Feature extraction and classifier combination for image-based sketch recognition

Authors:
R. Sinan Tumen;M. Emre Acer;T. Metin Sezgin
Affiliations:
Koc University, Istanbul, Turkey;Carnegie Mellon University, Pittsburgh, PA;Koc University, Istanbul, Turkey
Venue:
Proceedings of the Seventh Sketch-Based Interfaces and Modeling Symposium
Year:
2010

Citing 17
Cited 3

Invariant Image Recognition by Zernike Moments

IEEE Transactions on Pattern Analysis and Machine Intelligence
On Combining Classifiers

IEEE Transactions on Pattern Analysis and Machine Intelligence
Ensemble learning via negative correlation

Neural Networks
The Trace Transform and Its Applications

IEEE Transactions on Pattern Analysis and Machine Intelligence
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Online Recognition of Sketched Electrical Diagrams

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
Sketched Symbol Recognition using Zernike Moments

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Feature Selection Based on Mutual Information: Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy

IEEE Transactions on Pattern Analysis and Machine Intelligence
An Incremental On-line Parsing Algorithm for Recognizing Sketching Diagrams

ICDAR '07 Proceedings of the Ninth International Conference on Document Analysis and Recognition - Volume 01
Envisioning sketch recognition: a local feature based approach to recognizing informal sketches

Envisioning sketch recognition: a local feature based approach to recognizing informal sketches
A combinatorial approach to multi-domain sketch recognition

SBIM '07 Proceedings of the 4th Eurographics workshop on Sketch-based interfaces and modeling
Recognizing interspersed sketches quickly

Proceedings of Graphics Interface 2009
Eager interpretation of on-line hand-drawn structured documents: The DALI methodology

Pattern Recognition
Iconic and multi-stroke gesture recognition

Pattern Recognition
Combining geometry and domain knowledge to interpret hand-drawn diagrams

Computers and Graphics
A visual approach to sketched symbol recognition

IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Constellation models for sketch recognition

SBM'06 Proceedings of the Third Eurographics conference on Sketch-Based Interfaces and Modeling

Technical Section: Using data mining for digital ink recognition: Dividing text and shapes in sketched diagrams

Computers and Graphics
Sketched symbol recognition with auto-completion

Pattern Recognition
HBF49 feature set: A first unified baseline for online symbol recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Image-based approaches to sketch recognition typically cast sketch recognition as a machine learning problem. In systems that adopt image-based recognition, the collected ink is generally fed through a standard three stage pipeline consisting of the feature extraction, learning and classification steps. Although these approaches make regular use of machine learning, existing work falls short of presenting a proper treatment of important issues such as feature extraction, feature selection, feature combination, and classifier fusion. In this paper, we show that all these issues are significantfactors, which substantially affect the ultimate performance of a sketch recognition engine. We support our case by experimental results obtained from two databases using representative sets of feature extraction, feature selection, classification, and classifier combination methods. We present the pros and cons of various choices that can be made while building sketch recognizers and discuss their trade-offs.