This work proposes an algorithm for scalpel region detection using color segmentation and edge detection. The input images are obtained with a fixed camera that has a line of view perpendicular to the scalpel plane. Three squares of red, green and blue colors were added to the scalpel in order to serve as fiducials. For the detection of those marks, the use of two methods was evaluated: One based on the application of thresholds to the color components, and the other based on the use of a fuzzy rule machine. The experimentation shows that both approaches provide similar results. Some morphological operations are then applied in order to detect the scalpel region. The algorithm was successfully tested in several cases, and some examples of the results are presented and analyzed.