Proceedings ArticleDOI
Sort, merge, repeat: an algorithm for effectively finding corners in hand-sketched strokes
Aaron Wolin,Brandon Paulson,Tracy Hammond +2 more
- pp 93-99
Reads0
Chats0
TLDR
This paper presents a new multi-pass corner finding algorithm called MergeCF that is based on continually merging smaller stroke segments with similar, larger stroke segments in order to eliminate false positive corners.Abstract:
Free-sketch recognition systems attempt to recognize freely-drawn sketches without placing stylistic constraints on the users. Such systems often recognize shapes by using geometric primitives that describe the shape's appearance rather than how it was drawn. A free-sketch recognition system necessarily allows users to draw several primitives using a single stroke. Corner finding, or vertex detection, is used to segment these strokes into their underlying primitives (lines and arcs), which in turn can be passed to the geometric recognizers. In this paper, we present a new multi-pass corner finding algorithm called MergeCF that is based on continually merging smaller stroke segments with similar, larger stroke segments in order to eliminate false positive corners. We compare MergeCF to two benchmark corner finders with substantial improvements in corner detection.read more
Citations
More filters
Proceedings ArticleDOI
Sketch it, make it: sketching precise drawings for laser cutting
TL;DR: Sketch It, Make It (SIMI) is a modeling tool that enables non-experts to design items for fabrication with laser cutters and combines the strengths of sketch-based interaction with the power of constraint-based modeling.
Journal ArticleDOI
Technical Section: A ShortStraw-based algorithm for corner finding in sketch-based interfaces
Yiyan Xiong,Joseph J. LaViola +1 more
TL;DR: IStraw is presented, a corner finding technique based on the ShortStraw algorithm that addresses deficiencies with ShortSt Straw while maintaining its simplicity and efficiency and develops an extension for ink strokes containing curves and arcs.
Proceedings Article
A Sketch Recognition System for Recognizing Free-Hand Course of Action Diagrams
Tracy Hammond,Drew Logsdon,Brandon Paulson,Joshua Johnston,Joshua M. Peschel,Aaron Wolin,Paul Taele +6 more
TL;DR: A real-time sketch recognition interface that recognizes 485 freely-drawn military course-of-action symbols that achieves an accuracy of 90% when considering the top 3 interpretations and requiring every aspect of the shape to be correct.
Journal ArticleDOI
Technical Section: A machine learning approach to automatic stroke segmentation
James Herold,Thomas F. Stahovich +1 more
TL;DR: ClassySeg represents a movement away from prior, heuristic-based approaches, toward a more general and extensible technique, and is more accurate than previous techniques for both user-independent and user-optimized training conditions.
Proceedings ArticleDOI
Detection of Arrows in On-Line Sketched Diagrams Using Relative Stroke Positioning
TL;DR: An arrow detector which searches for arrows as arbitrarily shaped connectors between already found symbols as well as a design of an arrow recognizer where the head is detected using relative strokes positioning is proposed.
References
More filters
Proceedings ArticleDOI
Specifying gestures by example
TL;DR: GRANDMA, a toolkit for rapidly adding gestures to direct manipulation interfaces, and the trainable single-stroke gesture recognizer used by GRANDMA are described.
Proceedings ArticleDOI
PaleoSketch: accurate primitive sketch recognition and beautification
Brandon Paulson,Tracy Hammond +1 more
TL;DR: A new low-level recognition and beautification system that can recognize eight primitive shapes, as well as combinations of these primitives, with recognition rates at 98.56% and automatically generates beautified versions of these shapes to provide feedback early in the sketching process is proposed.
Proceedings ArticleDOI
Tahuti: a geometrical sketch recognition system for UML class diagrams
Tracy Hammond,Randall Davis +1 more
TL;DR: Tahuti is a dual-view sketch recognition environment for class diagrams in UML based on a multi-layer recognition framework which recognizes multi-stroke objects by their geometrical properties allowing users the freedom to draw naturally as they would on paper rather than requiring the user to draw the objects in a pre-defined manner.
Proceedings ArticleDOI
SketchREAD: a multi-domain sketch recognition engine
Christine Alvarado,Randall Davis +1 more
TL;DR: SketchREAD, a multi-domain sketch recognition engine capable of recognizing freely hand-drawn diagrammatic sketches, is presented and it is found that in both domains the use of context to reclassify low-level shapes significantly reduced recognition error over a baseline system that did not reinterpret low- level classifications.
Proceedings ArticleDOI
Visual similarity of pen gestures
TL;DR: A computational model for predicting perceived gesture similarity that correlates 0.56 with observation is derived and will be incorporated into a gesture design tool, which will aid the pen-based UI designer in creating gesture sets that are easier to learn and more memorable.
Related Papers (5)
PaleoSketch: accurate primitive sketch recognition and beautification
Brandon Paulson,Tracy Hammond +1 more
A curvature estimation for pen input segmentation in sketch-based modeling
Dae Hyun Kim,Myoung-Jun Kim +1 more