Article information

2016 , Volume 21, ¹ 1, p.49-59

Bychkov I.V., Rugnikov G.M., Fedorov R.K., Avramenko Y.V.

Interpreter of Spatial Object Query Language for raster image processing

Purpose. To expand the class of identifiable objects on raster images a priori knowledge is necessary. The required set of knowledge depends on the task. The existing identification methods are characterized by the use of a fixed set of knowledge and that is not enough. So further study in terms of formalization of knowledge and its application in the identification process is required.

Methodology. On the basis of the deformable models and Prolog III we propose calculus of spatial objects. The calculus of spatial objects allows a user to express the knowledge and requirements to identifiable objects. The effectiveness of the proposed algorithms for the interpretation of images has been proven. The interpretation is based on the classic Prolog mechanism with backtracking, discarding unpromising branches, checking the spatial limitations and the use of A* algorithm and the multi start.

Findings. The proposed interpreter differs from the existing ones by the feature, which allows the user to turn on and use a variety of knowledge in the recognition process. A series of experiments showed the efficiency of the interpreter spatial calculation objects for raster image processing.

Originality/value. The main advantage of this method is the usage of the language, which can describe the shape, position, texture spectral characteristics of identifiable objects without changing the code recognition algorithm. In the logical methods the object features are extracted from images and stored in a knowledge base as the facts. The size of the knowledge base influences on the speed and the requirement for the amount of the computer RAM. Therefore, these methods work well on tasks with low dimensional feature space. In the proposed method, the information of the image is generated dynamically on demand, in accordance with the knowledge base, by the unification of built-in predicates.

[full text]
Keywords: prolog, image identification, image analysis, pattern recognition, deformable templates

Author(s):
Bychkov Igor Vyacheslavovich
Dr. , Academician RAS, Professor
Position: Director
Office: Institute for System Dynamics and Control Theory of Siberian Branch of Russian Academy of Sciences
Address: 664033, Russia, Irkutsk, Lermontova st., 134
Phone Office: (3952) 45-30-61
E-mail: idstu@icc.ru
SPIN-code: 5816-7451

Rugnikov Gennady Mikhailovich
Dr. , Senior Scientist
Position: Head of Departament
Office: Institute for System Dynamics and Control Theory Siberian Branch of RAS, Irkutsk Scientific Center of Siberian Branch of Russian Academy of Sciences
Address: 664033, Russia, Irkutsk, Lermontova st., 134
Phone Office: (3952) 45-30-06
E-mail: rugnikov@icc.ru
SPIN-code: 2947-8443

Fedorov Roman Konstantinovich
PhD.
Position: Leading research officer
Office: Institute for System Dynamics and Control Theory, Siberian Branch of RAS, Irkutsk Scientific Center of Siberian Branch of Russian Academy of Sciences
Address: 664033, Russia, Irkutsk, Lermontova st., 134
Phone Office: (3952) 453108
E-mail: fedorov@icc.ru
SPIN-code: 5344-2226

Avramenko Yuriy Vladimirovich
Office: Matrosov Institute for System Dynamics and Control Theory of Siberian Branch of Russian Academy of Sciences
Address: 664033, Russia, Irkutsk, Lermontov str., 134
Phone Office: (3952) 45-31-12
E-mail: avramenko@icc.ru

References:
[1] Terzopoulos, D., Platt, J., Barr, A., Fleischer, K. Elastically deformable models. Computer Graphics. 1987; 21(4):205–214.
[2] Williams, D.J., Shah, M. A fast algorithm for active contours and curvature estimation. CVGIP: Image Understanding. 1992; 55(1):14–26.
[3] Amini, A.A., Weymouth, T.E., Jain, R.C. Using dynamic programming for solving variational problems in vision. IEEE Trans Pattern Anal Machine Intell. 1990; 12(9):855–867.
[4] Ganebnykh, S.N., Lange, M.M., Stepanov, D.Yu. Metric classifier using multilevel network of templates. Pattern Recognition and Image Analysis. 2012; 22(2):265–277.
[5] Bell, B., Pau, L.F. Context knowledge and search in object-oriented Prolog-based image understanding. Pattern Recognition Letters. 1992; (13):276–290.
[6] Schockaert, S., De Cock, M., Kerre, E.E. Spatial reasoning in a fuzzy region connection calculus. Artificial Intelligence. 2009; 173(2):258–298.
[7] Munoz-Velasco, E., Burrieza, A., Ojeda-Aciego, M. A logic framework for reasoning with movement based on fuzzy qualitative representation. Fuzzy Sets and Systems. 2014; (242):114–131.
[8] Colmerauer, A. An introduction to Prolog III. Communications of the ACM. 1990; 33(7):69–90.
[9] Fedorov, R., Shigarov, A. Unification of the predicate line in the logic-syntactic recognition of raster images. Pattern Recognition and Image Analysis. 2011; 21(2):242–246.
[10] Fedorov, R., Shigarov, A., Ruzhnikov, G. Algorithm A* in logical-structure recognition of objects. Pattern Recognition and Image Analysis. 2013; 23(4):435–439.
[11] Hogger, GJ. Introduction to logic programming. San Diego, USA: Academic Press Professional; 1984: 278.
[12] Harris, C., Stephens, M. A combined corner and edge detector. 4th Alvey Vision Conference. United Kingdom: Plessey Research Roke Manor; 1988: 147–151.
[13] Ojala, T., Pietikinen, M., Harwood, D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognition. 1996; 29(1):51–59.
[14] Joachims, T. SVMlight support vector machine. Available at: http://svmlight.joachims.org (accessed 30.06.2015).
[15] GEOS geometry engine. Available at: http://trac.osgeo.org/geos (accessed 30.06.2015).

Bibliography link:
Bychkov I.V., Rugnikov G.M., Fedorov R.K., Avramenko Y.V. Interpreter of Spatial Object Query Language for raster image processing // Computational technologies. 2016. V. 21. ¹ 1. P. 49-59
Home| Scope| Editorial Board| Content| Search| Subscription| Rules| Contacts
ISSN 1560-7534
© 2024 FRC ICT