[MGV logo]   Vol. 27 (2018):
  Abstracts and Contents of Papers


26 (2017) main 28 (2019)

No. 1/4.


Machine GRAPHICS & VISION, Vol. 27 (2018), No. 1/4

Flasiński M.:
Interpreted Graphs and ETPR(k) Graph Grammar Parsing for Syntactic Pattern Recognition
MGV vol. 27, no. 1/4, 2018, pp. 3-19.
Further results of research into graph grammar parsing for syntactic pattern recognition (Pattern Recognit. 21:623-629, 1988; 23:765-774, 1990; 24:1223-1224, 1991; 26:1-16, 1993; 43:249-2264, 2010; Comput. Vision Graph. Image Process. 47:1-21, 1989; Fundam. Inform. 80:379-413, 2007; Theoret. Comp. Sci. 201:189-231, 1998) are presented in the paper. The notion of interpreted graphs based on Tarski's model theory is introduced. The bottom-up parsing algorithm for ETPR(k) graph grammars is defined.
Key words: syntactic pattern recognition, graph grammar, parsing, interpreted graph, model theory.

Gong S., Newman T. S.:
Isocontouring with Sharp Corner Features
MGV vol. 27, no. 1/4, 2018, pp. 21-46.
A method that achieves closed boundary finding in images (including slice images) with sub-pixel precision while enabling expression of sharp corners in that boundary is described. The method is a new extension to the well-known Marching Squares (MS) 2D isocontouring method that recovers sharp corner features that MS usually recovers as chamfered. The method has two major components: (1) detection of areas in the input image likely to contain sharp corner features, and (2) examination of image locations directly adjacent to the area with likely corners. Results of applying the new method, as well as its performance analysis, are also shown.
Key words: marching squares, feature preservation, corner recovery, contour finding, isocontours.

Bohush R., Yarashevich P., Ablameyko S., Kalganova T.:
Extraction of Image Parking Spaces in Intelligent Video Surveillance Systems
MGV vol. 27, no. 1/4, 2018, pp. 47-62.
This paper discusses the algorithmic framework for image parking lot localization and classification for the video intelligent parking system. Perspective transformation, adaptive Otsu's binarization, mathematical morphology operations, representation of horizontal lines as vectors, creating and filtering vertical lines, and parking space coordinates determination are used for the localization of parking spaces in a video frame. The algorithm for classification of parking spaces is based on the Histogram of Oriented Descriptors (HOG) and the Support Vector Machine (SVM) classifier. Parking lot descriptors are extracted based on HOG. The overall algorithmic framework consists of the following steps: vertical and horizontal gradient calculation for the image of the parking lot, gradient module vector and orientation calculation, power gradient accumulation in accordance with cell orientations, blocking of cells, second norm calculations, and normalization of cell orientation in blocks. The parameters of the descriptor have been optimized experimentally. The results demonstrate the improved classification accuracy over the class of similar algorithms and the proposed framework performs the best among the algorithms proposed earlier to solve the parking recognition problem.
Key words: parking space, localization, Histogram of Oriented Descriptors, classification, Support Vector Machine.

 


26 (2017) main 28 (2019)

Last updated August 20, 2019