scholarly journals Identifikasi Jenis Daging dengan Menggunakan Algoritma Convolution Neural Network

2021 ◽  
Vol 3 (02) ◽  
pp. 82-88
Author(s):  
Peter Winardi ◽  
Endang Setyati
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Convolution Neural Network ◽  
Cross Entropy ◽  
Model Training

Abstrak — Kebutuhan protein tubuh manusia salah satunya didapatkan dari daging. Banyak jenis daging yang bisa dikonsumsi untuk kebutuhan protein, diantaranya ayam, babi, bebek, kambing, sapi dan jenis lainnya. Pada kondisi daging mentah, tidak semua orang memahami karakteristik / identitas jenis daging karena ada beberapa jenis daging mentah yang hampir sama dari tampilan visual. Untuk menghindari kesalahan saat pemilihan jenis daging yang diinginkan perlu dilakukan identifikasi jenis daging. Pengenalan jenis daging dapat dilakukan dengan pengambilan gambar / citra secara digital. Citra digital yang didapatkan dapat dilakukan identifikasi dengan Convolution Neural Network. Salah satu kemampuan Convolution Neural Network (CNN) dapat melakukan proses identifikasi dan klasifikasi pada Computer Vision. Pada penelitian ini identifikasi jenis daging yang digunakan berupa adalah daging mentah tanpa lemak, kulit dan tulang. Jenis daging mentah yang digunakan sebanyak 5 buah berupa ayam, babi, bebek, kambing dan sapi. Melalui ekstraksi warna dan deteksi tepi beserta CNN didapatkan identitas jenis daging tersebut berupa tulisan / text sesuai jenis daging input citra. Dataset yang digunakan sebanyak 2,250 citra pada masing-masing jenis daging sehingga total 11,250 dataset citra. Penelitian dilakukan dalam 2 bagian sistem arsitektur. Bagian penelitian berupa Training dan Validation beserta testing. Pada bagian training dan validation dilakukan preprocessing . citra resize dari ukuran  300 × 300 piksel menjadi 50 × 50 piksel. Dataset dari masing-masing jenis citra daging mentah yang digunakan 2,250 citra terdiri dari citra jpeg dengan beberapa model citra , diantaranya citra asli, citra cropping, citra flip horisontal RGB, citra flip vertikal RGB, citra RGB, citra channel Red, citra channel Green, citra channel  Blue, citra channel Magenta (greyscale), citra flip vertikal dan citra flip horisontal. Output training dan validasi berupa penyimpanan konfigurasi CNN yang dihasilkan untuk pemodelan saat testing beserta grafik cross entropy. Pembagian dataset citra model training dan validasi sebesar 70% training dan 30% validasi. Sistem testing digunakan uji coba menentukan jenis daging untuk mendapatkan output tulisan / text dari nama daging yang sesuai. Bahasa program yang digunakan  penelitian berupa Python 3.8 beserta Tensorflow dan Keras dengan aplikasi PyCharm 2020.3.2 community edition. Untuk training dan validasi dilakukan uji coba pertama pada dataset dengan resize citra pada ukuran 50 X 50 pixel didapatkan hasil : training loss= 43.89% ; training accuracy= 82.82% ; validation loss= 87.44% ; validation juga dilakukan pada ukuran accuracy: 72.27%. Uji coba training dan validasi ke dua dilakukan resize citra pada ukuran 100 X 100 pixel dengan hasil : training loss= 35.74% ; training accuracy= 85.75% ; validation loss: 81.08% ; validation accuracy: 71.65%. Uji coba testing didapatkan nilai tertinggi dari angka array hasil pembandaingan dengan penyimpanan konfigurasi training dan validasi. Penelitian identifikasi jenis daging bisa ditingkatkan lebih baik bila dilengkapi dengan dataset citra yang lebih memadai.

scholarly journals Automated Failure Detection in Computer Vision Systems

2016 ◽  
Vol 2 (1) ◽  
Author(s):  
H. Yan ◽  
A. Achkar ◽  
Akshaya Mishra ◽  
K. Naik
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Vehicle Detection ◽  
Failure Detection ◽  
Convolution Neural Network ◽  
Vision Systems ◽  
Testing Data ◽  
Computer Vision Systems ◽  
Human Validation

