Affiliations: [a] Baikal School of BRICS, Irkutsk National Research Technical University, Irkutsk, Russia | [b] Artificial Intelligence Laboratory, Institute of Information Technology and Data Science, Irkutsk National Research Technical University, Irkutsk, Russia | [c] University of Information and Communication Technology, Thai Nguyen, Vietnam | [d] Institute of Energy Systems SB RAS, Irkutsk, Russia
Corresponding author: T.H. Nguyen, Baikal School of BRICS, Irkutsk National Research Technical University, Irkutsk, Russia. E-mail: [email protected].
Abstract: Bubble detection is a challenging problem in automatic process control in the power and energy industry, medical and pharmaceutical industry and many other fields. Computer vision methods applications for bubble detection and measurement is the principal step of robust bubbles monitoring systems development. In various applications the input image may include a diverse and image background, especially in different environments. This paper presents a new and effective bubble detection approach. The main steps of this proposed approach are as follows: image preprocessing, background subtraction, and contour detection. The graph cut algorithm is used for image segmentation. The Haar wavelet transform is applied to collect bubble component points. The developed approach is evaluated based on the real data set.