IMPLEMENTASI DEEP LEARNING MENGGUNAKAN FRAMEWORK TENSORFLOW DENGAN METODE FASTER REGIONAL CONVOLUTIONAL NEURAL NETWORK UNTUK PENDETEKSIAN JERAWAT

2018 ◽  
Vol 23 (2) ◽  
pp. 89-102
Author(s):  
Yunita Aulia Hasma ◽  
Widya Silfianti
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network

Jerawat sering dialami oleh kaum wanita maupun pria dari usia remaja hingga dewasa. Banyak rumah sakit dan klinik kecantikan yang dapat di datangi oleh para penderita untuk memeriksakan jerawat tersebut. Penelitian ini merupakan implementasi dari pendeteksian jerawat menggunakan image processing dan secara realtime, lalu sistem akan mengklasifikasikan jerawat yang ada pada wajah. Jerawat yang dapat dikenali oleh sistem ini yaitu jerawat, bekas, dan pus. Sistem deteksi dan klasifikasi ini dibuat dengan metode deep learning dengan menggunakan bahasa pemrograman Python, yang dibantu dengan menggunakan framework TensorFlow dengan model Faster R-CNN. Sistem ini hanya dapat berjalan di laptop dengan memiliki Python versi 3.6 di dalamnya dan telah memliki library Numpy, TkInter, Matplotlib, dan OpenCV dan juga memiliki kamera pada laptop yang digunakan agar dapat menjalankan sistem secara realtime yang didukung dengan GPU yang memadai. Perancangan alur aplikasi menggunakan flowchart diagram. Hasil uji terhadap sistem menggunakan perbandingan objek yang terdeteksi dengan yang seharusnya lalu dibagi dan dikalikan dengan seratus persen. Hasil yang didapat dari pengujian cukup baik menggunakan metode deep learning.

scholarly journals Deep Learning- Based Surveillance System using Face Recognition

2020 ◽  
Vol 32 ◽  
pp. 03011
Author(s):  
Divya Kapil ◽  
Aishwarya Kamtam ◽  
Akhil Kedare ◽  
Smita Bharne
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Face Recognition ◽  
Convolutional Neural Network ◽  
Surveillance System ◽  
Surveillance Systems ◽  
Learning Method ◽  
Security Systems ◽  
The Face

Surveillance systems are used for the monitoring the activities directly or indirectly. Most of the surveillance system uses the face recognition techniques to monitor the activities. This system builds the automated contemporary biometric surveillance system based on deep learning. The application of the system can be used in various ways. The face prints of the persons will be stored inside the database with relevant statistics and does the face recognition. When any unknown face is recognized then alarm will ring so one can alert the security systems and in addition actions will be taken. The system learns changes while detecting faces automatically using deep learning and gain correct accuracy in face recognition. A deep learning method including Convolutional Neural Network (CNN) is having great significance in the area of image processing. This system can be applicable to monitor the activities for the housing society premises.

scholarly journals Deep Learning Convolutional Neural Network for Defect Identification and Classification in Woven Fabric

2021 ◽  
Vol 1 (2) ◽  
pp. 9-13
Author(s):  
Subrata Das ◽  
Sundaramurthy S ◽  
Aiswarya M ◽  
Suresh Jayaram
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Textile Industry ◽  
Woven Fabric ◽  
Defect Identification ◽  
Complete Inspection ◽  
Hidden Layer ◽  
Deep Learning Neural Network

Inspection is the most important role in textile industry which declares the quality of the apparel product. Many Industries were improving their production or quality using Artificial Intelligence. Inspection of fabric in textile industry takes more time and labours. In order to reduce the number of labours and time taken to complete inspection, computerized image processing is done to identify the defects. It gives the accurate result in less time, thereby saves time and increases the production. The convolutional neural network in deep learning is mainly used for image processing for defect detection and classification. The high quality images are given as input, and then the images were used to train the deep learning neural network. Thewoven fabricdefects such as Holes, Selvedge tails, Stains, Wrong drawing and Snarlswere identified by using Convolutional Neural Network. The sample images were collected from the SkyCotex India Pvt.Ltd. The sample images were processed in CNN based machine learning ingoogle platform; the network has a input layer, n number of hidden layer and output layer. The neural network is trained and tested with the samples and the result obtained is used to calculate the efficiency of defect identification.

