An efficient, classification-based approach for grouping pen strokes into objects

Stahovich, Thomas F.; Peterson, Eric J.; Lin, Hanlung

doi:10.1016/j.cag.2014.03.003

Cited by 13 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, our grouping methods build upon the work of Stahovich et al [46]. Just as they do, we use a pairwise classifier to determine if pairs of pen strokes belong to the same objects.…”

mentioning

confidence: 99%

“…Our HMM has 50 states including letters, numerical digits, '(', Table 6: Accuracy for classifying cross-out strokes vs. non-cross-outs using our cross-out features (X) listed in Table 2 [46]. were used for testing.…”

mentioning

confidence: 99%

“…We use three metrics from [46] (by arc length) that was correctly located. Ink-Extra is the per- 13 grouping features from [46]. We also examined the per- our techniques provide a foundation for such analysis.…”

mentioning

confidence: 99%

“…We compared the performance of our set of 10 features 769 to that of the features developed by Stahovich et al[46] and 770 Blagojevic et al[6]. In the results below, we refer to our fea-771 ture set as DE.…”

mentioning

confidence: 99%

“…G = our equation grouping features. S = the grouping features from[46]. A = the combination of G and S.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Enabling data mining of handwritten coursework

Stahovich

Lin

2016

Computers & Graphics

Self Cite

View full text Add to dashboard Cite

Data mining has become an increasingly important tool for education researchers and practitioners. However, work in this field has focused on data from online educational systems. Here, we present techniques to enable data mining of handwritten coursework, which is an essential component of instruction in many disciplines. Our techniques include methods for classifying pen strokes as diagram, equation, and cross-out strokes. The latter are used to strike out erroneous work. We have also created techniques for grouping equation strokes into equation groups and then individual characters. Our results demonstrate that our classification and grouping techniques are more accurate than prior techniques for this task. We also demonstrate applications of our techniques for automated assessment of student competence. We present a novel approach for measuring the correctness of exam solutions from an analysis of lexical features of handwritten equations. This analysis demonstrates, for example, that the number of equation groups correlates positively with grade. We also use our techniques to extend graphical protocol analysis to free-form, handwritten problem solutions. While prior work in a laboratory setting suggests that long pauses are indicative of low competence, our work shows that the frequency of long pauses during exams correlates positively with competence.

show abstract

“…Similarly, our grouping methods build upon the work of Stahovich et al [46]. Just as they do, we use a pairwise classifier to determine if pairs of pen strokes belong to the same objects.…”

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

“…G = our equation grouping features. S = the grouping features from[46]. A = the combination of G and S.…”

mentioning

confidence: 99%

See 3 more Smart Citations