Human validation of computer vision systems increase their operatingcosts and limits their scale. Automated failure detection canmitigate these constraints and is thus of great importance to thecomputer vision industry. Here, we apply a deep neural networkto detect computer vision failures on vehicle detection tasks. Theproposed model is a convolution neural network that estimates theoutput quality of a vehicle detector. We train the network to learnto estimate a pixel-level F1 score between the vehicle detector andhuman annotated data. The model generalizes well to testing data,providing a mechanism for identifying detection failures.

scholarly journals Application Research of Deep Convolutional Neural Network in Computer Vision

2020 ◽  
Vol 2 (2) ◽  
pp. 23
Author(s):  
Lei Wang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Computer Vision ◽  
Face Recognition ◽  
Human Brain ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Convolution Neural Network ◽  
Data Set ◽  
Deep Convolution Neural Network

<p>As an important research achievement in the field of brain like computing, deep convolution neural network has been widely used in many fields such as computer vision, natural language processing, information retrieval, speech recognition, semantic understanding and so on. It has set off a wave of neural network research in industry and academia and promoted the development of artificial intelligence. At present, the deep convolution neural network mainly simulates the complex hierarchical cognitive laws of the human brain by increasing the number of layers of the network, using a larger training data set, and improving the network structure or training learning algorithm of the existing neural network, so as to narrow the gap with the visual system of the human brain and enable the machine to acquire the capability of "abstract concepts". Deep convolution neural network has achieved great success in many computer vision tasks such as image classification, target detection, face recognition, pedestrian recognition, etc. Firstly, this paper reviews the development history of convolutional neural networks. Then, the working principle of the deep convolution neural network is analyzed in detail. Then, this paper mainly introduces the representative achievements of convolution neural network from the following two aspects, and shows the improvement effect of various technical methods on image classification accuracy through examples. From the aspect of adding network layers, the structures of classical convolutional neural networks such as AlexNet, ZF-Net, VGG, GoogLeNet and ResNet are discussed and analyzed. From the aspect of increasing the size of data set, the difficulties of manually adding labeled samples and the effect of using data amplification technology on improving the performance of neural network are introduced. This paper focuses on the latest research progress of convolution neural network in image classification and face recognition. Finally, the problems and challenges to be solved in future brain-like intelligence research based on deep convolution neural network are proposed.</p>

scholarly journals Potato Leaf Disease Diagnosis and Detection System Based on Convolution Neural Network

2020 ◽  
Vol 9 (4) ◽  
pp. 254-259
Keyword(s):  
Neural Network ◽  
Detection System ◽  
Potato Crop ◽  
Disease Diagnosis ◽  
Plant Diseases ◽  
Convolution Neural Network ◽  
Fine Tuning ◽  
Training Dataset ◽  
Potato Leaf ◽  
Model Training

For decades, agriculture has been an essential food source. According to related statics, over 60% of the total earth population mainly depend on agriculture’s sources for their primary feed. Unfortunately, one of the disaster problems that affect badly on agriculture production is plant diseases. There are about 25% of agriculture production lost annually because of plant diseases. Late and Early Blight diseases are one of the most destructive diseases that infect potato crop. Although, the late and inaccurate detection of plant diseases increases the losing percentage for the crop. The main approach of our proposed system is to detect early the plant diseases to decrease the plant’s production losses by using a diagnosis and detection system based on the Convolution Neural Network (CNN). We used CNN to extract the diseases features from the input images of the supported training dataset for classification purposes. For model training, 1700 of potato leaf images were used, then the testing process is done by using approximately 300 images and 100 images for fine tuning and parameters calibration against any biased data. Our proposed CNN architecture archives 98.2% accuracy, which is higher compared with other approaches run on the same dataset.

scholarly journals Convolution neural network and histogram equalization for COVID-19 diagnosis system

