Analysis of the Performance of Various Edge Detection Techniques in Detecting Prominent Edges in Plant-based Images

Conference: Recent Trends in Information Processing, Computing, Electrical and Electronics
Author(s): Radhika Kamath, Mamatha Balachandra, Srikanth Prabhu Year: 2017
Grenze ID: 02.IPCEE.2017.1.509 Page: 486-494

Abstract

Edge detection is a process of detecting the sharp intensity discontinuity in digital images. More commonly these\ndiscontinuities are found on the boundary of the objects in images. So edge detection is the significant step in identifying the\nobjects in the digital images or in segmenting the image. Edge detection in digital image processing is achieved by\nconvolving a 2-D image with a spatial filter which may be based on first order or second order derivatives. There are many\nclassic edge detecting operators like Canny, Sobel, Roberts, Prewitts..etc. The goal of this paper is to analyze the\nperformance of various edge detecting techniques in detecting prominent edges in plant-based images with the intention of\ngetting clear boundaries of the leaves. That is, in this case we are interested only detecting the prominent edges which form\nthe boundaries of the leaves. Many plant-based images particularly agricultural images consists lots of overlapping. These\noverlapping may be complete or partial. For instance, the leaves of crop may be partially overlapped on the weed plant or\nweed leaves. So applying edge techniques on these images and analyzing their performance gives us good understanding of\nthese edge detecting techniques and how well these techniques can be used as initial processing steps in computer vision\nsystem in segmenting the weeds among crops.

<< BACK

IPCEE - 2017