Correction of Disturbances Influence on Results of Elongated Objects's Probe Microscopy Using Predictive Relief Estimates

Correct measurement of the distorted objects length in images is an important task of probe microscopy. Existing measurement methods do not fully take into account the specifics of a given subject area. The purpose of this work was to develop an algorithm for locating the objects skeletons adapted to the images peculiarities in scanning probe microscopy and does not require significant computing resources. The limited speed of the probe microscope, contamination of the sample surface, and Non-ideality of the probe lead to typical disturbances in the form of stripes, 1/f noise, and brightness fluctuations and cause defragmentation of the skeletons of objects and a decrease in the accuracy of length measurements. The method proposed in this paper uses predictive relief estimates to eliminate the influence of these disturbances. The forecast is calculated based on extrapolation of information from the raster columns of the already scanned part of the image. The forecast interval is equal to the discretization interval of the image. The set of forecast estimates forms a predictive image, which is subsequently used to determine the length of objects. The peculiarity of predictive images is the sharpening of areas distorted by disturbances. This made it possible to defragment the skeletons and measure their length more accurately when locating objects using curvature detectors. Studies have shown that an increase in the integral prediction error is a indication of the need for additional image filtering from low-frequency or shock interference. At the same time, the use of predictive images reduces the relative deviation of the number of unrecognized skeletons and the average deviation of the maximum measured length. It has been established that control information in the form of forecast estimates can be used in image processing in probe microscopy to detect and partially eliminate disturbances. The formation of predictive images enhances the sharpness of objects and increases the probability of their correct selection using methods based on the analysis of changes in the brightness function.

1. Persky E, Vardi N, Shperber Y, Kalisky B. Improving the sensitivity of scanning probe microscopy with mechanical vibrations. Appl. Phys. Lett. 2018;(113): 173101. DOI: 10.1063/1.5051620

2. Eaton P, West P. Atomic Force Microscopy. Oxford university press, 2010. doi: 10.1093/acprof:oso/9780199570454.001.0001

3. Ronneberger O, Fischer Ph, Brox T. U-Net: Convolutional networks for biomedical image segmentation. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science. Springer, Cham. 2015;(9351):234-241. doi: 10.1007/978-3-319-24574-4_28

4. Ramadevi Y, Sridevi T, Poornima B, Kalyani B. Segmentation And Object Recognition Using Edge Detection Techniques, International Journal of Computer Science and Information Technology. 2010;(2):153-161. DOI: 10.5121/IJCSIT.2010.2614

5. Okunev AG, Mashukov MY, Nartova AV, Matveev AV. Nanoparticle Recognition on Scanning Probe Microscopy Images Using Computer Vision and Deep Learning. Nanomaterials. 2020;10(7):1285. doi: 10.3390/nano10071285

6. Saha K, Borgefors G, di Baja GS. A survey on skeletonization algorithms and their applications. Pattern Recognition Letters. 2016;(76):3-12. doi: 10.1016/j.patrec.2015.04.006

7. Shen W. [et al.]. DeepSkeleton: Learning MultiTask Scale-Associated Deep Side Outputs for Object Skeleton Extraction in Natural Images. IEEE Transactions on Image Processing. 2016;(26):5298-5311. doi: 10.1109/tip.2017.2735182

8. Gonzalez RС, Woods RE. Digital image processing. Pearson Education. 2008;954 p.

9. Sultane C, Bhalerao M, Bonde S. Character recognition based on skeletonization: a survey. International Journal of Advanced Research. 2017;(5):1503-1519. DOI: 10.21474/IJAR01/4564

10. Russ JC, Neal FB. The Image Processing Handbook. CRC Press, 2017. 7th Edition. 1056 P. doi: 10.1201/b18983

11. Sebastian TB, Klein PN, Kimia BB. Recognition of shapes by editing their shock graphs. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;26(5):550-571. doi: 10.1109/TPAMI.2004.1273924

12. Liu Wenping [et al.]. Distance Transform-Based Skeleton Extraction and Its Applications in Sensor Networks. IEEE Transactions on Parallel and Distributed Systems. 2013;24(9):1763-1772. doi: 10.1109/TPDS.2012.300

13. Gulyaev PV, Shelkovnikov EY. Segmentation of Fragmented Reference Labels Images Using Combined Surface Curvature Detectors in Probe Microscopy. Chemical Physics and Mesoscopy. 2023;25(1):5-12. (In Russ.). DOI: 10.15350/17270529.2023.1.1

14. Lipanov AM, Shelkovnikov YuK, Gafarov MR, Gulyaev PV. Application of the forecasting device in raster scanning devices. Management, Control, Diagnostics. 2010;(7):59-64. (In Russ.).

15. Vatolin D, Ratushnyak A, Smirnov M, Yukin V. Data compression methods. Archiver device, image and video compression. M.: Dialog-MIFI. 2002;384 p.