View article

Machine vision requires detectors to obtain the characteristics and the nature of the object in the image. The Canny edge detection method is the most recognisable technique that combines a low-pass Gaussian filter to reduce noise and oppression instead of the maximum threshold and hysteresis for localisation advantages. One of the problems encountered in the Canny approach is in the selection of a threshold value. Using a single fixed threshold value for the maximum gradient is not the optimal choice. Therefore, the Canny approach uses two threshold values, a high threshold and a low threshold to reduce the number of false positive pixels, representing the contours in the image significantly. However, using two fixed threshold values is also not the best option because of the high variation in the image. Although adaptive thresholds have been introduced, they are only used for specific types of …