Edge Detection and Geometric Feature Extraction of A Burner’s Jet in FNBZ Images Using Seeded Region Growing Algorithm

摘要: The method based jet trajectory is routinely used in a cold-state test of FNBZ (flow field near burner zone). However, the traditional measurement can not effectively obtain useful information from images. In this paper, approach computer-aided diagnosis image processing attempted. noisy nature images, as well varying intensity, edge feature and centerline location under different boiler loads, defeat most automatic detection algorithms, making difficult. This paper applies seeded region growing algorithm to images with manualed seed selection realizes semi-automated producing good performance tests. With high success rate over 90%, refinement scheme could be applicable tests tool aiding diagnosis, possible applications analysis flame for combusting condition.