Deep Learning to Analyze Sliding Drops

Abstract

State-of-the-art contact angle measurements usually involve image analysis of sessile drops. The drops are symmetric and images can be taken at high resolution. The analysis of videos of drops sliding down a tilted plate is hampered due to the low resolution of the cutout area where the drop is visible. The challenge is to analyze all video images automatically, while the drops are not symmetric anymore and contact angles change while sliding down the tilted plate. To increase the accuracy of contact angles, we present a 4-segment super-resolution optimized-fitting (4S-SROF) method. We developed a deep learning-based super-resolution model with an upscale ratio of 3; i.e., the trained model is able to enlarge drop images 9 times accurately (PSNR = 36.39). In addition, a systematic experiment using synthetic images was conducted to determine the best parameters for polynomial fitting of contact angles. Our method improved the accuracy by 21% for contact angles lower than 90°and by 33% for contact angles higher than 90°.

Estimating sliding drop width via side-view features using recurrent neural networks

“…We employed the 4-segment super-resolution optimized-fitting (4S-SROF) 21 , 51 toolkit to extract drop velocity, drop center height, drop length, , and the drop’s middle line angle from the recorded videos (Fig. 2 a).…”

“…The proposed method exhibits robustness against higher Gaussian Blurring values. Recently, we presented a CNN-based super-resolution technique that achieved a more precise analysis of sliding drops 21 . The reported approach led to a 21% increase in accuracy for contact angles below 90° and a 33% improvement for contact angles above 90°.…”