Determining the bias and variance of a deterministic finger-tracking algorithm.
Identifieur interne : 000297 ( PubMed/Corpus ); précédent : 000296; suivant : 000298Determining the bias and variance of a deterministic finger-tracking algorithm.
Auteurs : Valerie S. Morash ; Bas H M. Van Der VeldenSource :
- Behavior research methods [ 1554-3528 ] ; 2016.
Abstract
Finger tracking has the potential to expand haptic research and applications, as eye tracking has done in vision research. In research applications, it is desirable to know the bias and variance associated with a finger-tracking method. However, assessing the bias and variance of a deterministic method is not straightforward. Multiple measurements of the same finger position data will not produce different results, implying zero variance. Here, we present a method of assessing deterministic finger-tracking variance and bias through comparison to a non-deterministic measure. A proof-of-concept is presented using a video-based finger-tracking algorithm developed for the specific purpose of tracking participant fingers during a psychological research study. The algorithm uses ridge detection on videos of the participant's hand, and estimates the location of the right index fingertip. The algorithm was evaluated using data from four participants, who explored tactile maps using only their right index finger and all right-hand fingers. The algorithm identified the index fingertip in 99.78 % of one-finger video frames and 97.55 % of five-finger video frames. Although the algorithm produced slightly biased and more dispersed estimates relative to a human coder, these differences (x=0.08 cm, y=0.04 cm) and standard deviations (σ x =0.16 cm, σ y =0.21 cm) were small compared to the size of a fingertip (1.5-2.0 cm). Some example finger-tracking results are provided where corrections are made using the bias and variance estimates.
DOI: 10.3758/s13428-015-0610-3
PubMed: 26174712
Links to Exploration step
pubmed:26174712Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Determining the bias and variance of a deterministic finger-tracking algorithm.</title><author><name sortKey="Morash, Valerie S" sort="Morash, Valerie S" uniqKey="Morash V" first="Valerie S" last="Morash">Valerie S. Morash</name><affiliation><nlm:affiliation>Department of Psychology, University of California, Berkeley, CA, USA. valmo@alum.mit.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Van Der Velden, Bas H M" sort="Van Der Velden, Bas H M" uniqKey="Van Der Velden B" first="Bas H M" last="Van Der Velden">Bas H M. Van Der Velden</name><affiliation><nlm:affiliation>Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands.</nlm:affiliation></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PubMed</idno><date when="2016">2016</date><idno type="RBID">pubmed:26174712</idno><idno type="pmid">26174712</idno><idno type="doi">10.3758/s13428-015-0610-3</idno><idno type="wicri:Area/PubMed/Corpus">000297</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Determining the bias and variance of a deterministic finger-tracking algorithm.</title><author><name sortKey="Morash, Valerie S" sort="Morash, Valerie S" uniqKey="Morash V" first="Valerie S" last="Morash">Valerie S. Morash</name><affiliation><nlm:affiliation>Department of Psychology, University of California, Berkeley, CA, USA. valmo@alum.mit.edu.</nlm:affiliation></affiliation></author><author><name sortKey="Van Der Velden, Bas H M" sort="Van Der Velden, Bas H M" uniqKey="Van Der Velden B" first="Bas H M" last="Van Der Velden">Bas H M. Van Der Velden</name><affiliation><nlm:affiliation>Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands.</nlm:affiliation></affiliation></author></analytic><series><title level="j">Behavior research methods</title><idno type="eISSN">1554-3528</idno><imprint><date when="2016" type="published">2016</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Finger tracking has the potential to expand haptic research and applications, as eye tracking has done in vision research. In research applications, it is desirable to know the bias and variance associated with a finger-tracking method. However, assessing the bias and variance of a deterministic method is not straightforward. Multiple measurements of the same finger position data will not produce different results, implying zero variance. Here, we present a method of assessing deterministic