A Method for Distortion Correction in Label Images Processing

Purpose of research. Methods and algorithms for automatic acquisition and improvement of digital image quality in controllers for labeling systems and image processing and recognition systems are the objects of the article. The purpose of the study is to develop new methods to improve quality and image processing for optoelectronic devices and vision systems. The topicality of the scientific and technical task to expand the functionality and improve the quality of computing devices in control systems and quality control of objects labeling is mentioned; in particular, the need to extract the image of the label in order to determine defects of the quality of labeling is highlighted. Distortion was chosen as the main adjustable feature of the obtained images.

Methods. The main approaches used in the determination and correction of distortion are considered; their shortcomings are revealed; the analysis of the main methods described in the literature is carried out. The paper used the framework of analytical geometry, pattern recognition theory, methods for processing and analysis of bitmap images.

Results. A method for image processing to improve image quality, software for detecting and processing images of labels and documents were developed. A variant of determining the radial distortion in case of the shift of the observation in different directions is proposed. The modeling of the developed method by means of the specially created software is performed. The experimental studies of the developed software were carried out. Their results are provided, and advantages and disadvantages are highlighted.

Conclusion. The developed method can be used in image acquisition and processing devices operating in automatic mode and applied in vision and labeling quality control systems.

1. Panishchev V.S., Reshetnikova V.P., Chernetskaya I.Ye. Blok upravleniya avtomatizirovannoy sistemoy naneseniya etiketok na podvizhnyy ob"yekt. [Control block of automated system for label gluing to mobile object] Izvestiya vysshikh uchebnykh zavedeniy. Priborostroyeniye = Journal of Instrument Engineering, 2010, vol. 53, no. 9, pp. 5862 (In Russ.).

2. Panishchev V.S., Slavkova O.B. Skhema upravleniya shagovym dvigatelem dlya avtomatizirovannoy sistemy naneseniya etiketki na podvizhnyy ob"yekt [Control circuit of stepper motor for automated system of moving objects labeling] Izvestiya vysshikh uchebnykh zavedeniy. Priborostroyeniye = Journal of Instrument Engineering, 2012, vol. 55, no. 2, pp. 4346 (In Russ.).

3. Panishchev V.S., Slavkova O.B. [The algorithm of the automatic system for applying labels to a moving object] Informatsionnoizmeritel'nyye diagnosticheskiye i upravlyayushchiye sistemy. Diagnostika 2011. Sbornik materialov II Mezhdunarodnoy nauchno-tekhnicheskoy konferentsii [In the collection: Informationmeasuring diagnostic and control systems. Diagnostics 2011. Collection of materials of the II International Scientific and Technical Conference]. Kursk, 2011, pp. 152155 (In Russ.).

4. Devernay F., Faugeras O. Straight lines have to be straight F. Devernay. MVA, 2001, no.13(1), pp. 1424.

5. Beyer H. Accurate calibration of CCDcameras. Proc. International Conference on Computer Vision and Pattern Recognition, Urbana Champaign. IEEE CS Press, Piscataway, June 1992.

6. Tsai R. A versatile camera calibration technique for highaccuracy 3D machine vision metrology using offtheshelf TV cameras and lenses. IEEE Robotics Autom, 1987, no.3(4), pp. 323–344.

7. Faugeras O., Toscani G. Structure from Motion using the Reconstruction and Reprojection Technique. IEEE Workshop on Computer Vision, Miami Beach, November-December, IEEE CS Press, Piscataway, 1987, pp. 345–348.

8. Lavest J., Viala M., Dhome M. Do we really need an accurate calibration pattern to achieve a reliable camera calibration. Proceedings of the 5th European Conference on Computer Vision. Vol. 1 of Lecture Notes in Computer Science, Freiburg, Germany. Springer, Berlin Heidelberg New York, June 1998, pp. 158–174.

9. Brown D. Closerange camera calibration. Photogrammetric Engineering, 1971, N37(8), pp. 855–866.

10. Deriche R., Vaillant R., Faugeras O. From noisy edge points to 3D reconstruction of a scene: A robust approach and its uncertainty analysis. Proceedings of the 7th Scandinavian Conference on Image Analysis, Alborg, Denmark, August 1991, pp. 225–232.

11. Shah S., Aggarwal J.K. Intrinsic parameter calibration procedure for a (highdistortion) fisheye lens camera with distortion model and accuracy estimation. Pattern Recognition, no.29(11), pp. 1175–1788.

12. Devernay F. A nonmaxima suppression method for edge detection with subpixel accuracy. Technical report RR 2724, NRIA, 1995.

13. Otsu N. A Threshold Selection Method from GrayLevel Histograms. IEEE Trans. Syst . Man Cybern, 1979, vol. 9, no.1, pp. 6266.

14. Korostelev S.I. [Program for pattern recognition]. Mater. XXXV mezhvuzovskoy nauchno-tekhnicheskoy konferentsii studentov i aspirantov v oblasti nauchnykh issledovaniy: "Molodezh' i XXI vek". [Materials of XXXV interuniversity scientific and technical conference of students and graduate students in the field of scientific research. "Youth and the 21st Century"]. Kursk, 2007, pp. 2021 (In Russ.).