Costin-Anton BOIANGIU, Andrei TIGORA
Abstract. This paper describes an image binarization method that applies localized Otsu thresholding to irregular regions of images, determined through watershed segmentation. Traditional localized binarization techniques work on square regions, which group together pixels of different origins. This is a problem, as there may not always be available a comparator for objects from different classes. In order to solve this problem, we use a method that first selects the objects (like shadow and light regions) and then performs binarization on each individual object in order to expose its characteristics. For more accurate results, an inter-scale segmentation and binarization method is proposed. Read the pdf
Yan ZHU, Renying CHANG
Abstract. The harmonic index H(G) of a graph G is defined as the sum of weights of all edges uv of G, where d(u) denotes the degree of a vertex u in G. In this paper, we first present a sharp lower bound on the harmonic index of unicyclic conjugated graphs (unicyclic graphs with a perfect matching). Also a sharp lower bound on the harmonic index of unicyclic graphs is given in terms of the order and given size of matching. Read the pdf.
Muzafer H. SARAČEVIĆ, Predrag S. STANIMIROVIĆ, Predrag V. KRTOLICA,
Abstract. In this paper we provide a new way for constructing and storing the convex polygon triangulations. The main motivation for the presented method is derived from two combinatorial problems: ballot problem and problem of lattice path. The method is derived upon the so-called movement through polygon. The movement is defined on ballot records and validity of the lattice path through the grid. We give two algorithms: Triangulation to ballot and Ballot to triangulation. Also, we give a method to make coding for a ballot record or the corresponding triangulation even more compact using a stack. All mentioned algorithms are implemented in the Java programming language. Read the pdf.
Broderick Crawford, Ricardo Soto, Miguel Olivares-Suárez,
Abstract. This work presents a study of a new binary coded firefly algorithm. The firefly algorithm is a novel nature-inspired metaheuristic, inspired by the social behavior of fireflies, which is being applied to solve many optimization problems. We test the proposed binary coded firefly algorithm solving the non-unicost set covering problem which is a well-known NP-hard discrete optimization problem with many practical applications. To tackle the mapping from a continuous search space to a discrete search space we use different transfer functions which are investigated in terms of convergence speed and accuracy of results. The experimental results show the effectiveness of our approach where the binary coded firefly algorithm produce competitive results solving a portfolio of set covering problems from the OR-Library. Read the pdf.
Andrei ALEXANDRU, Gabriel CIOBANU
Abstract. We provide a nominal semantics of the monadic version of the fusion calculus. A set of compact transition rules is presented in the Fraenkel-Mostowski framework by using a specific nominal quantifier. Using several nominal techniques, it is proved the equivalence between the new nominal semantics and the original semantics of the monadic fusion calculus. Read the pdf.
Ion CHIŢESCU, Anca PLĂVIŢU
Abstract. One considers a finite set X (the alphabet), the code space of all sequences formed with elements (letters) from the alphabet X and Bthe Borel sets of . A concrete representation of all Sugeno measures on Bis given. This representation is, heuristically speaking, matricial, being inspired by the concrete representation of all probabilities on B. Read the pdf.