Combination of Sobel+Prewitt Edge Detection Method with Roberts+Canny on Passion Flower Image Identification

Abstract Edge detection is at the forefront of image processing for object detection, so a good understanding edge algorithms essential. This paper aims to analyze ability combined methods identify images, through comparison two different methods, namely combination Sobel and Prewitt (Sobel+Prewitt) with Roberts Canny (Roberts+Canny). The analysis process uses dataset Passion Flower Images obtained from United States Department Agriculture (USDA) Plant Database, Natural Resources Conservation Service (NRCS). Image was using Nikon Coolpix 995 camera, JPG format resolution 128×192 pixels. Based on testing, results research technique resulted in better identification accuracy compared Prewitt. average 92.84% versus 68.75%.