Addressing class distribution issues of the drawing vs writing classification in an ink stroke sequence

Wang, Xin; Biswas, Manoj Kumar; Raghupathy, Sashi

doi:10.1145/1384429.1384458

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Addressing a similar problem, Bishop et al (2004), Patel et al (2007), and Bhat and Hammond (2009) present methods that integrate shape and temporal information for classifying individual strokes as either text or drawing strokes. Wang et al (2007) improve on Bishop et al's method. The goal of most previous single-stroke classification techniques is to identify the text strokes so they can be sent to a character recognizer, while the shape strokes (i.e., strokes comprising graphic objects) are left ungrouped. Our approach goes further, grouping the shape strokes as well.…”

Section: Introductionmentioning

confidence: 99%

Grouping Strokes into Shapes in Hand-Drawn Diagrams

Peterson

Stahovich

Doi

et al. 2010

AAAI

View full text Add to dashboard Cite

Objects in freely-drawn sketches often have no spatial or temporal separation, making object recognition difficult. We present a two-step stroke-grouping algorithm that first classifies individual strokes according to the type of object to which they belong, then groups strokes with like classifications into clusters representing individual objects. The first step facilitates clustering by naturally separating the strokes, and both steps fluidly integrate spatial and temporal information. Our approach to grouping is unique in its formulation as an efficient classification task rather than, for example, an expensive search task. Our single-stroke classifier performs at least as well as existing single-stroke classifiers on text vs. nontext classification, and we present the first three-way single-stroke classification results. Our stroke grouping results are the first reported of their kind; our grouping algorithm correctly groups between 86% and 91% of the ink in diagrams from two domains, with between 69% and 79% of shapes being perfectly clustered.

show abstract

Section: Introductionmentioning

confidence: 99%

Grouping Strokes into Shapes in Hand-Drawn Diagrams

Peterson

Stahovich

Doi

et al. 2010

AAAI

View full text Add to dashboard Cite

show abstract

“…Bishop et al 6 trained and evaluated a classification algorithm using a Hidden Markov Model. Wang et al 7 extend Bishop's approach by integrating a neural network. Gennari et al 8 segmented pen strokes and then used properties of the pen stroke segments to interpret hand-drawn diagrams.…”

Section: Introductionmentioning

confidence: 99%

Automatic Handwritten Statics Solution Classification and its Applications in Predicting Student Performance

Lin¹,

Stahovich²,

Herold³

2012 ASEE Annual Conference &Amp; Exposition Proceedings

View full text Add to dashboard Cite

In previous research, we found that the spatial and temporal organization of students' solutions to engineering Statics problems correlates with the correctness of their work. Our technique utilized Livescribe TM Smartpens to capture digital records of students' handwritten solutions. Analysis of the temporal and spatial organization of a solution can, for example, enable an instructor to inexpensively identify students who may be struggling in the course and need extra assistance. This requires, however, that the pen strokes be labeled according to the type of content they represent: free body diagrams, equations, or cross-outs of incorrect work (the ink of the Smartpens cannot be erased). For our initial analyses, we manually labeled the pen strokes, but it is too time consuming to do this for the entire data set. This led to our current work on a technique for automatically determining the content type of the pen stoke in a solution. Our approach correctly classified 93.30% of pen strokes in one experiment. We have used these labeled sketches to detect potentially poor-performing students by comparing the equation drawing time and total length of strokes for each student to the mean from all students.

show abstract

Multi-domain Hierarchical Free-Sketch Recognition Using Graphical Models

Alvarado¹

2011

Sketch-Based Interfaces and Modeling

View full text Add to dashboard Cite

Addressing class distribution issues of the drawing vs writing classification in an ink stroke sequence

Cited by 5 publications

References 8 publications

Grouping Strokes into Shapes in Hand-Drawn Diagrams

Grouping Strokes into Shapes in Hand-Drawn Diagrams

Automatic Handwritten Statics Solution Classification and its Applications in Predicting Student Performance

Multi-domain Hierarchical Free-Sketch Recognition Using Graphical Models

Contact Info

Product

Resources

About