scholarly journals Rancang Bangun Computer Vision System (CVS) Sebagai Instrumen Pengukuran Warna Buah-Buahan

2020 ◽  
Vol 40 (1) ◽  
pp. 21
Author(s):  
Ferlando Jubelito Simanungkalit ◽  
Rosnawyta Simanjuntak
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Vision System ◽  
Agricultural Products ◽  
Color Measurement ◽  
Percentage Error ◽  
Computer Vision System ◽  
Accuracy Rate ◽  
Processing Software ◽  
Image Processing Software

Color had a correlation with physical appearance, nutritional and chemical content as well as sensory properties which determine the quality of agricultural products and foods. Conventional color measurements were performed destructively using laboratory equipment. Therefore, color measurement methods of agricultural products were needed more quickly, accurately and non-destructively. This study aimed to develop a Computer Vision System (CVS) that can be used as a tool to measure the color of fruits. The designed CVS consists of a 60x60x60 cm black mini photo studio; a pair 15 watt LED lighting, sony α6000 digital camera, a set of laptop and an image processing software applications. Image processing software was programmed using VB.Net 2008 programming language. The developed CVS was calibrated using 24 color charts Macbeth Colorchecker (Gretag-Macbeth, USA). The calibration results of 24 color chart of Macbeth Colorchecker was resulted in a MAPE (Mean Absolute Percentage Error) value of component R / Red = 0%; G / Green = 0% and B / Blue = 0,5%; with 99% accuracy rate. In color measurement, the developed CVS had a 95% accuracy rate.

scholarly journals Sistem Computer Vision Pengenalan Pola Angka dan Operator Matematika Pada Permainan Kartu Angka Berbasis Jaringan Syaraf Tiruan Perceptron

2018 ◽  
Vol 9 (1) ◽  
Author(s):  
Rian Rahmanda Putra ◽  
Fery Antony
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Vision System ◽  
Computer Vision System ◽  
Image Processing Techniques ◽  
Perceptron Algorithm ◽  
Card Number ◽  
Training Stage ◽  
Processing Techniques ◽  
Real Time Application

<p align="center"><strong><em>Abstract <br /></em></strong></p><p><em>Computer vision is an image processing by a computer to obtain information from image captured through the camera generally used in real-time application. This paper reports on the results of research conducted on computer vision system designed to be able to recognize the image number (0-9) and mathematical operators (addition (+) and subtraction (-)) in a card number figures. Computer vision system designed in this study consists of a camera on the android phone that used to captured images on the card number and the computer that has artificial neural network perceptron algorithm in identifiying images. Both components of the computer vision system are connected wirelessly through the TCP/IP Protocol. At the training stage of Perceptron ANN, 10 samples for each number and mathematical operators are used. Computer vision system built in this study also have several image processing techniques such as greyscalling, thresholding, cropping and resizing. This techniques is used to filter the information from the images captured by camera in order to get the adequate and smaller image to be processed by ANN Perceptron. Stages of testing performed three times. First testing is given picture numbers 0-3, second testing is given picture number 4-7 and third testing is given number 8-9, addition symbol and subtraction symbol. Based on testing result, system built are able to recognize 10 from 12 image rendered with a success rate of 83.33%.</em></p><p><strong><em>Keywords</em></strong><em> : Computer vision, perceptron, card number</em></p><p><em> </em></p><p align="center"><strong><em>Abstrak <br /></em></strong></p><p><em>Computer vision merupakan proses pengolahan citra oleh computer untuk mendapatkan informasi dari citra yang ditangkap melalui kamera yang umumnya digunakan pada aplikasi waktu nyata. Tulisan ini melaporkan tentang hasil penelitian yang dilakukan tentang sistem computer vision yang dirancang untuk dapat mengenali gambar angka (0-9) dan operator matematika(penjumlahan (+) dan pengurangan (-)) pada permainan kartu angka. Sistem computer vision yang dirancang pada penelitian ini terdiri dari kamera pada ponsel android yang digunakan untuk menangkap gambar pada kartu angka dan komputer yang memiliki algoritama Jaringan Syaraf Tiruan Perceptron dalam melakukan identifikasi gambar. Kedua komponen sistem computer vision tersebut dihubungkan memlaui jaringan wireless melalui protocol TCP/IP. Pada tahapan pelatihan JST perceptron, digunakan 10 sample citra untuk masing – masing angka dan operator matematika yang akan dikenali oleh sistem. Pada penelitian ini juga dilakukan tahapan pemrosesan citra sebelum diolah oleh JST Perceptron baik dalam tahapan pelatihan maupun pada saat sistem dijalankan. Tahapan pengolahan citra yang digunakan pada penelitian ini adalah greyscalling, thresholding, cropping dan resizing. Hal ini dilakukan untuk menyaring informasi pada citra yang ditangkap oleh kamera agar didapatkan citra yang berukuran kecil dengan  informasi yang lengkap untuk diproses oleh JST Perceptron. Pada saat sistem diuji coba, diberikan 4 deret kartu angka di depan kamera. Pada pengujian pertama diberikan gambar angka 0-3, pengujian kedua diberikan gambar angka 4-7 dan pada pengujian ketiga diberikan angka 8-9 serta gambar operator penjumlahan dan pengurangan. Berdasarkan pengujian yang dilakukan, sistem computer vision yang dirancang mampu mengenali 10dari 12 gambar yang diberikan dengan tingkat keberhasilan sebesar 83.33%.</em></p><p><strong><em>Kata Kunci </em></strong><em>: computer vision, perceptron, kartu angka</em></p>

