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

Delaye, Adrien; Anquetil, Éric

doi:10.1016/j.patcog.2012.07.015

Cited by 53 publications

(53 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As Table 1 indicates, on this dataset we achieved an best accuracy rate of 97.95%., compared to other results in the literatures [4,7,8]. Table 1.…”

Section: Resultsmentioning

confidence: 79%

“…Willems et al [7] explored a large number of on-line features, which were sorted in three feature sets due to different levels of details. Recently Delaye and Anquetil [8] presented a set of 49 features, called HBF49, for the representation of hand-drawn symbols for use as a reference for evaluation of symbol recognition systems. This paper presents an on-line sketched symbol recognition method using the direction feature.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

On-Line Sketch Recognition Using Direction Feature

Wu¹,

Yu²,

Lai³

2013

Human-Computer Interaction – INTERACT 2013

View full text Add to dashboard Cite

Abstract. Sketch recognition is widely used in pen-based interaction, especially as the increasing popularity of devices with touch screens. It can enhance human-computer interaction by allowing a natural/free form of interaction. The main challenging problem is the variability in hand drawings. This paper presents an on-line sketch recognition method based on the direction feature. We also present two feature representations to train a classifier. We support our case by experimental results obtained from the NicIcon database. A recognition rate of 97.95% is achieved, and average runtime is 97.6ms using a Support Vector Machine classifier. Keywords: Sketched symbol recognition, NicIcon database, multi-stroke shapes IntroductionSketching is a natural form of human communication. Sketch-based interaction is a fast and efficient means of capturing information by automatically interpreting handdrawn sketches and can be an important part of the early design process, where it can help people explore rough ideas and solutions in an informal environment. Sketch recognition refers to the recognition of predefined symbols or free-form drawings(e.g., an unconstrained circuit drawing); in the latter case, the recognition task is generally preceded by segmentation in order to locate individual symbols. This paper focuses on the recognition of hand-drawn isolated symbols. With the growing popularity of devices with touch screens, there is increasing interest in building sketch-based user interfaces. However, many challenges remain in terms of intra-class compactness and interclass separation due to the variability of sketching. Because it is likely that different people will have different drawing styles, such as the stroke-order, -number, and nonuniform scaling , as well as complex local shifts. Moreover, the style of the same individual at different times may differ. A good recognition algorithm should place few drawing constraints on users. Related research is that of handwriting recognition, such as handwritten digit and Chinese character recognition with many effective algorithms.

show abstract

“…As Table 1 indicates, on this dataset we achieved an best accuracy rate of 97.95%., compared to other results in the literatures [4,7,8]. Table 1.…”

Section: Resultsmentioning

confidence: 79%

Section: Related Workmentioning

confidence: 99%

On-Line Sketch Recognition Using Direction Feature

Wu¹,

Yu²,

Lai³

2013

Human-Computer Interaction – INTERACT 2013

View full text Add to dashboard Cite

show abstract

“…The rest of this section presents these two approaches. [7] is a generic set of features designed for handwriting symbols 200 recognition. More precisely, it is composed of dynamic features that depend on the writing process (e.g.…”

Section: Analysis-based Featuresmentioning

confidence: 99%

“…It is also seen as an extension of [5] that analyses symbols with an evolving fuzzy inference system [6] and HBF49 [7] 55 features. More precisely, this paper contains five main contributions by introducing:…”

mentioning

confidence: 99%

Multi-criteria handwriting quality analysis with online fuzzy models

Simonnet

Anquetil

Bouillon

2017

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

IntuiScript is an innovative project aiming at the development of a digital workbook providing feedback during the handwriting learning process for children from three to seven years old. In this context, the paper presents a method to analyse handwriting quality that responds to the expectations of the IntuiScript educational scenario: on-line and real time feedback for children, an automatic detection of children mistakes guiding the pedagogical progression, and a precise analysis of children writing saved to help teacher to understand children writing skills. The presented method introduces a multi-criteria architecture to analyse handwriting quality based on three different aspects: shape, order and direction. The validation of the proposed approach is done on a realistic dataset collected in preschools and primary schools with 952 children. Results show a positive feedback of children and teachers about the use of tactile digital devices, and a significant improvement of the performances of the multi-criteria architecture compared to the previous analyser. The ground truth has been annotated by experts with different levels of confidence. Specific evaluation metrics are introduced to deal with confidence annotations.

show abstract

“…The supplied HBF49 [66] feature set is a unified feature representation for universal online symbol recognition. It was designed to cover all the aspects needed for symbol recognition with various characteristics: online, offline, mono-stroke, multi-stroke, and in various contest: handwritten digits, mathematical symbols, iconic gestures, geometrical objects, architectural objects, etc.…”

Section: Evaluation Databasementioning

confidence: 99%

Online active supervision of an evolving classifier for customized-gesture-command learning

Bouillon

Anquetil

2017

Neurocomputing

Self Cite

View full text Add to dashboard Cite

To cite this version:Manuel Bouillon, Eric Anquetil.Online active supervision of an evolving classifier for customized-gesture-command learning.Neurocomputing AbstractTouch sensitive interfaces enable new interaction methods, like gesture commands. For users to easily memorize more than a dozen of gesture commands, it is important to enable gesture set customization. The classifier used to recognize drawn symbols must hence be customizable -able to learn from very few data -and evolving -able to learn new classes on-the-fly and improve during its use. The objective of this work is to obtain a gesture command system that cooperates as best as possible with the user: that learns from its mistakes without soliciting the user too often. This paper presents a novel approach for the online active learning of gesture commands, with three contributions. The IntuiSup supervisor monitors the learning process and user interactions. The Evolving Sampling by Uncertainty (ESU) algorithm enables to maintain the error/interaction compromise over time. The Boosted-ESU (B-ESU) method optimizes interaction impact to fasten system learning speed. The efficiency of our approach is evaluated on the publicly available ILG Data Base of gesture commands. Experimentation shows the effectiveness of the supervision strategy and improvements both in term of accuracy and learning speed.

show abstract

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

Cited by 53 publications

References 53 publications

On-Line Sketch Recognition Using Direction Feature

On-Line Sketch Recognition Using Direction Feature

Multi-criteria handwriting quality analysis with online fuzzy models

Online active supervision of an evolving classifier for customized-gesture-command learning

Contact Info

Product

Resources

About