The Design and Development of Tobacco Leaves Color Quality Tester Machine By using Image Processing
Article Sidebar
Main Article Content
Abstract
The objective of this research was to create a tobacco-leaf color quality testing machine by using color classification technique. This technique contains the NI color classification training and nearest neighbor classifier algorithm. This classifier algorithm was used for sample teaching classification. The model of each class was a set of feature vectors which each member was a feature vector of a sample image of the same type used to teach the model. This research used 8 sets of training samples, totaling 800 samples of tobacco leaves, by 100 tobacco leaves for each group. The machine operation test was performed by feeding the tobacco leaves chosen by expertise, 20 tobacco leaves from each sample group, so it was 160 tobacco leaves in total for the testing machine. The results showed that the tobacco leaves color quality tester machine can correctly sort 152 tobacco leaves and 8 tobacco leaves which was an error. It could calculate the percentage of accuracy in each group as following, BL group was 95%, BF group was 90%, BK group was 100%, CL group was 100%, CF group was 100%, CV group was 90%, CS group was 95%, and XS group was 90%. The total average accuracy was 95%. In addition, the overall machine operation was good. These could develop to use image processing technology to increase the accuracy and decrease human errors during the tobacco leaves buying process in the future.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Articles published in Journal of Industrial Technology Ubon Ratchathani Rajabhat University both hard copy and electronically are belonged to the Journal.
References
Pengchan C, Chomtohsuwan T, Cost-Benefit Analysis of Tobacco Production in Thailand. In Piewthongngam K, editors. The 10th Annual Master’s Thesis Conference in Economics; 2016 May 13; Faculty of Economics Khonkaen University. Khonkaen : Faculty of Economics Khonkaen University ; 2016. 40-9. (in Thai)
Yawootti A. Kaewtrakulpong P. A machine vision system for thai flue-cured tobacco classification. In Electrical Engineering/Electronics, Computer, Telecommunications, and Information Technology International Conference; 2005.
Kaewtrakulpong P, Applications of machine vision algorithms using NI Vision. Bangkok: Chulalongkorn University Press; 2016. (in Thai)
Porjai P, Wungmool P, Khamchaiseemek N, Luengviriya C, Chongsereecharoen E, & Wongkrogsri W. (2017). Classification of Thai Rice Seed Cultivars with Image Processing. Progress in Applied Science and Technology, 7(2), 145-52. (in Thai)
Kuhumbunmee Y, Nattawuttsit S, Maneerat P. The Classification of RGB Image with Deep Learning Technique by Artificial Neural Network. Mahidol R2R e-Journal. 2018; 5(2): 1-9. (in Thai)
Pannawan A, Sudsawat S. Automated part inspection by image Processing system in vehicle part manufacturing. The Journal of Applied Science. 2017; 16(1): 45-59. (in Thai)
Nerakaea P, Uangpairojb P, Chamniprasartb K. Using machine vision for flexible automatic assembly system. Procedia Computer Science. 2016; 96: 428-35.
