Image Enhancement by Modifying Gray Scale of Individual PixelsImage EnhancementGray-level TransformsImage NegativesLog Gray-level TransformPower Law Gray-level TransformPiece-wise Linear Gray-level TransformContrast StretchingGray-level SlicingBit-SlicingHistogram ProcessingHistogram EqualizationHistogram MatchingIndirect MethodHistogram Matching ExampleHistogram for Local EnhancementImage subtractionImage Averaging© 2002-2003 by Yu Hen Hu1ECE533 Digital Image ProcessingImage Enhancement by Modifying Gray Scale of Individual Pixels© 2002-2003 by Yu Hen Hu2ECE533 Digital Image ProcessingImage EnhancementGoal: to modify an image so that its utilization on a particular application is enhanced.A set of ad hoc tools applicable based on viewer’s specific needs. No general theory on image enhancement exists.Methods:»Spatial domain–Pixel processingGray level transformation: Data independenthistogram processing: Data-dependentArithmetic ops–Spatial filtering »Frequency domain filtering© 2002-2003 by Yu Hen Hu3ECE533 Digital Image ProcessingGray-level TransformsOperated on individual pixel’s intensity values: s = T(r). r: original intensity, s: new intensityData independent pixel-based enhancement method.Approaches»Image negatives»Log transform»Power law transform»Piece-wise linear transform© 2002-2003 by Yu Hen Hu4ECE533 Digital Image ProcessingImage Negativess = T(r) = L1rSimilar to photo negatives.Suitable for enhancing white or gray details in dark background.© 2002-2003 by Yu Hen Hu5ECE533 Digital Image ProcessingLog Gray-level Transforms = T(r) = c log(1+r)expand dark value to enhance details of dark area© 2002-2003 by Yu Hen Hu6ECE533 Digital Image ProcessingPower Law Gray-level Transforms = T(r) = c sGamma correction: to compensate the built-in power law compression due to display characteristics.© 2002-2003 by Yu Hen Hu7ECE533 Digital Image ProcessingPiece-wise Linear Gray-level TransformAllow more control on the complexity of T(r). »Contrast stretching»Gray-level slicing»Bit-plane slicing© 2002-2003 by Yu Hen Hu8ECE533 Digital Image ProcessingContrast Stretching© 2002-2003 by Yu Hen Hu9ECE533 Digital Image ProcessingGray-level Slicing© 2002-2003 by Yu Hen Hu10ECE533 Digital Image ProcessingBit-Slicing© 2002-2003 by Yu Hen Hu11ECE533 Digital Image ProcessingHistogram ProcessingData-dependent pixel-based image enhancement method.Histogram = PDF of image pixels.»Assumption: each image pixel is drawn from the same PDF independently (i.i.d.)»Several effects of histograms are shown at the right side.© 2002-2003 by Yu Hen Hu12ECE533 Digital Image ProcessingHistogram EqualizationA gray-level transformation method that forces the transformed gray level to spread over the entire intensity range.»Fully automatic, »Data dependent,»(usually) Contrast enhancedUsually, the discrete-valued histogram equalization algorithm does not yield exact uniform distribution of histogram.In practice, one may prefer “histogram specification”.10,1)()()(0sspdwwprTssrwr© 2002-2003 by Yu Hen Hu13ECE533 Digital Image ProcessingHistogram MatchingTransform pdf of r to a desired pdf ps(s).A generalization of histogram equalization. Basic idea: Given pr(r) and desired pdf pz(z), find a transform z = T(r), such that P(Z ≤ z) = P(R ≤ r).© 2002-2003 by Yu Hen Hu14ECE533 Digital Image ProcessingIndirect MethodIndirect approach:»First equalize the histogram using transform s = T(r).»Equalize the desired histogram v = G(z).»Set v = s to obtain the composite transform))((1rTGzFig. 3.19© 2002-2003 by Yu Hen Hu15ECE533 Digital Image ProcessingHistogram Matching Example© 2002-2003 by Yu Hen Hu16ECE533 Digital Image ProcessingHistogram for Local Enhancement© 2002-2003 by Yu Hen Hu17ECE533 Digital Image ProcessingImage subtractionMask mode radiography© 2002-2003 by Yu Hen Hu18ECE533 Digital Image ProcessingImage AveragingSame signal, but different noise realization.Averaging of many such images will enhance
View Full Document