╔═══════════════════════════════════════════════════════════════════════════════╗
║                    CSC566 IMAGE PROCESSING - QUICK STUDY CHECKLIST            ║
╚═══════════════════════════════════════════════════════════════════════════════╝

📚 LAB 1: HISTOGRAM EQUALIZATION & IMAGE ENHANCEMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ Can you list the 4 steps of histogram equalization from memory?
  1. Calculate histogram of original image
  2. Calculate cumulative distribution function (CDF)
  3. Normalize CDF to [0, 255]
  4. Map each pixel to new intensity value

□ Mnemonic: "H.C.C.M" - "Have Calm Careful Meditation"

□ Can you explain what histogram equalization does to an image?
   Answer: Redistributes pixel intensities to enhance contrast

□ Can you explain histogram matching?
   Answer: Modifies image to match a specified histogram


📚 LAB 2: NOISE & SPATIAL FILTERING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ Types of Noise:
   • Gaussian Noise - Statistical noise with bell-shaped distribution
   • Salt & Pepper Noise - Random white/black pixels

□ Filter Selection:
   • Salt & Pepper → Median Filter (non-linear, removes outliers)
   • Gaussian Noise → Mean or Gaussian Filter (linear, averages)
   • For Edges → Sobel/Prewitt (first-order derivative)

□ Edge Detection Operators:
   • Sobel: Detects vertical and horizontal edges
   • Prewitt: Similar to Sobel, different weights
   • Laplacian: Second-order derivative, sensitive to details

□ Mnemonic: "S.A.G.E" - "Salt, Add Gaussian, Edges"


📚 LAB 3: FREQUENCY DOMAIN FILTERING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ What is Fourier Transform?
   Answer: Converts image from spatial to frequency domain

□ Frequency Basics:
   • High Frequency = Fine details, edges, noise
   • Low Frequency = Smooth areas, background

□ Filter Effects:
   • Low-Pass Filter: Removes HIGH frequencies → Smooths/blurs image
   • High-Pass Filter: Removes LOW frequencies → Sharpens/enhances edges
   • Notch Filter: Removes specific frequency components (periodic noise)

□ Mnemonic: "Lo-FI Smooths, Hi-FI Sharpens"
□ Mnemonic: "LPF removes the HIGHs, HPF removes the LOWs"


📚 LAB 4: IMAGE SEGMENTATION
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ Thresholding Types:
   • Global: Single threshold for entire image
   • Local (Adaptive): Different threshold for different regions
   • Otsu's Method: Automatically finds optimal threshold

□ When to Use Each:
   • Simple image → Global Thresholding
   • Varying illumination → Adaptive (Local) Thresholding
   • Let computer decide → Otsu's Method

□ Other Methods:
   • Region Growing: Seeds grow based on similarity criteria
   • K-Means Clustering: Partitions image into K clusters

□ Mnemonic: "T.O.R.K" - "Threshold, Otsu, Region, K-means"


📐 KEY FORMULAS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ Histogram Equalization:
   T(v) = round((CDF(v) - CDF_min) / (M×N - CDF_min)) × (L-1)

□ Convolution:
   g(x,y) = Σ Σ f(m,n) × h(x-m,y-n)

□ Sobel Operators:
   Gx = [-1 0 1; -2 0 2; -1 0 1]
   Gy = [-1 -2 -1; 0 0 0; 1 2 1]
   Magnitude = √(Gx² + Gy²)

□ Fourier Transform:
   F(u,v) = Σ Σ f(x,y) × e^(-j2π(ux/M + vy/N))


🎯 TEST DAY ESSENTIALS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ Can you identify noise type from description?
□ Can you choose the correct filter for given scenario?
□ Can you explain the visual effect of each operation?
□ Do you know when to use spatial vs frequency domain?
□ Can you describe histogram equalization step-by-step?
□ Do you understand first-order vs second-order derivatives?
□ Can you explain thresholding vs clustering segmentation?
□ Do you remember the key operators and their purposes?


💡 FINAL REVIEW TIPS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
1. Use the website's flashcard feature - it has 10 essential questions
2. Review the cheat sheet section multiple times
3. Practice identifying which technique to use in scenarios
4. Review formulas, especially histogram equalization and convolution
5. Understand WHY each technique is used, not just HOW


✅ CONFIDENCE CHECK - Can you answer these?
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
□ If an image has salt & pepper noise, which filter do you use and why?
□ What happens to an image when you apply a low-pass filter?
□ What are the 4 steps of histogram equalization?
□ When would you use adaptive thresholding instead of global?
□ What's the difference between Sobel and Laplacian operators?
□ What does a high-pass filter do to an image?
□ How does K-means clustering segment an image?
□ What is Otsu's method and when is it useful?


🎓 REMEMBER: Understanding > Memorization
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Good luck on your test! You've got this! 📚✨

╔═══════════════════════════════════════════════════════════════════════════════╗
║  Open index.html in your browser to access the full interactive study guide  ║
╚═══════════════════════════════════════════════════════════════════════════════╝