In this paper, we present a new image segmentation algorithm which is based on local binary patterns (LBPs) and the combinatorial pyramid and which preserves structural correctness and image topology. For this purpose, we define a codification of LBPs using graph pyramids. Since the LBP code characterizes the topological category (local max, min, slope, saddle) of the gray level landscape around the center region, we use it to obtain a "minimal" image representation in terms of the topological characterization of a given 2D grayscale image. Based on this idea, we further describe our hierarchical texture aware image segmentation algorithm and compare its segmentation output and the "minimal" image representation. KeywordsLocal binary patterns • Irregular graph pyramid • Primal and dual graph • Topological characterization • Image segmentation Author was partially supported by IMUS and Spanish Ministry under grant MTM2015-67072-P (MINECO/FEDER, UE).

No abstract

No abstract

In undergraduate practical courses, it is common to work with groups of 100 or more students. These large-scale courses bring their own challenges. For example, course problems are too small and lack "the big picture"; grading becomes burdensome and repetitive for the teaching staff; and it is difficult to detect cheating. Based on their experience with a traditional large-scale practical course in image processing, the authors developed a novel course approach to teaching "Introduction to Digital Image Processing" (or EDBV, from the German course title Einführung in die Digitale Bild-Verarbeitung) for all undergraduate students of media informatics and visual computing and medical informatics at the TU Wien.

No abstract