Skip to main content

Start Here

NOCTVISION has a growing set of articles on lenses, lighting, cameras, decision algorithms and edge AI. This page suggests where to begin if you are new here. Each stage is chosen to build on the calculations of the one before.

Where to Start

If you are new to machine vision

Reading from stage 1 in order connects, by calculation, why lenses and lighting come first.

If you need to put vision into equipment

Starting with the spec, installation space and lighting choice cuts redesign during commissioning.

If you follow the industry

Start with which vision methods are used where, and how to read the numbers behind new technologies.

Reading Order by Stage

Stage 1 · Basics of Light and Lenses

  1. Machine-Vision Inspection: Physics Comes Before Software
    Why light, contrast and resolution are settled before choosing a camera
  2. How to Calculate Machine-Vision Lens Focal Length
    The basic formula for focal length from FOV, WD and sensor size
  3. Machine Vision Lens Calculator — Catching the FOV Error the Shortcut Formula Hides, Plus Depth of Field and Diffraction in One Pass
    Where the shortcut formula breaks at higher magnification, plus depth of field and diffraction
  4. Vision Types Split First by Wavelength and Pixel Size
    Several vision methods compared at a glance by wavelength and pixel size

Stage 2 · Choosing the Lighting

  1. Six Machine-Vision Lighting Methods and How to Choose
    How six lighting methods work and the order for choosing
  2. How to Handle Imaging on Highly Reflective Surfaces
    Methods for imaging highly reflective surfaces
  3. Scratches on Highly Reflective Metal: Choosing the Lighting First — A Selection Map for Coaxial, Dome, Dark-Field, Cross-Polarization and HDR
    A map for choosing lighting by surface type
  4. Specular Reflection Erases Defects: How Cross-Polarization Catches Missed Detections on Highly Reflective Surfaces
    Suppressing specular reflection with cross-polarization

Stage 3 · Cameras and Sensors

  1. How Much Closer Does a CIS Sit Than a Line Scan Camera?
    How CIS, line-scan, area-scan and smart cameras differ
  2. A Board at 0.5 m/s Leans 15 mm Under a Rolling Shutter
    How shutter type and color layout affect moving targets
  3. The Line-Scan Camera You Picked by Line Rate Alone — Why It Still Misses Defects: TDI and the Resolution Design Relationship
    Line rate and TDI in line-scan cameras
  4. Camera Interface Bandwidth Determines Resolution — From GigE Vision to CoaXPress 2.0
    Where camera interface bandwidth caps resolution

Stage 4 · Decision Algorithms

  1. Deep Learning vs. Rule-Based Algorithms: When to Use Which
    The conditions that suit deep learning and rule-based methods
  2. Overdetection vs. Missed Detection — Which One Costs More?
    Comparing overdetection and missed detection by cost
  3. When the Light Dims by 5 %, How Many Good Pixels Turn Into Defects?
    Why anomaly-detection decisions waver when the light dims slightly
  4. Building a Vision Inspection App with PySide6 and OpenCV — A Minimal UI for Tuning Defect Detection Parameters on Screen (Full Code)
    Full code for an inspection app that tunes parameters on screen

Stage 5 · Edge AI

  1. Four Snags in Initial Jetson Orin Nano Setup
    Where first power-on of a Jetson Orin Nano gets stuck
  2. It Worked Fine on the Server — Why Does Accuracy Drop on the Edge?
    Why accuracy differs between the server and the edge
  3. What You Must Check Before Applying INT8 Quantization to Edge AI Inference: Why Micro-Defects Quietly Disappear
    Per-class accuracy to check before INT8 quantization
  4. Is It Safe When the Average Latency Fits the Deadline? — Breaking Down the Edge Vision Inspection Latency Budget by p99
    Splitting the latency budget by p99 rather than the average

Stage 6 · Putting It into Equipment

  1. What to Write First in a Machine Vision Spec Sheet — The Order and Checklist for Choosing Camera, Lens and Lighting Specs
    What to write in the spec before requesting quotes
  2. The Camera Cannot Be Bolted On Last — Reserving Space and WD for Vision Cameras and Lighting at the Mechanical Design Stage
    Reserving camera and lighting space and WD during mechanical design
  3. The Vision Decision Is Done — So Why Does the PLC Learn It Late? Breaking Down Trigger-to-Output Latency on the Vision Side
    Why vision results reach the PLC late
  4. Why Edge AI Vision Fails on the Factory Floor — A Troubleshooting Map from Symptom to Cause
    A troubleshooting map for when edge AI fails on site

If a term is unfamiliar, keep the Glossary open alongside. The full list for each topic is on the topic pages in the menu.

Last updated: October 24, 2026