Skills & Algorithmic Capability

Module 1: Intensity Transformations

Negative Transform: Implementing s = L - 1 - r [3].
Gamma Correction: Implementing s = c \cdot r^\gamma for monitor correction or detail expansion [4, 14].
Piecewise-Linear: Contrast stretching and bit-plane slicing to isolate image details [15, 16].

Global Equalization: Spreading intensity distributions using Cumulative Distribution Functions (CDF) [5, 17].
Local Enhancement: Computing histograms over sliding n \times n neighborhoods to reveal obscured small-area details [6, 18].

Smoothing (Low-pass): Box filters, weighted averages, and Median Filters for Salt-and-Pepper noise reduction [7, 9, 10, 19].
Sharpening (High-pass):
- Laplacian: Using second-order derivatives to highlight fine detail [14, 20, 21].
- High-boost Filtering: Combining original images with unsharp masks using an amplification factor A [13, 20].
- Gradient Operators: Implementing Sobel and Roberts masks for edge detection [22-24].

Backend: Building REST APIs with Django/OpenCV.
Frontend: Creating interactive UI with React, Tailwind CSS, and synchronized zoom viewports.
Task Management: Offloading heavy 35 \times 35 mask operations to Celery workers [9].