scholarly journals Digital Image Processing Technology in Design and Development of Automatic Sorting System for Energy Meter Recovery

2021 ◽  
Vol 2143 (1) ◽  
pp. 012042
Author(s):  
Hao Hu ◽  
Bo Liu ◽  
Wen Jie Li ◽  
He Liu Sun ◽  
Tang Sen Ni

Abstract In order to solve the problems of low sorting efficiency and poor quality caused by manual sorting in traditional electricity meter recovery, this study adopts digital image processing technology to construct an automatic sorting system for electricity meter recovery based on artificial neural network. Firstly, the basic requirements of system construction are analyzed in detail, and then the principle and method of image recognition of artificial neural network are introduced in detail. On this basis, an overall framework of automatic sorting of electricity meter recovery is constructed. Finally, the functional modules are designed and applied, and Azure database is built through SQL Server platform, so as to realize the system application of this research. The final application shows that the automatic sorting system constructed by this study has simple interface and easy operation, which can greatly improve the efficiency and quality of the electricity meter recycling and sorting, and has certain practical significance for the development of the state grid industry.

2019 ◽  
Vol 9 (3) ◽  
pp. 47-52
Author(s):  
Noprizal ◽  
Feri Candra

Abstract Vehicle license plate recognition application has been found in shopping centers, university, and other agency buildings with various methods of recognition. Some examples of methods used such as digital image processing techniques, neural networks and so forth. This study makes an application for the introduction of license plates, especially for student vehicle license plates in the university area. This application is developed with Digital Image Processing Methods and Artificial Neural Networks. In this study, 900 training data are used, taken from 200 photo vehicle number plates, to train 36 characters that contain 26 alphabets and 10 decimal numbers. The training data is used to test 30 photos of vehicle license plates. Plate photos used as training and testing data are the Indonesian standard with black and white plates. Artificial Neural Network used to recognize vehicle license plate by using the Backpropagation method with parameters Epoch 1000, Hidden layer1 with node 60, Hidden layer2 with node 55, Goal 0.001. The final conclusion of this Study shows that the use of Artificial Neural Network Backpropagation method is very good, with the best testing accuracy obtained, namely 98% and 1.25 error. Keywords : digital image processing, artificial neural networks, vehicle license plate Abstrak Aplikasi pengenalan plat nomor kendaraan sudah banyak ditemukan di pusat perbelanjaan, universitas, dan gedung instansi dengan berbagai metode pengenalan. Beberapa contoh metode yang digunakan seperti teknik pengolahan citra digital, jaringan syaraf tiruan dan lain sebagainya. Disini penulis membuat sebuah aplikasi pengenalan plat nomor kendaraan khususnya untuk plat nomor kendaraan mahasiswa yang ada dilikungan Universitas Riau. Aplikasi ini dikembangkan dengan metode pengolahan citra digital dan jaringan syaraf tiruan. Pada penelitian ini, digunakan 700 data pelatihan yang diambil dari 200 foto plat nomor, untuk melatih 36 karakter. Data pelatihan tersebut kemudian digunakan untuk menguji 30 foto plat nomor kendaraan. Foto plat yang dijadikan untuk data pelatihan dan pengujian yaitu plat standar indonesia yang berwarna hitam dan putih. Jaringan syaraf tiruan yang digunakan untuk melakukan pengenalan yaitu dengan Metode Backpropagation dengan parameter Epoch 1000, Hidden layer1 dengan jumlah node 60, Hidden layer2 dengan jumlah node 55, Goal  0,001. Kesimpulan akhir dari penelitian ini yaitu menunjukan bahwa penggunaan Metode Backpropagation jaringan syaraf tiruan ini sangat bagus, dengan akurasi pengujian terbaik yang didapat yaitu 98% dengan eror 1,25. Kata kunci: pengolahan citra digital, jaringan syaraf tiruan, Backpropagation, plat nomor  


2012 ◽  
Vol 24 (01) ◽  
pp. 47-56 ◽  
Author(s):  
Sheng-Fuu Lin ◽  
Hsien-Tse Chen ◽  
Tung-Lung Tsai

Laryngopharyngeal Reflux mostly leads to burns of the pharynx and larynx by reflux from gastric acid and also leads to different degrees of burns in the esophagus and the stomach. This paper aims to develop a technique for analyzing pharyngeal and laryngeal images. With techniques of digital image processing, this paper can choose the suitable images from burns of the pharynx and larynx to obtain the feature zones of burns of the pharynx and larynx. Artificial neural network helps physicians to develop the diagnostic standard about the burns severity of Laryngopharyngeal Reflux. This paper divides the types of the complications into three degrees and compares with other ways (Hanson et al.5 and Ilgner et al.6). The results can be the technical assistance in helping physicians to diagnose the severity of Laryngopharyngeal Reflux and to make a more precise diagnosis.


Author(s):  
Mukhlisulfatih Latief ◽  
Rampi Yusuf

The purpose of this research is to design the application of digital image processing system to identify the image of medicinal plants of Gorontalo region using artificial neural network method using back propagation. This research used a digital image processing method with segmentation and extraction techniques. Segmentation process was carried out using thresholding method. Furthermore, a process of characteristic extraction from medicinal plants drawings was carried out using feature and color feature extractions to obtain the value of metric, eccentricity, hue, saturation and value. these five values were used as parameters for input neurons and one output neuron which denoted the class of the medicinal plants image. Data of this research consisted of 91 images which had been divided into two types, training data and test data. The training data consisted of 80 images and the test data consisted of eleven images. A network architecture was obtained from the training result and it provided the highest accuracy level (100%) and least number of iteration with a number of 50 neurons on hidden layer and 143 epochs. The testing result showed a lower accuracy of 54.54%.


Sign in / Sign up

Export Citation Format

Share Document