Digital Image Processing \u2013 II Detailed Syllabus for Geo-Informatics and Surveying Technology M.Tech first year second sem is covered here. This gives the details about credits, number of hours and other details along with reference books for the course.<\/p>\n
The detailed syllabus for Digital Image Processing \u2013 II M.Tech 2017-2018 (R17) first year second sem is as follows.<\/p>\n
M.Tech. I Year II Sem.<\/p>\n
Course Objective:<\/strong> to understand the advance image enhancement, analysis and management techniques<\/p>\n Course Outcome:<\/strong> At the end of the course the student will able to classify the processed remote sensing data, apply the advanced processing methods for deriving the useful information and Classify, and analyze Hyper spectral data<\/p>\n UNIT- I: Image Resolution:<\/strong> Correction and calibrations- Noise Reduction \u2013 Global, Local and Periodic, radiometric calibrations, Senor Calibrations, Atmospheric Correction, Topographic Correction.<\/p>\n UNIT- II: Advance Enhancement:<\/strong> Advanced Enhancement Techniques. PCA, Tasseled Cap Transformation, MNF Transformation, Independent Component Analysis. Color Transformation \u2013 RGB to IHS, Natural Color Transformation. Data Fusion Techniques: IHS, Multiplicative, Brovey and Wavelet Based Transformation.<\/p>\n UNIT- III: Image Compression Techniques:<\/strong> Data compression: Methods- lossless & Lossy \u2013TechniquesDFT, wavelet, JPEG, Cosine transformations.<\/p>\n UNIT- IV: Classifications:<\/strong> Parametric & Non Parametric- Training sets Statistics, Minimum distance to mean, Maximum Likelihood, ANN, Weight Vector, Support Vector Machine, Decision Tree Approach, Concepts of hierarchical decision tree for Multi Temporal data, GLCM & Texture based classifiers. Sub pixel classifiers: Fuzzy Classification. K Mean, ISO Data, Fuzzy K Means, Fuzzy ML Classifiers, Expert and Artificial Intelligence Based Systems, Mathematical Morphology.<\/p>\n UNIT- V: Hyper Spectral Image & Change Detection Analysis:<\/strong> Data Visualization, Dimensional Reduction, Feature Extraction \u2013 Characteristic, Pixel Purity Index, Hyper Spectral Mapping Methods: – SAM, Spectral Feature Filtering, Spectral Unmixing. Change Detection: Nature of Change Detection, Introduction to Change Detection algorithms. Post Classification- Comparison, Ratioing, Vegetative Indices, Change Vector Analysis.<\/p>\n TEXT BOOKS:<\/strong><\/p>\n REFERENCES:<\/strong><\/p>\n\n
\n