Visual inspection is widely used to improve the reliability of in-service products such as wind turbine blades (WTBs), aircraft surfaces, and bridges. Lowering costs by reducing maintenance hours and increasing labor safety, decreasing production and service downtimes, promoting high accuracy inspections as well as making early repair are motivating factors for having reliable visual inspection techniques. In this study, a new image processing technique was investigated to assess its ability to detect surface flaws on a WTB on-tower. The method was tested by varying the parameters of the surface flaws as well as the parameters of the method. It was found that detecting and quantifying cracks as small as hair thickness with computer-based visual inspection is feasible and the orientation of a crack was not sensitive to image processing so that the inspection camera does not need to set up at a specific angle to detect cracks. It was found that uneven background illumination was not a major concern for the edge detection methods and can be reduced by using optimized threshold number and opening images techniques with the line detection method. In addition, the accuracy of quantifying a crack was improved by reducing noise with the intersection two processed images from different methods.