Riverbed: A Novel User-Steered Image Segmentation Method Based on Optimum Boundary Tracking

This paper presents an optimum user-steered boundary tracking approach for image segmentation, which simulates the behavior of water flowing through a riverbed. The riverbed approach was devised using the image foresting transform with a never-exploited connectivity function. We analyze its properties in the derived image graphs and discuss its theoretical relation with other popular methods such as live wire and graph cuts. Several experiments show that riverbed can significantly reduce the number of user interactions (anchor points), as compared to live wire for objects with complex shapes. This paper also includes a discussion about how to combine different methods in order to take advantage of their complementary strengths.

OPTIMUM RATIO OF CALCIUM AND BORON IN THE NUTRIENT SOLUTION OR IN CASTOR BEAN SHOOT FOR FRUIT YIELD AND SEED OIL CONTENT

Calcium (Ca) and boron (B) have been reported as the major macro-and micronutrient required for castor bean plant yield. The objective of this study was to determine the Ca: B ratios (in the growth media and plant tissue) for fruit yield and shoot dry weight of the castor bean (Ricinus communis L.), grown in a nutrient solution, and to evaluate Ca and B supply on concentration and total uptake of Ca, potassium (K), magnesium (Mg), and B, as well on the seed oil content. The treatments were arranged in a 3 x 3 factorial fashion, consisting of three rates of Ca (40, 80, and 160 mg L-1) and three of B (0.32, 0.96, and 1.60 mg L-1). Calcium and B rates increased the shoot and root dry weight and fruit yield at a Ca: B ratio in the nutrient solution of 166 and 100, respectively. Symptoms of B deficiency were observed in plants supplied with 0.32 mg B L-1, regardless of the Ca concentration in the nutrient solution. Plants which showed visual symptoms of Ca deficiency cultivated with 40 mg Ca L-1 presented concentration of Ca in plant tissue up to 10 g kg(-1). The concentration and total Ca and B uptake increased with the rates of them. Notwithstanding, the shoot Ca accumulation was improved by B rates. In addition, there were no decreases in K and Mg uptake due to Ca rates. Furthermore, addition of 80 mg L-1 of Ca and 1.60 mg L-1 of B in the growth media increased the seed oil content. The Ca: B ratio in the diagnostic leaf associated with the highest plant dry weight (shoot and root) and fruit yield, was 500 (16 to 20 g kg(-1) of Ca, and for 30 to 40 mg kg(-1) of B).

EFFICIENT FAULT LOCATION IN UNDERGROUND DISTRIBUTION SYSTEMS THROUGH OPTIMUM-PATH FOREST

In this article we propose an efficient and accurate method for fault location in underground distribution systems by means of an Optimum-Path Forest (OPF) classifier. We applied the time domains reflectometry method for signal acquisition, which was further analyzed by OPF and several other well-known pattern recognition techniques. The results indicated that OPF and support vector machines outperformed artificial neural networks and a Bayesian classifier, but OPF was much more efficient than all classifiers for training, and the second fastest for classification.