of five classes, namely the color Blue / Green (B), Yellow (K), Yellow Sprayed (KV), Red (M), Red Sprayed (MV). Before analyzed the leaves image photographed using a cabinet that unaffected the outside light. TBN leaf image is then analyzed using the RGB model and models HSV, RGB image of the model  is  analyzed using the characteristic leaf color values, The image of leaf TBN that meets the characteristics become an input of Bakcpropagation Neural Networks with the target are 5 color grade which converted into a binary form. The research resulted Segmentation Model for pixel readout TBN tobacco leaves using RGB models, classification model that can be used for the classification of TBN leaves use Neural Network Back Training RGB with an error value = 8.7%.”keywords : besuki tobacco, shaded tobacco, image processingABSTRAK Aneka cerutu, yang hadir di kalangan komunitas elit dan tempat-tempat yang prestisius, bahan bakunya adalah Java Tabak Cerutu, tembakau asal Jawa, khususnya Klaten dan Jember. Beberapa tahun belakangan ini, ketersediaan tenaga kerja semakin sulit den gan biaya yang semakin meroket, sehingga harus mulai mengarah ke mekanisasi. Tujuan Penelitian ini adalah menghasilkan Rancang Bangun Aplikasi Analisa Daun Tembakau, mendapatkan Model Segmentasi untuk pembacaan piksel daun tembakau, menghasilkan Model Klasifikasi yang dapat digunakan untuk Pemisahan daun tembakau,sehingga diharapkan dapat mempermudah proses evaluasi dan klasifikasi warna pada Sortasi I daun Tembakau. Daun Tembakau yang digunakan adalah Daun Tembakau Bawah Naungan (TBN) jenis besuki terdiri dari 5 kelas warna yaitu Biru / Hijau (B), Kuning (K), Kuning Tidak Merata (KV), Merah (M), Merah Tidak Merata (MV). Sebelum dianalisa citra daun difoto menggunakan cabinet yang tidak terpengaruh cahaya luar. Citra daun TBN tersebut kemudian dianalisa menggunakan model RGB, dari model RGB citra daun dianalisa menggunakan karakteristik nilai warna, citra daun TBN yang memenuhi karakteristik menjadi masukan Jaringan Saraf Tiruan Bakcpropagation dengan target 5 kelas warna yang sudah diubah menjadi bentuk biner. Penelitian menghasilkan Model Segmentasi untuk pembacaan piksel daun tembakau TBN menggunakan model RGB, Model Klasifikasi yang dapat digunakan untuk klasifikasi daun TBN menggunakan Neural Network Back PropagationTraining RGB dengan nilai error = 8.7%.Kata Kunci : tembakau besuki, tembakau bawah naungan, pengolahan citra 

scholarly journals A Novel Identification Method for Apple (Malus domestica Borkh.) Cultivars Based on a Deep Convolutional Neural Network with Leaf Image Input

Symmetry ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 217
Author(s):  
Chengzhong Liu ◽  
Junying Han ◽  
Baihong Chen ◽  
Juan Mao ◽  
Zhengxu Xue ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Malus Domestica ◽  
High Specificity ◽  
Deep Convolutional Neural Network ◽  
Stable Convergence ◽  
Malus Domestica Borkh ◽  
Apple Cultivars ◽  
Leaf Image ◽  
Generalization Accuracy

The innovation of germplasm resources and the continuous breeding of new varieties of apples (Malus domestica Borkh.) have yielded more than 8000 apple cultivars. The ability to identify apple cultivars with ease and accuracy can solve problems in apple breeding related to property rights protection to promote the healthy development of the global apple industry. However, the existing methods are inconsistent and time-consuming. This paper proposes an efficient and convenient method for the classification of apple cultivars using a deep convolutional neural network with leaf image input, which is the delicate symmetry of a human brain learning. The model was constructed using the TensorFlow framework and trained on a dataset of 12,435 leaf images for the identification of 14 apple cultivars. The proposed method achieved an overall accuracy of 0.9711 and could successfully avoid the over-fitting problem. Tests on an unknown independent testing set resulted in a mean accuracy, mean error, and variance of μ a c c = 0.9685 , μ ε = 0.0315 , and σ 2 = 1.89025 E − 4 , respectively, indicating that the generalization accuracy and stability of the model were very good. Finally, the classification performance for each cultivar was tested. The results show that model had an accuracy of 1.0000 for Ace, Hongrouyouxi, Jazz, and Honey Crisp cultivars, and only one leaf was incorrectly identified for 2001, Ada Red, Jonagold, and Gold Spur cultivars, with accuracies of 0.9787, 0.9800, 0.9773, and 0.9737, respectively. Jingning1 and Pinova cultivars were classified with the lowest accuracies, with 0.8780 and 0.8864, respectively. The results also show that the genetic relationship between cultivars Shoufu 3 and Yanfu 3 is very high, which is mainly because they were both selected from a red mutation of Fuji and bred in Yantai City, Shandong Province, China. Generally, this study indicates that the proposed deep learning model is a novel and improved solution for apple cultivar identification, with high generalization accuracy, stable convergence, and high specificity.

Cotton Leaf Disease Detection by Feature Extraction

2016 ◽  
pp. 89-104
Author(s):  
Savita N. Ghaiwat ◽  
Parul Arora
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Feature Extraction ◽  
Early Stage ◽  
Cotton Leaf ◽  
Control Methods ◽  
The Neural Network ◽  
The World ◽  
Leaf Image

Cotton leaf diseases have occurred all over the world, including India. They adversely affect cotton quality and yield. Technology can help in identifying disease in early stage so that effective treatment can be given immediately. Now, the control methods rely mainly on artificial means. This paper propose application of image processing and machine learning in identifying three cotton leaf diseases through feature extraction. Using image processing, 12 types of features are extracted from cotton leaf image then the pattern was learned using BP Neural Network method in machine learning process. Three diseases have been diagnosed, namely Powdery mildew, Downy mildew and leafminer. The Neural Network classification performs well and could successfully detect and classify the tested disease.

Sign in / Sign up

Export Citation Format

Share Document