Fast Level Set Algorithm for Extraction and Evaluation of Weld Defects in Radiographic Images

Optical Fiber Splicing Defect Segmentation Using Hybrid Active Contour

“…It had been known that region-based Active Contours using local image statistics can deal effectively with highlight or intensity inhomogeneity problem, but they are found to act locally and to be easy to trap into local minima. To overcome these problems, the authors proposed in [18] a model that combines an optimized Laplacian of Gaussian (LoG) term which can smooth the homogeneous regions and enhance edge information and the Region-Scalable Fitting (RSF) term proposed in [13] which make use of local region information to drive the curve towards the boundaries. The total energy function can be defined as:…”

“…where Ф is the level set function, f1 , f2 are the interior, exterior local means, respectively giving in (9) and E RSF (Ф, f1 , f2) is the RSF energy defined in [13] as:…”

“…Using the steepest descent method to minimize the above energy functional in (7), the following gradient flow equation can be obtained: (13) where e1(x) and e2(x) are defined as follow [18]: y y d x f y I y x K x e and d x f y I y x K x e   (14) Combining edge and local region information improves the performance of active contour model, however the core element of edge information (i.e. the edge indicator function g(∇I)) has two major drawbacks: In practice, the discrete gradients are bounded and then, the function g can be relatively far from zero on the edges and the curve may pass through the boundaries.…”

“…Active Contours [9][10][11][12][13][14][15][16][17][18] are the most popular techniques in this category where the idea is to drive an initial curve inside the image domain to be segmented to reach the boundaries of the objects of interest by minimizing energy where the curve is the argument of this energy [19]. Generally, active contours can be classified into edge-based models relying on contour information [9][10][11], region based models relying either on global or local image statistics [12][13][14][15] and hybrid models combining all information [16][17][18]. Over the past few years, modern approaches based on convolutional neural networks (CNNs) [20][21][22] have yielded a new generation of image segmentation models with remarkable performance improvements.…”