190 likes | 232 Vues
Learn about the properties of the visual pathway mapping, including hypercolumns, hyperfields, orientation selectivity, and edge detection in machines using different algorithms such as Roberts and Sobel. Discover how intensity gradients and noise removal play a crucial role in image processing.
E N D
Edge Detection Lecture 2: Edge Detection Jeremy Wyatt
The striate cortex Eye-cortex mapping has certain properties • Neighbouring areas in the retina are approximately mapped to neighbouring areas in the cortex • Half the image in each half of the cortex • Middle of retinal image on the outer edge of the relevant half of the cortex • Mapping is spatial distorted
Hypercolumns & Hyperfields 0.5-1mm • Each hypercolumn processes information about one area of the retina, its hyperfield. • 400-600 columns in each hypercolumn. • Each column has its own receptive field. • All the cells in one column are excited by line stimuli of the same orientation. Surface 3-4mm Column
Cells within a column • Light on the right and dark on the left of this cell causes excitation • The less the contrast the lower the excitation • Different cells in a single column respond to different patterns with the same orientation
Orientation across columns • Different columns are tuned to different orientations • Adjacent columns are tuned to similar orientations • Cells can be excited to different degrees Less excited More excited
Slabs and Hyperfields • Each hypercolumn is composed of about 20 slabs of columns • Each slab is tuned to one orientation • Each column in a slab is centred on a different portion of the hyperfield • But each column takes input from the whole hyperfield Slabs Columns in each slab
Learning • We learn the orientation selectivity of cells in the early months of life • This has been shown by depriving animals of certain orientations of input Sole visual input Orientations present in cortex
Edge detection in machines • How can we extract edges from images? • Edge detection is finding significant intensity changes in the image
Images and intensity gradients • The image is a function mapping coordinates to intensity • The gradient of the intensity is a vector • We can think of the gradient as having an x and a y component direction magnitude a
Approximating the gradient • Our image is discrete with pixels indexed by i and j • We want and to be estimated in the same place i i+1 j j+1
Approximating the gradient • So we use 2x2 masks instead • For each mask of weights you multiply the corresponding pixel by the weight and sum over all pixels i i+1 j j+1
Other edge detectors • Roberts • Sobel
Convolution mask • This process is very general image
What do these do? Original After Sobel Gx Threshold =30 Threshold=100 After Roberts Threshold=5 Threshold=20
Noise • It turns out we will need to remove noise • There are many noise filters • We can implement most of them using the idea of convolution again • e.g. Mean filter
Reading • RC Jain, Chapter 5, Edge Detection