MATLAB Code Implementation for Image Processing
MATLAB image processing techniques covering histograms, image transforms, spatial filtering (image enhancement using templates), and edge detection operators with practical code implementations.
Image Transformation with DCT and IDCT Implementation
Image transformation techniques involving 8x8 block partitioning, Discrete Cosine Transform (DCT) for compression encoding, and Inverse DCT (IDCT) for decompression, with code implementation insights
Commonly Used Contrast Calculation Formulas in Image Processing with Code Implementation
Implementation of widely-used contrast calculation formulas in image processing, including a canvas expansion method for image transformation that requires minimal code modifications for practical application.
MATLAB Code for Shadow Detection Using Illumination-Invariant Transformation
Background: This shadow detection method was proposed by Mr. J.W. Hofstee and Mr. E.J. Hanten in their paper "Shadow Segmentation Based on Image Transformation for Illumination Changes" presented at the International Conference on Agricultural Engineering in Zurich (July 6-10). Key Technology: Implements shadow detection through illumination-invariant image transformation. The algorithm successfully detects shadows in certain images but shows varying performance across different image types, indicating potential areas for optimization in practical implementations.
Curvelet Transform-Based Image Processing with Threshold Reconstruction
Implementing curvelet transform on an image, visualizing its coefficient distribution, performing threshold-based reconstruction, and displaying the reconstructed image with MATLAB code implementation details.
Digital Image Processing Lab Manual and Reference Solutions
This Digital Image Processing Lab Manual and Reference Solutions from Central South University, entirely authored by myself, has been successfully tested and run on MATLAB 6.5. It covers essential topics including image transformation and frequency domain filtering, spatial domain image enhancement, image edge detection with reference images. Significantly superior to versions circulating online, this serves as foundational material for learning image processing with detailed algorithm implementations and function demonstrations.