Identifying the edges of digital images is an important step towards identifying human organs objects, such as skeletons of bone. Usually, once a bone fracture image is obtained, various algorithms are used to extract useful information. This information is particularly useful for identifying tumor boundaries for planning operations, etc. There are many edge detection algorithms based purely on the differential operators, such as Canny Operator, Robert operator, Sobel operator, Prewitt operator, etc. These operators are simple, easy to implement, and have a good execution time. On the other hand, they are sensitive to noise; thus, edge detection accuracy should be improved. Canny operator represents the improvement of the traditional single threshold method, in which the high and low threshold is selected according to the gradient of the image histogram.
展开▼