2021 ◽  
Vol 24 (1) ◽  
pp. 420
Author(s):  
Bashra Kadhim Oleiwi Chabor Alwawi ◽  
Layla H. Abood
Keyword(s):  
Neural Network ◽  
Data Augmentation ◽  
Training Model ◽  
Histogram Equalization ◽  
Convolution Neural Network ◽  
Training Dataset ◽  
Learning Technology ◽  
Detection Model ◽  
Proposed Model ◽  
Model Training

The coronavirus disease-2019 (COVID-19) is spreading quickly and globally as a pandemic and is the biggest problem facing humanity nowadays. The medical resources have become insufficient in many areas. The importance of the fast diagnosis of the positive cases is increasing to prevent further spread of this pandemic. In this study, the deep learning technology for COVID-19 dataset expansion and detection model is proposed. In the first stage of proposed model, COVID-19 dataset as chest X-ray images were collected and pre-processed, followed by expanding the data using data augmentation, enhancement by image processing and histogram equalization techniuque. While in the second stage of this model, a new convolution neural network (CNN) architecture was built and trained to diagnose the COVID-19 dataset as a COVID-19 (infected) or normal (uninfected) case. Whereas, a graphical user interface (GUI) using with Tkinter was designed for the proposed COVID-19 detection model. Training simulations are carried out online on using Google colaboratory based graphics prossesing unit (GPU). The proposed model has successfully classified COVID-19 with accuracy of the training model is 93.8% for training dataset and 92.1% for validating dataset and reached to the targeted point with minimum epoch’s number to train this model with satisfying results.

Identification of Violence Images Using Convolution Neural Network in Social Network

2020 ◽  
Vol 5 (3) ◽  
pp. 34-38
Author(s):  
Santhi Baskaran ◽  
Jahnavi Korrapati ◽  
Sooriya K. ◽  
Pavithra R.
Keyword(s):  
Neural Network ◽  
Social Network ◽  
Convolution Neural Network

The Convolution Neural Network Combined with the HT Person Fit Statistic to Develop an APP for Detecting Dengue Fever in Children: Development and Usability Study (Preprint)

2019 ◽  
Author(s):  
CHIEN WEI ◽  
Chi Chow Julie ◽  
Chou Willy
Keyword(s):  
Neural Network ◽  
Dengue Fever ◽  
Prediction Accuracy ◽  
Early Stage ◽  
Family Members ◽  
Convolution Neural Network ◽  
Public Health Issue ◽  
Person Fit ◽  
Model Accuracy ◽  
Comparison Results

UNSTRUCTURED Backgrounds: Dengue fever (DF) is an important public health issue in Asia. However, the disease is extremely hard to detect using traditional dichotomous (i.e., absent vs. present) evaluations of symptoms. Convolution neural network (CNN), a well-established deep learning method, can improve prediction accuracy on account of its usage of a large number of parameters for modeling. Whether the HT person fit statistic can be combined with CNN to increase the prediction accuracy of the model and develop an application (APP) to detect DF in children remains unknown. Objectives: The aim of this study is to build a model for the automatic detection and classification of DF with symptoms to help patients, family members, and clinicians identify the disease at an early stage. Methods: We extracted 19 feature variables of DF-related symptoms from 177 pediatric patients (69 diagnosed with DF) using CNN to predict DF risk. The accuracy of two sets of characteristics (19 symptoms and four other variables, including person mean, standard deviation, and two HT-related statistics matched to DF+ and DF−) for predicting DF, were then compared. Data were separated into training and testing sets, and the former was used to predict the latter. We calculated the sensitivity (Sens), specificity (Spec), and area under the receiver operating characteristic curve (AUC) across studies for comparison. Results: We observed that (1) the 23-item model yields a higher accuracy rate (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90) based on the 177-case training set; (2) the Sens values are almost higher than the corresponding Spec values (90% in 10 scenarios) for predicting DF; (3) the Sens and Spec values of the 23-item model are consistently higher than those of the 19-item model. An APP was subsequently designed to detect DF in children. Conclusion: The 23-item model yielded higher accuracy rates (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90). An APP could be developed to help patients, family members, and clinicians discriminate DF from other febrile illnesses at an early stage.

Sign in / Sign up

Export Citation Format

Share Document