Proceedings ArticleDOI
An incremental Bayesian approch to sketch recognition [approach read approach]
Shizhong Liao,Xiao-Jun Wang,Jin-Liang Lu +2 more
- Vol. 7, pp 4549-4553
TLDR
A new framework proposed in this paper offers user more sketching freedom by automatically grouping strokes and recognizing editing gestures as well as over-traced strokes in the framework of Bayesian network.Abstract:
Sketch recognition is an essential process for sketch understanding. The free drawing style of sketching makes it difficult to build a robust sketch recognition system that can support the imprecision and high variability present in sketch. This paper addresses these problems inherent in sketch recognition in the framework of Bayesian network which can readily represent uncertainty in the recognition process and make inference based on partial evidence. To further improve recognition accuracy, context information is incorporated in the recognition process rather than identifying sketches in isolation. The new framework proposed in this paper offers user more sketching freedom by automatically grouping strokes and recognizing editing gestures as well as over-traced strokes.read more
Citations
More filters
Proceedings ArticleDOI
Sketch recognition via string kernel
Shizhong Liao,Menghua Duan +1 more
TL;DR: A novel recognition approach that can recognize primitive shapes, as well as combinations of these primitives, independent of stroke order, number, aswell as invariant to size and aspect ratio of sketch is proposed.
Journal ArticleDOI
The implementation of a sketch-based virtual product development
TL;DR: How to interpret product descriptions in freehand sketches and to transfer them to digital three-dimensional models, e.g. in order to visualize, calculate and evaluate shapes to the development of computer-aided design (CAD) models is described.
Proceedings ArticleDOI
Chapter 11: Creative Shape Interpretation in Paper Scribbles
TL;DR: The paper discusses special geometrical issues that are concerned with the interpretation of the future productpsilas contours within paper scribbles and virtual pre-CAD models and implemented algorithms combine image-based modeling methods with usual computer-aided design (CAD) modeling strategies.
Book ChapterDOI
The colour sketch recognition interface for training systems
TL;DR: The elaborated interface, supported by the low-level recognition algorithm, simplifies the evaluation procedures and removes both interpretation uncertainty factor and simple errors from the sketch, using the user interaction interface.
Journal ArticleDOI
Creative spatial interpretation of freehand sketches
TL;DR: The paper discusses ideas and R&D work concerned with the interpretation of creative shape depictions in freehand sketches and the generation of digital shape models, which enable not only the transfer of 2-D shape depictions to fuzzy digital2-D sketches but also the transfer to 3-D digital shapes.
References
More filters
Book
Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference
TL;DR: Probabilistic Reasoning in Intelligent Systems as mentioned in this paper is a complete and accessible account of the theoretical foundations and computational methods that underlie plausible reasoning under uncertainty, and provides a coherent explication of probability as a language for reasoning with partial belief.
An empirical study of the naive Bayes classifier
TL;DR: This work analyzes the impact of the distribution entropy on the classification error, showing that low-entropy feature distributions yield good performance of naive Bayes and demonstrates that naive Baye works well for certain nearlyfunctional feature dependencies.
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.
CALI: An Online Scribble Recognizer for Calligraphic Interfaces
Manuel J. Fonseca,Joaquim Jorge +1 more
TL;DR: This work uses temporal adjacency to allow users to input the most common shapes in drawing such as triangles, lines, rectangles, circles, diamonds and ellipses, using multiple strokes, and has further extended this approach to identify useful shapes such as arrows, crossing lines and unistroke gestures.
Proceedings ArticleDOI
Using fuzzy logic to recognize geometric shapes interactively
Manuel J. Fonseca,Joaquim Jorge +1 more
TL;DR: Presents a simple method, based on fuzzy logic, to recognize multi-stroke sketches of geometric shapes and uni-stroke gestural commands that has proved suitable for interactive applications.