Matching and Retrieval System Based on Vocabulary and Grammar of Color PatternsThe ProblemMimicking Humans is a Tough Job!Our Approach - Vocabulary and GrammarOverview of the SystemSteps for Feature Extraction (Color Based)Steps for Feature Extraction (Texture Based)The DatabaseResults (Obvious Matches)Results (contd.) - Obvious MatchesResults contd. (Non Obvious Matches?)ReferencesMatching and Retrieval System Based on Vocabulary and Grammar of Color PatternsByPradeep C.VenkatSrinath SrinivasanThe ProblemTo design an intelligent perception based system for pattern matching and retrieval of patterns from a databaseSystem must retrieve the closest match(es) in terms of ‘similarity’ to a user-inputted query imageMatching must be done so as to emulate human perception to the extent possibleMimicking Humans is a Tough Job!How do humans judge ‘similarity’ of images?What factors would best characterize the subjective phenomenon of human perception?Can these factors be generalized over all kinds of images?Our Approach - Vocabulary and GrammarVocabulary: Four perceptual criteria (Mojsilovic, et al.) were identified for comparison of color patterns:Overall colorColor purityRegularity and PlacementDirectionalityoGrammar: A set of rules governing the use of these criteria in judging similarity of patternsOverview of the SystemEstimation of ColorDistributionGeneration ofPattern MapExtraction of TexturePrimitivesEstimation ofPrimitiveDistribution Image DecompositionSimilarity JudgmentImageDatabasequeryFeature ExtractionSimilarity MeasurementSteps for Feature Extraction (Color Based)The input image is transformed into the Lab Color Space for compact perceptually based color representationColor distribution is determined using a vector quantization approachSignificant features are determined from the histogramColor features are used in conjunction with an L2-norm distance measure to determine similaritySteps for Feature Extraction (Texture Based)Spatial smoothing to remove background noiseConstruction of the achromatic pattern map (APM)Construction of an edge map from the APMOrientation processing to extract the distribution of pattern contours along different spatial directionsComputation of scale-spatial texture edge distributionThe DatabaseOur database consisted of over 300 images of color patterns, sceneries, buildings, plants, etc.Results (Obvious Matches) QueryClosest MatchesResults (contd.) - Obvious MatchesQueryClosest MatchesResults contd. (Non Obvious Matches?)QueryClosest MatchesReferencesA. Mojsilovic, et. al, Matching and retrieval based on vocabulary and grammar of color patterns, IEEE Trans. Image Processing, vol. 9, no. 1 (Special issue on Digital Libraries), Jan. 2000, pp.38-54. A. Mojsilovic, et. al, The vocabulary and Grammar of Color Patterns, IEEE Trans. Image Processing, vol. 9, no. 3 (Special issue on Digital Libraries), Jan. 2000,
View Full Document