During my university studies I worked at Adaptive Vision. It’s a Polish startup building software for camera-based industrial quality inspection: think cameras in factory lines detecting manufacturing defects. (Since then the startup got acquired and rebranded as Zebra Aurora Vision .)

I worked there for three years (2009–2012) and ended up becoming the engineering lead for the image recognition team. It was a fantastic adventure: we were working with real end-to-end systems, building solutions for real problems of our clients in factories around the world.

At the end of my time at Adaptive Vision I wrote a small book summarizing what I learned about the various image analysis techniques, based on 3 years of experience applying them to realistic industrial quality inspection problems.

The book is called “Image Analysis Techniques for Industrial Inspection Systems”. You can find it here , the LaTeX source code is on GitHub.

The company has been sending a printed copy to all customers who bought license for our software :). I don’t know if they still do.

Table of contents:

  1. Image Thresholding
    1. Introduction
    2. Global Thresholding
    3. Threshold Selection
    4. Dynamic Thresholding
  2. Blob Analysis
    1. Introduction
    2. Region
    3. Elementary Operators
    4. Mathematical Morphology
    5. Topology
    6. Features
    7. Examples
  3. 1D Edge Detection
    1. Introduction
    2. Profile Extraction
    3. Step Edges
    4. Ridges
    5. Stripes
    6. Examples
  4. 2D Edge Detection
    1. Introduction
    2. Image Gradient
    3. Canny Edge Detector
  5. Contour Analysis
    1. Introduction
    2. Path
    3. Segmentation
    4. Statistical Features
    5. Geometrical Features
  6. Shape Fitting
    1. Introduction
    2. Lines
    3. Circles
    4. Fitting Approximate Primitives to Images
    5. Examples
  7. Template Matching
    1. Introduction
    2. Brightness-Based Matching
    3. Edge-Based Matching
    4. Examples