Comparison of Water Levels By Sobel Fringe Method and First Order Differential Equations
DOI:
https://doi.org/10.14456/rmutlengj.2024.1Keywords:
Sobel edge detection, First order derivatives bounding, MSE, RMSE, MADAbstract
This research is to determine the edge of the camera image using a model to create a water barrier. CCTV images were analyzed as color images and transformed to find the edge of the image by two methods: Sobel method and first-order derivative method. The number of images to be analyzed was 1000 frames and analyzed 1:1 frames for greater resolution and accuracy, then compared with MSE, RMSE and MAD. The results showed that the first order derivative method was the most detailed and accurate with an MSE of 13.968 %, RMSE of 1.18 and MAD of 0.491 compared to Sobel method with an MSE of 919.01. %RMSE of 9.586% and MAD of 8.645.
References
Thepkasetkul N. Improvement of the canny method for detecting edges of images. 20th National Graduate Research Conference, Khon Kaen University, 2019, p. 299-308.
Homnan B. Moving edge detection using hybrid algorithm. suthiparitat, Faculty of Engineering, Dhurakij Pundit University, p. 133 – 146.
Kawinphas M. Prediction comparison between the bayesian network method and the exponential smoothing method. Journal of Science and Technology. 2015; 2(1): 203-211.
Boonmana C. Comparison of forecasting accuracy with mixed time series models. Journal of Science and Technology, 2015; 177 – 190.
Nawaree P. Planning fresh chicken purchases to reduce the cost of wichian buri grilled chicken restaurants with forecasting methods. 4th Rajamangala University of Technology Rattanakosin Academic Conference; 2019 June 26-28; Bangkok, p. 1-12.
Li B. Comparison of algorithms for finding edges of objects in aerial photography. J Sci Technol. 2022; 105–120.
Kayakij V. Design and development of image edge circuit using impulse C high-level language. In 7th Prince of Songkla University Engineering Conference, 2009; p. 120 – 125.
Sakulwuttichai P. Size analysis of case study materials: peeled bananas. Asia Undergraduate Conference on Computing (AUC), 2022; p. 608 – 615.
Janechai M, Thongkam J. Development of the average of water stream flow prediction models for Nakhonratsima province using data mining techniques. Journal of Science and Technology Mahasarakham University. 2017;36(3):302-12
Kujur A, Raza Z, Khan AA, Wechtaisong C. Data Complexity Based Evaluation of the Model Dependence of Brain MRI Images for Classification of Brain Tumor and Alzheimer’s Disease. IEEE Access, 2022; 10: 112117-33.
Vishnoi VK, Kumar K, Kumar B, Mohan S, Khan AA. Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network. IEEE Access, 2022; 11:6594-609.
Chingthongka N. Image brightness adjustment using histogram properties. 9th National Academic Conference, Nakhon Pathom Rajabhat University, 2017, p. 291 – 295.
Tepkasekul N. Modifications of canny method for image edge detection. 20th Male Graduate Research Conference, 2019, p. 299 – 308.
Khayankit W. Design and development of image boundary circuits using impulse C high-level language. The 7th Prince of Songkla University Academic Conference of Engineering, 2009, p. 120 -125.
Kulvanich N. Comparison of distance measures in cluster analysis for time- series data. Journal of Science and Technology, 2019; 27: p.1002 – 1014.
Boonmana C, Kulvanich N. A comparative prediction accuracy of hybrid time series models. Science and Technology Journal. 2017;25(2):177-90.
Akranuchart P. Comparing the effectiveness of predict model for price return of world gold by employing bootstrap and artificial neural network. 14th National Graduate Studies Research Conference, 2019: p. 425 - 436.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
For Author
