AI Lesson 84 – Convolutions & Kernels | Dataplexa

AI Course

I. AI Foundations
1. Introduction to AI 2. History of AI 3. AI vs ML vs DL 4. Search Algorithms 5. Intelligent Agents 6. Informed & Uninformed Search 7. Constraint Satisfaction 8. Adversarial Search 9. Logic in AI 10. Planning in AI 11. Knowledge Representation 12. Probabilistic AI 13. Bayesian Networks 14. Markov Models 15. AI Ethics 16. AI Applications 17. Intro to PyTorch 18. Intro to TensorFlow 19. AI Workflows 20. Data for AI
II. Machine Learning
21. Introduction to ML 22. ML Workflow 23. Supervised Learning 24. Unsupervised Learning 25. Reinforcement Learning 26. Linear Regression 27. Logistic Regression 28. SVM 29. Decision Trees 30. Random Forest 31. Gradient Boosting 32. XGBoost 33. K-Means 34. Hierarchical Clustering 35. Dimensionality Reduction 36. Feature Engineering 37. Feature Selection 38. Model Evaluation 39. Overfitting vs Underfitting 40. Cross Validation
III. Deep Learning
41. Intro to Deep Learning 42. Neural Networks 43. Activation Functions 44. Backpropagation 45. Loss & Optimizers 46. Regularization 47. CNN Basics 48. CNN Architectures 49. RNN, LSTM, GRU 50. Seq2Seq 51. Transformers 52. Attention 53. Positional Encoding 54. Training DL 55. Hyperparameter Tuning 56. Transfer Learning 57. Autoencoders 58. GAN Basics 59. GAN Applications 60. Model Serving
IV. Natural Language Processing
61. Intro to NLP 62. Text Processing 63. Tokenization 64. Stopwords & Lemmatization 65. BoW & TF-IDF 66. Word Embeddings 67. Sentence Embeddings 68. NLP Classification 69. Sequence Modeling 70. RNN in NLP 71. Transformers in NLP 72. BERT Basics 73. BERT Fine-tuning 74. RoBERTa & DistilBERT 75. Sentiment Analysis 76. NER 77. Machine Translation 78. Text Generation 79. NLP Evaluation 80. NLP Use Cases
V. Computer Vision
81. Intro to CV 82. Image Processing 83. Filters & Edges 84. Convolutions 85. Object Detection 86. Object Tracking 87. Image Segmentation 88. Face Recognition 89. Feature Detection 90. OCR 91. Image Augmentation 92. Generative Vision 93. Vision Transformers 94. Multimodal Models 95. CV Use Cases
VI. LLM Engineering
96. Intro to LLMs 97. Tokenization 98. LLM Architecture 99. Pretraining 100. Fine-tuning 101. RLHF 102. Prompt Engineering 103. Embedding Models 104. Vector Databases 105. LLM Agents 106. Guardrails & Safety 107. AI in Production 108. End-to-End Project

Lesson 84: Convolutions & Kernels

Convolutions and kernels form the mathematical foundation of image filtering. Almost every image operation you have learned so far — blurring, sharpening, and edge detection — is powered by convolution.

Understanding this concept is critical because convolution is also the backbone of Convolutional Neural Networks (CNNs), which dominate computer vision today.

Real-World Connection

When your phone camera sharpens photos, when medical scans highlight tissues, or when self-driving cars identify road boundaries — convolution is working behind the scenes.

Instead of looking at the whole image at once, convolution processes images locally, one small region at a time.

What Is a Kernel?

A kernel (also called a filter or mask) is a small matrix of numbers that is applied to an image to extract specific features.

  • Kernels usually have sizes like 3×3, 5×5
  • Each kernel serves a purpose: blur, sharpen, detect edges
  • The kernel slides over the image pixel by pixel

What Is Convolution?

Convolution is the process of placing a kernel over a region of an image, multiplying corresponding values, summing them, and assigning the result to a new pixel.

This operation is repeated across the entire image to produce a transformed output.

Simple Convolution Example

Below is a basic example of applying a custom kernel to an image using OpenCV. 


import cv2
import numpy as np

image = cv2.imread("image.jpg", cv2.IMREAD_GRAYSCALE)

kernel = np.array([
    [0, -1, 0],
    [-1, 5, -1],
    [0, -1, 0]
])

convolved = cv2.filter2D(image, -1, kernel)

cv2.imshow("Original", image)
cv2.imshow("Convolved", convolved)
cv2.waitKey(0)
cv2.destroyAllWindows()

What This Code Is Doing

The kernel used above is a sharpening kernel. It emphasizes differences between neighboring pixels, making edges and details more visible.

The filter2D function slides the kernel over the image, performs convolution at each position, and generates a new image.

Understanding the Output

The output image appears sharper than the original. Fine details and boundaries become more visible because the kernel amplifies intensity changes.

Different kernels produce very different results even when applied to the same image.

Common Kernels and Their Purpose

  • Blur kernel: Smooths the image
  • Sharpen kernel: Enhances edges
  • Edge kernel: Detects boundaries

Why Convolution Matters in AI

In deep learning, convolution layers automatically learn kernels from data instead of manually defining them.

This allows models to detect edges, textures, shapes, and complex patterns efficiently.

Practice Questions

Practice 1: What is the small matrix used in convolution called?



Practice 2: What operation applies a kernel across an image?



Practice 3: What does convolution help extract from images?



Quick Quiz

Quiz 1: What is a common kernel size?





Quiz 2: Which OpenCV function applies convolution?





Quiz 3: Convolution is a core operation in which type of neural network?





Coming up next: Object Detection — how machines locate and identify objects inside images.

← Previous Course Index Next →