Voting-based edge detection

The edge detection algorithms stand on convolving the input image with a filter for a specific direction. With the present scenario, no solution can grant the best output for various types of input image. Then, diverse algorithms have been implemented for a specific approach and have a good result only on a specific dataset and a selected filter. We can evaluate the behavior of an algorithm based on different types of images and in this way, we could choose the best candidate from all the results. The voting algorithm uses weighted, majority and unanimous votes. The general propose of this voting mechanism is to increase the accuracy of the output. This paper proposes a voting mechanism that chooses the best candidates from all available ones and selects the relevant result from a pool of intermediate outputs from well-known techniques.