scholarly journals Image Processing Failure and Deep Learning Success in Lawn Measurement

2020 ◽  
Author(s):  
J. Wilkins Wilkins ◽  
M. V. Nguyen Nguyen ◽  
B. Rahmani Rahmani
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Area Measurement ◽  
Learning Methods ◽  
Hierarchical Networks ◽  
Processing Methods ◽  
Learning Success ◽  
Segmented Images

Lawn area measurement is an application of image processing and deep learning. Researchers used hierarchical networks, segmented images, and other methods to measure the lawn area. Methods’ effectiveness and accuracy varies. In this project, image processing and deep learning methods were used to find the best way to measure the lawn area. Three image processing methods using OpenCV compared to convolutional neural network, which is one of the most famous, and effective deep learning methods. We used Keras and TensorFlow to estimate the lawn area. Convolutional neural network or shortly CNN shows very high accuracy (94-97%). In image processing methods, thresholding with 80-87% accuracy and edge detection are the most effective methods to measure the lawn area while the method ofcontouring with 26-31% accuracy does not calculate the lawn area successfully. We may conclude that deep learning methods, especially CNN, could be the best detective method comparing to image processing learning techniques.

scholarly journals Deep Learning Convolutional Neural Network for Defect Identification and Classification in Woven Fabric

2021 ◽  
pp. 9-13
Author(s):  
Subrata Das ◽  
◽  
Sundaramurthy S ◽  
Aiswarya M ◽  
Suresh Jayaram ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Textile Industry ◽  
Woven Fabric ◽  
Defect Identification ◽  
Complete Inspection ◽  
Hidden Layer ◽  
Deep Learning Neural Network

Inspection is the most important role in textile industry which declares the quality of the apparel product. Many Industries were improving their production or quality using Artificial Intelligence. Inspection of fabric in textile industry takes more time and labours. In order to reduce the number of labours and time taken to complete inspection, computerized image processing is done to identify the defects. It gives the accurate result in less time, thereby saves time and increases the production. The convolutional neural network in deep learning is mainly used for image processing for defect detection and classification. The high quality images are given as input, and then the images were used to train the deep learning neural network. The woven fabric defects such as Holes, Selvedge tails, Stains, Wrong drawing and Snarls were identified by using Convolutional Neural Network. The sample images were collected from the Sky Cotex India Pvt. Ltd. The sample images were processed in CNN based machine learning in google platform; the network has a input layer, n number of hidden layer and output layer. The neural network is trained and tested with the samples and the result obtained is used to calculate the efficiency of defect identification.

scholarly journals Fusion of Multi Modal Lumber Spine Scans Using Wavelet and Convolutional Neural Network

2019 ◽  
Vol 8 (9) ◽  
pp. 1704-1709
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Ct Images ◽  
Single Image ◽  
Mr Images ◽  
Planning Time ◽  
Medical Practitioners ◽  
Fused Image

Multiple medical images of different modalities are fused together to generate a new more informative image thereby reducing the treatment planning time of medical practitioners. In recent years, wavelets and deep learning methods have been widely used in various image processing applications. In this study, we present convolutional neural network and wavelet based fusion of MR and CT images of lumber spine to generate a single image which comprises all the important features of MR and CT images. Both CT and MR images are first decomposed into detail and approximate coefficients using wavelets. Then the corresponding detail and approximate coefficients are fused using convolutional neural network framework. Inverse wavelet transform is then used to generate fused image. The experimental results indicate that the proposed approach achieves good performance as compared to conventional methods

scholarly journals Investigation of a Novel Deep Learning-Based Computed Tomography Perfusion Mapping Framework for Functional Lung Avoidance Radiotherapy

2021 ◽  
Vol 11 ◽  
Author(s):  
Ge Ren ◽  
Sai-kit Lam ◽  
Jiang Zhang ◽  
Haonan Xiao ◽  
Andy Lai-yin Cheung ◽  
...  
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Radiation Therapy ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Contrast Enhancement ◽  
Lung Tissue ◽  
Ct Images ◽  
Normal Lung ◽  
Ct Contrast

