This preview shows pages 1–9. Sign up to view the full content.

1 Advanced Features Jana Kosecka Slides from: S. Thurn, D. Lowe, Forsyth and Ponce CS223b 2 Advanced Features: Topics Template matching SIFT features Haar features

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
2 3 Features for Object Detection/Recognition Want to find … in here 4 Template Convolution Pick a template - rectangular/square region of an image Goal - find it in the same image/images of the same scene from Different viewpoint
3 5 Convolution with Templates % read image im = imread('bridge.jpg'); bw = double(im(:,:,1)) ./ 255; imshow(bw) % apply FFT FFTim = fft2(bw); bw2 = real(ifft2(FFTim)); imshow(bw2) % define a kernel kernel=zeros(size(bw)); kernel(1, 1) = 1; kernel(1, 2) = -1; FFTkernel = fft2(kernel); % apply the kernel and check out the result FFTresult = FFTim .* FFTkernel; result = real(ifft2(FFTresult)); imshow(result) % select an image patch patch = bw(221:240,351:370); imshow(patch) patch = patch - (sum(sum(patch)) / size(patch,1) / size(patch, 2)); 6 Template Convolution

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
4 7 Given a template - find the region in the image with the highest matching score Matching score - result of convolution is maximal (or use SSD, SAD, NSS similarity measures) Given rotated, scaled, perspectively distorted version of the image Can we find the same patch (we want invariance!) Scaling Rotation Illumination Perspective Projection Feature Matching with templates 8 Given a template - find the region in the image with the highest matching score Matching score - result of convolution is maximal (or use SSD, SAD, NSS similarity measures) Given rotated, scaled, perspectively distorted version of the image Can we find the same patch (we want invariance!) Scaling - NO Rotation - NO Illumination - depends Perspective Projection - NO Feature Matching with templates
5 9 Scale Invariance: Image Pyramid 10 Aliasing Effects Constructing a pyramid by taking every second pixel leads to layers that badly misrepresent the top layer Slide credit: Gary Bradski

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
6 11 “Drop” vs “Smooth and Drop” Drop every second pixel Smooth and Drop every second pixel Aliasing problems 12 Improved Invariance Handling Want to find … in here
7 13 SIFT Features Invariances: Scaling Rotation Illumination Deformation Provides Good localization Yes Not really 14 SIFT Reference Distinctive image features from scale-invariant keypoints. David G. Lowe, International Journal of Computer Vision, 60, 2 (2004), pp. 91-110. SIFT = Scale Invariant Feature Transform

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
8 15 Invariant Local Features Image content is transformed into local feature coordinates that are invariant to translation, rotation, scale, and other imaging parameters SIFT Features 16 Advantages of invariant local features Locality: features are local, so robust to occlusion and clutter (no prior segmentation)
This is the end of the preview. Sign up to access the rest of the document.