search

brandonmpetty / Doxa

A Local Adaptive Thresholding framework for image binarization written in C++, with JS and Python bindings. Implementing: Otsu, Bernsen, Niblack, Sauvola, Wolf, Gatos, NICK, Su, T.R. Singh, WAN, ISauvola, Bataineh, Chan and Shafait.
https://brandonmpetty.github.io/Doxa/WebAssembly
Creative Commons Zero v1.0 Universal
167 stars 37 forks source link

Documentation - Parameter Defaults #23

Closed brandonmpetty closed 1 year ago

brandonmpetty commented 3 years ago

We need to document the parameter defaults for each algorithm, and other algorithms. Create a Wiki that describes how to use the API and its options, along with how each Algorithm works.

Algorithm Parameters

Otsu
Bataineh
    No parameters

Niblack
Sauvola
ISauvola
TRSingh
Wan
Wolf
    name: "window", default: 75
    name: "k", default: 0.2

NICK
    name: "window", default: 75
    name: "k", default: -0.2

Bernsen
    name: "window", default: 75
    name: "threshold", default: 100
    name: "contrast-limit", default: 25

Gatos
    name: "glyph", default: 60

Su *
    name: "window", default: 0 = Auto-Detect
    name: "minN", default: value of "window"

* Su - A "window" value of 0 will cause the algorithm to auto-detect based on stroke width.  This is not currently implemented so a default value of 9 is currently being used.

PNM Parameters

This is for C++ only

PNM::Read *
    name: "grayscale", default: Mean

* "grayscale" algorithm options include: Qt, Mean, BT601, BT709, BT2100, Value, Luster, Lightness
brandonmpetty commented 1 year ago

I added the details for Python and JS into the new Notebooks I created. I will work on creating a Wiki entry at some point.