Vol. 22 (2013):
Abstracts and Contents of Papers
Machine GRAPHICS & VISION, Vol. 22 (2013), No. 1/4
Borusiewicz, A., Drożyner, P.:
Application of Shape Analysis to the Assessment of Geometrical Properties of Grains in the Selected Species of Spring Cereals
MGV vol. 22, no. 1/4, 2013, pp. 3-15.
The competition in many branches of industry including agriculture has grown as a result of Polish access to the European Union. It resulted in the intense research development in order to intensify production processes and improve the quality of the final product. One of the methods which might be helpful in this process is the shape analysis. This method makes it possible to measure selected properties of materials in a very precise way. The paper presents the possibilities of computer analysis in the research of grain geometrical features of 128 species of cereals. The program ImageJ was used. It enabled us to define surface, perimeter, width, height and circular projection of every caryopsis. Shape analysis also helps to define basic values of the tested features of caryopsis species. Significant differences between the shape of tested cereals species were indicated. However, significant differences between varieties of the same species were not found. Barley grain had the largest average surface while rye grain had the smallest one. Winter barley grain had the largest perimeter and spring wheat had the smallest one. Oat was characterized by the longest average length while spring wheat had the smallest one. Winter barley had the largest grain width and rye had the smallest one. Spring wheat grain is the most circular while oat grain is the less circular one.
Taking into consideration the data mentioned above, one can use them in the production of equipment and machines used for seed planting, selection, segregation of cereal seeds both in agriculture as well as in agricultural and food processing industry.
caryopsis, spring cereals, grain, shape analysis, geometrical features.
Chmielewski, L.J., Orłowski, A.:
Hough Transform for Lines with Slope Defined by a Pair of Co-primes
MGV vol. 22, no. 1/4, 2013, pp. 17-25.
Data structure and Hough-type algorithm suitable for finding the lines having the slope exactly specified by the ratio of small co-prime numbers is proposed. It is suitable for analysing images like the Ulam square in which the points representing prime numbers form such structures as contiguous lines and other regular sequences of points. This analysis is different from that in the case of images in which the real-world objects are represented approximately. Until now in the Ulam square the horizontal and vertical sequences, and those inclined by 45 deg were typically analysed. With the proposed method the sequences having slopes represented by such tangents like 1/3, 2/3, 3/4 etc. can be looked for.
Hough transform, slope, co-prime, coprime, prime, Ulam, square, spiral.
Kaczmarczyk, J., Pankiewicz, M.:
Color Transformation Method that Preserves the Impression of Texture in Virtual Makeover System
MGV vol. 22, no. 1/4, 2013, pp. 27-35.
The algorithms of color transformation that preserves the impression of texture are used in virtual makeover systems, where maintaining the impression of unaltered texture is important in the process of transforming the color. The content of this paper covers the process of implementing the algorithm of digital picture color transformation with its main objective - minimizing its influence on the texture structure. The main idea of the presented algorithm is to determine the area in HSV space that consists of the original picture pixels and then, to move it towards the target color in such a way that every color is moved by the same vector, limited only by the fact that the transformation is not always possible. The analysis of the algorithm was conducted based on fragments of real face photographs. Its results were compared on the basis of measures estimated on the run length matrix and the co-occurrence matrix.
color, texture, color transform, virtual makeover, digital image processing.