Functional lung avoidance radiation therapy aims to minimize dose delivery to the normal lung tissue while favoring dose deposition in the defective lung tissue based on the regional function information. However, the clinical acquisition of pulmonary functional images is resource-demanding, inconvenient, and technically challenging. This study aims to investigate the deep learning-based lung functional image synthesis from the CT domain. Forty-two pulmonary macro-aggregated albumin SPECT/CT perfusion scans were retrospectively collected from the hospital. A deep learning-based framework (including image preparation, image processing, and proposed convolutional neural network) was adopted to extract features from 3D CT images and synthesize perfusion as estimations of regional lung function. Ablation experiments were performed to assess the effects of each framework component by removing each element of the framework and analyzing the testing performances. Major results showed that the removal of the CT contrast enhancement component in the image processing resulted in the largest drop in framework performance, compared to the optimal performance (~12%). In the CNN part, all the three components (residual module, ROI attention, and skip attention) were approximately equally important to the framework performance; removing one of them resulted in a 3–5% decline in performance. The proposed CNN improved ~4% overall performance and ~350% computational efficiency, compared to the U-Net model. The deep convolutional neural network, in conjunction with image processing for feature enhancement, is capable of feature extraction from CT images for pulmonary perfusion synthesis. In the proposed framework, image processing, especially CT contrast enhancement, plays a crucial role in the perfusion synthesis. This CTPM framework provides insights for relevant research studies in the future and enables other researchers to leverage for the development of optimized CNN models for functional lung avoidance radiation therapy.

Comparative Analysis of Deep Convolutional Neural Network Models for Humerus Bone Fracture Detection

2021 ◽  
Vol 11 (12) ◽  
pp. 3117-3122
Author(s):  
A. Sasidhar ◽  
M. S. Thanabal
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Bone Fracture ◽  
Medical Image ◽  
Bone Fractures ◽  
Medical Image Processing ◽  
Fracture Detection ◽  
Wide Range

Deep learning plays a key role in medical image processing. One of the applications of deep learning models in this domain is bone fracture detection from X-ray images. Convolutional neural network and its variants are used in wide range of medical image processing applications. MURA Dataset is commonly used in various studies that detect bone fractures and this work also uses that dataset, in specific the Humerus bone radiograph images. The humerus dataset in the MURA dataset contains both images with fracture and without fracture. The image with fracture includes images with metals which are removed in this work. Experimental analysis was made with two variants of convolutional neural network, DenseNet169 Model and the VGG Model. In case of the DenseNet169 model, a model with the pre trained weights of ImageNet and one without it is experimented. Results obtained with these variants of CNN are comparedand it shows that DenseNet169 model that uses pre-trained weights of ImageNet model performs better than the other two models.

scholarly journals Predicting Retinal Diseases using Efficient Image Processing and Convolutional Neural Network (CNN)

2021 ◽  
pp. 221-227
Author(s):  
Asif Mohammad ◽  
Mahruf Zaman Utso ◽  
Shifat Bin Habib ◽  
Amit Kumar Das
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Image Processing ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Retinal Images ◽  
Retinal Diseases ◽  
Medical Sector ◽  
The Neural Network ◽  
Computational Technology

Neural networks in image processing are becoming a more crucial and integral part of machine learning as computational technology and hardware systems are advanced. Deep learning is also getting attention from the medical sector as it is a prominent process for classifying diseases.  There is a lot of research to predict retinal diseases using deep learning algorithms like Convolutional Neural Network (CNN). Still, there are not many researches for predicting diseases like CNV which stands for choroidal neovascularization, DME, which stands for Diabetic Macular Edema; and DRUSEN. In our research paper, the CNN (Convolutional Neural Networks) algorithm labeled the dataset of OCT retinal images into four types: CNV, DME, DRUSEN, and Natural Retina. We have also done several preprocessing on the images before passing these to the neural network. We have implemented different models for our algorithm where individual models have different hidden layers.  At the end of our following research, we have found that our algorithm CNN generates 93% accuracy.

Sign in / Sign up

Export Citation Format

Share Document