Iris Cracks Detection Method Based on Minimum Local Gray Value and Dilating Window of Regional Mean Gray Value

摘要

Iris crack has the characteristics of minimum local gray value and regional meoan gray value. Its gray value is lower than those of the surrounding area and from the edge to the inside the gray value is shown a trend of decline gradually. A method is proposed based on Minimum local Gray value and Dilating Window of Regional Mean Gray value. The initial starting point of the dilating window is determined by the minimum local gray value, and the dilating windows is configured with the regional mean gray value, and the areas of iris cracks will be found. Thirdly, the iris crack is segmented at the area according to minimum local gray value again. Finally, the result is found with the connection and de-noising. Compared method with single minimum local gray value method and Gaussian filter method, this method has low misdetection rate and simple threshold selection, and can meet the expected requirement.