Squiggle - A Glyph Recognizer for Gesture Input

TL;DR

Squiggle is a fast, robust glyph recognizer that uses affine transformations to accurately identify user-drawn gestures in real time, supporting various symmetries and providing visual feedback.

Contribution

It introduces a template-based glyph recognition algorithm that is invariant to rotation, scaling, skew, and reflection, enabling real-time gesture recognition with visual feedback.

Findings

Recognizes glyphs accurately in real time

Invariant to multiple geometric transformations

Provides visual feedback during gesture input

Abstract

Squiggle is a template-based glyph recognizer in the lineage of `$1 Recognizer' and `Protractor'. It seeks a good fit linear affine mapping between the input and template glyphs which are represented as a list of milestone points along the glyph path. The algorithm can recognize input glyphs invariant of rotation, scaling, skew, and reflection symmetries. In practice the algorithm is fast and robust enough to recognize user-generated glyphs as they are being drawn in real time, and to project `shadows' of the matching templates as feedback.