Measuring empirical discrepancy in image segmentation results


A methodology for comparison of boundary and segmentation images based on Precision??Recall graphs is presented in this study. The proposed methodology compares the location of edge pixels between an image under test and an ideal reference, in order to obtain a precise normalised similarity measure. This approach also deals with the case when multiple references are available using a merging procedure. Small displacement errors in edge pixel location are handled using a tolerance radius, which introduces the problem of multiple matching between test and reference edge pixels. This problem is addressed as a bipartite graph, solved by using the Hopcroft??Karp algorithm to obtain the maximum number of unique matchings. Experiments have been carried out in order to determine the performance of this evaluation approach.

Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here

PROJECT TITLE : On the Security of Key Extraction From Measuring Physical Quantities - 2016 ABSTRACT: Key extraction via measuring a physical quantity could be a category of information theoretic key exchange protocols
PROJECT TITLE : Measuring Improvement When Using HUB Formats to Implement Floating-Point Systems Under Round-to-Nearest - 2016 ABSTRACT: This paper analyzes the advantages of using half-unit-biased (HUB) formats to implement
PROJECT TITLE :Putting a Number on Pain: Technology Has an Increased Role in Measuring Subjective Symptoms in Clinical TrialsABSTRACT:WiFi and cellular networks are pervasively provided for mobile Web access. Though most existing
PROJECT TITLE :Heterodyne System for Measuring Frequency Response of Photodetectors in Ultrasonic ApplicationsABSTRACT:The heterodyne interferometer using acousto-optic modulation is presented to live the frequency response of
PROJECT TITLE :Modeling, Measuring, and Compensating Color Weak VisionABSTRACT:We tend to use strategies from Riemann geometry to investigate transformations between the colour spaces of color-normal and color-weak observers.

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry