视觉感知lab实验报告.doc

edge detector——实验报告
赵宏伟
1 实验要求
Load the three receptive fields , , and (corresponding to three different neurons), in addition to the edge images () and the Einstein image () from your emails.
(a) Plot the three different receptive fields side by side within the same figure using imagesc and subplot so you can see what they look like. Use the scaling option for imagesc to make sure that the grayscale for each is equivalent - ., so they are parable.
(b) Show what each of the edge images looks like in the same manner - ., by showing them side by side in the same figure using subplot. You should see that they are just edges at different positions and orientations.
(c) Now, for each of your neurons, compute the inner product between its receptive field and each of the edge images. Plot your results for each neuron as a bar plot, with the position of the edge on the x-axis of each barplot.
(d) Finally, for receptive fields DOG , Gaborh, Gaborv, show what it would look like to have an entire array of these neurons processing the Einstein image. You can do this by typing
        pim=conv2(einstein,DOG,’same’);
where pim is your result image.
Compare differences of the results from DOG , Gaborh and Gaborv.
2 实验环境
pc机:windows 7 ultimate X86
Matlab(2009a)
3 实验内容
A.
(1)结果图
图1
实验代码
load ;
load ;