scholarly journals IMPLEMENTATION OF GENETIC ALGORITHM BASED ARTIFICIAL NEURAL NETWORK TO IDENTIFY VEGETABLES WITH PHYSIOLOGICAL DISEASES

2013 ◽  
pp. 72-77
Author(s):  
Bibhu Prasad ◽  
Ashima Sindhu Mohanty ◽  
Ami Kumar Parida
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Computer Vision ◽  
Artificial Neural Network ◽  
Vision System ◽  
Computer Vision System ◽  
Accuracy Rate ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Neural Network Technology

We synthetically applied computer vision, genetic algorithm and artificial neural network technology to automatically identify the vegetables (tomatoes) that had physiological diseases. Initially tomatoes’ images were captured through a computer vision system. Then to identify cavernous tomatoes, we analyzed the roundness and detected deformed tomatoes by applying the variation of vegetable’s diameter. Later, we used a Genetic Algorithm (GA) based artificial neural network (ANN). Experiments show that the above methods can accurately identify vegetables’ shapes and meet requests of classification; the accuracy rate for the identification for vegetables with physiological diseases was up to 100%. [Nature and Science. 2005; 3(2):52-58].

scholarly journals Measuring drone flight-stability using computer vision

2018 ◽  
Vol 184 ◽  
pp. 02016
Author(s):  
Dávid Dezső; ◽  
Kornél Sarvajcz
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Closed Loop ◽  
Closed Loop Control ◽  
Loop Control ◽  
Flight Stability ◽  
Processing Software ◽  
Image Processing Software

In this project we made an image processing software that we used to examine drone flight stability. One can read about the closed loop control of a quadcopter, the computer vision technics and the results of the test under real circumstances.

Applying Image Processing Methods to Positional Error Evaluation for a Microhole Array

2012 ◽  
Vol 538-541 ◽  
pp. 2131-2134 ◽  
Author(s):  
Dar Yuan Chang ◽  
Yu Xiao Lai ◽  
Ren Bin Fu
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Vision System ◽  
Positional Error ◽  
Error Evaluation ◽  
Computer Vision System ◽  
Critical Feature ◽  
Processing Methods ◽  
Fluid Delivery ◽  
Microhole Array

A microhole array is a critical feature in high-precision products, and acts as a microchannel for fluid delivery or a guiding hole for needle positioning. The precision of microhole fabrication affects the functions of product directly. This study presents a computer vision system that uses image processing methods to evaluate the positional error of a microhole array. A ceramic microhole array drilled by microdrilling process was made to demonstrate the proposed method. Analytical results show that the positional error is related to the precision of machining device noticeably and decreases with the number of holes drilled when adopts the mechanical microdrilling process.

scholarly journals The feasibility of animal source foods’ color measurement using CVS

2021 ◽  
Vol 854 (1) ◽  
pp. 012060
Author(s):  
Bojana Milovanovic
Keyword(s):  
Computer Vision ◽  
Vision System ◽  
Color Measurement ◽  
Computer Vision System ◽  
Animal Source Foods ◽  
Animal Source ◽  
Actual Color

Abstract Color assessment of animal source foods was investigated using a computer vision system (CVS) and a traditional colorimeter. With the same measurement conditions, color readings varied between these two approaches. The color measured by CVS was highly similar to the actual color of animal source foods, and ranged from 75.0%-100.0% of actual colors, whereas colors read by a Minolta colorimeter showed non-typical appearances. The CVS-obtained colors were more similar to the color of food visualized on the monitor, compared to colorimeter-generated color chips. Considering these results, it could be concluded that the CVS is a superior alternative for replacing traditional devices by providing better accuracy.

Sign in / Sign up

Export Citation Format

Share Document