Image FilteringQuestions about HW 1?Questions about class?Key ideas from last classLightness PerceptionLightness PerceptionSlide Number 7Slide Number 8Slide Number 9Today’s classColor spacesColor spaces: RGBColor spaces: HSVColor spaces: L*a*b*If you had to choose, would you rather go without luminance or chrominance?If you had to choose, would you rather go without luminance or chrominance?Most information in intensityMost information in intensityMost information in intensityThe raster image (pixel matrix)The raster image (pixel matrix)Image filteringSlide Number 24Slide Number 25Slide Number 26Slide Number 27Slide Number 28Slide Number 29Slide Number 30Slide Number 31Slide Number 32Practice with linear filtersPractice with linear filtersPractice with linear filtersPractice with linear filtersPractice with linear filtersPractice with linear filtersSharpeningOther filtersOther filtersFiltering vs. ConvolutionKey properties of linear filtersMore propertiesSlide Number 45Gaussian filtersSeparability of the Gaussian filterSeparability exampleSeparabilitySlide Number 50Slide Number 51Thinking in terms of frequencyThinking in terms of frequencySignals can be composedFourier TransformFourier Matlab demoSome practical mattersPractical mattersPractical mattersPractical mattersPractical mattersThings to rememberNext classQuestionsImage FilteringComputer VisionCS 543 / ECE 549 University of IllinoisDerek Hoiem02/02/10Questions about HW 1?Questions about class?• Room change starting thursday: Everitt 163, same timeKey ideas from last class• Lighting– Ambiguity between light source and albedo– Shading is a strong cue for shape– Interreflections, multiple sources, ambient light, etc. make lighting and shadows complicated• Color constancy– Color can be rebalanced by making assumptions (e.g., average pixel is gray)Lightness Perceptionfrom Ted AdelsonLightness Perceptionfrom Ted AdelsonBy nickwheeleroz, on FlickrBy nickwheeleroz, on FlickrKarsch et al. in reviewToday ’s class• How can we represent color?• What is image filtering and how do we do it?• What are some useful filters and what do they do?• What is linear separability?• Thinking in the frequency domainColor spaces• How can we represent color?http://en.wikipedia.org/wiki/File:RGB_illumination.jpgColor spaces: RGB0,1,00,0,11,0,0Image from: http://en.wikipedia.org/wiki/File:RGB_color_solid_cube.pngSome drawbacks• Strongly correlated channels• Non-perceptualColor spaces: HSVColor spaces: L*a*b*“Perceptually uniform” color spaceIf you had to choose, would you rather go without luminance or chrominance?If you had to choose, would you rather go without luminance or chrominance?Most information in intensityOnly color shown – constant intensityMost information in intensityOnly intensity shown – constant colorMost information in intensityOriginal imageThe raster image (pixel matrix)The raster image (pixel matrix)0.92 0.93 0.94 0.97 0.62 0.37 0.85 0.97 0.93 0.92 0.990.95 0.89 0.82 0.89 0.56 0.31 0.75 0.92 0.81 0.95 0.910.89 0.72 0.51 0.55 0.51 0.42 0.57 0.41 0.49 0.91 0.920.96 0.95 0.88 0.94 0.56 0.46 0.91 0.87 0.90 0.97 0.950.71 0.81 0.81 0.87 0.57 0.37 0.80 0.88 0.89 0.79 0.850.49 0.62 0.60 0.58 0.50 0.60 0.58 0.50 0.61 0.45 0.330.86 0.84 0.74 0.58 0.51 0.39 0.73 0.92 0.91 0.49 0.740.96 0.67 0.54 0.85 0.48 0.37 0.88 0.90 0.94 0.82 0.930.69 0.49 0.56 0.66 0.43 0.42 0.77 0.73 0.71 0.90 0.990.79 0.73 0.90 0.67 0.33 0.61 0.69 0.79 0.73 0.93 0.970.91 0.94 0.89 0.49 0.41 0.78 0.78 0.77 0.89 0.99 0.93Image filtering• Image filtering: compute function of local neighborhood at each position• Why bother?– Modify images• Denoise, resize, enhance contr ast, etc.– Extract information from images• Edge detection, matc hing, find distinctive points, etc.111111111Slide credit: David Lowe (UBC)],[g⋅⋅Example: box filter000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 000000000000090000000000000000000000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000Credit: S. Seitz],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000010000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅Credit: S. Seitz000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 0000000000000900000000000000000001020000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅Credit: S. Seitz000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 000000000000090000000000000000000102030000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅Credit: S. Seitz0 10203030000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 00000000000009000000000000000000],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅Credit: S. Seitz000000000000000000000 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 00 0 0 90 90 90 90 90 0 0000900909090000 0 0 90 90 90 90 90 0 000000000000090000000000000000000 102030303020100 204060606040200 306090909060300 305080809060300 305080809060300 2030505060402010 20 30 30 30 30 20 1010 10 10 0 0 0 0 0],[],[],[,lnkmglkfnmhlk++=∑[.,.]h[.,.]fImage filtering111111111],[g⋅⋅Credit: S. SeitzQ?What does it do?• Replaces each pixel with an average of its neighborhood• Achieve smoothing effect (remove sharp features)111111111Slide credit: David Lowe (UBC)],[g⋅⋅Box FilterSmoothing with box filterPractice with linear filters000010000Original?Source: D. LowePractice with linear