finger-tracking variance and bias through comparison to a non-deterministic measure. A proof-of-concept is presented using a video-based finger-tracking algorithm developed for the specific purpose of tracking participant fingers during a psychological research study. The algorithm uses ridge detection on videos of the participant's hand, and estimates the location of the right index fingertip. The algorithm was evaluated using data from four participants, who explored tactile maps using only their right index finger and all right-hand fingers. The algorithm identified the index fingertip in 99.78 % of one-finger video frames and 97.55 % of five-finger video frames. Although the algorithm produced slightly biased and more dispersed estimates relative to a human coder, these differences (x=0.08 cm, y=0.04 cm) and standard deviations (σ x =0.16 cm, σ y =0.21 cm) were small compared to the size of a fingertip (1.5-2.0 cm). Some example finger-tracking results are provided where corrections are made using the bias and variance estimates.</div></front></TEI><pubmed><MedlineCitation Owner="NLM" Status="In-Data-Review"><PMID Version="1">26174712</PMID><DateCreated><Year>2016</Year><Month>06</Month><Day>03</Day></DateCreated><Article PubModel="Print"><Journal><ISSN IssnType="Electronic">1554-3528</ISSN><JournalIssue CitedMedium="Internet"><Volume>48</Volume><Issue>2</Issue><PubDate><Year>2016</Year><Month>Jun</Month></PubDate></JournalIssue><Title>Behavior research methods</Title><ISOAbbreviation>Behav Res Methods</ISOAbbreviation></Journal><ArticleTitle>Determining the bias and variance of a deterministic finger-tracking algorithm.</ArticleTitle><Pagination><MedlinePgn>772-82</MedlinePgn></Pagination><ELocationID EIdType="doi" ValidYN="Y">10.3758/s13428-015-0610-3</ELocationID><Abstract><AbstractText>Finger tracking has the potential to expand haptic research and applications, as eye tracking has done in vision research. In research applications, it is desirable to know the bias and variance associated with a finger-tracking method. However, assessing the bias and variance of a deterministic method is not straightforward. Multiple measurements of the same finger position data will not produce different results, implying zero variance. Here, we present a method of assessing deterministic finger-tracking variance and bias through comparison to a non-deterministic measure. A proof-of-concept is presented using a video-based finger-tracking algorithm developed for the specific purpose of tracking participant fingers during a psychological research study. The algorithm uses ridge detection on videos of the participant's hand, and estimates the location of the right index fingertip. The algorithm was evaluated using data from four participants, who explored tactile maps using only their right index finger and all right-hand fingers. The algorithm identified the index fingertip in 99.78 % of one-finger video frames and 97.55 % of five-finger video frames. Although the algorithm produced slightly biased and more dispersed estimates relative to a human coder, these differences (x=0.08 cm, y=0.04 cm) and standard deviations (σ x =0.16 cm, σ y =0.21 cm) were small compared to the size of a fingertip (1.5-2.0 cm). Some example finger-tracking results are provided where corrections are made using the bias and variance estimates.</AbstractText></Abstract><AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Morash</LastName><ForeName>Valerie S</ForeName><Initials>VS</Initials><AffiliationInfo><Affiliation>Department of Psychology, University of California, Berkeley, CA, USA. valmo@alum.mit.edu.</Affiliation></AffiliationInfo></Author><Author ValidYN="Y"><LastName>van der Velden</LastName><ForeName>Bas H M</ForeName><Initials>BH</Initials><AffiliationInfo><Affiliation>Image Sciences Institute, University Medical Center Utrecht, Utrecht, the Netherlands.</Affiliation></AffiliationInfo></Author></AuthorList><Language>eng</Language><PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType></PublicationTypeList></Article><MedlineJournalInfo><Country>United States</Country><MedlineTA>Behav Res Methods</MedlineTA><NlmUniqueID>101244316</NlmUniqueID><ISSNLinking>1554-351X</ISSNLinking></MedlineJournalInfo><CitationSubset>IM</CitationSubset><KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Algorithm</Keyword><Keyword MajorTopicYN="N">Bias</Keyword><Keyword MajorTopicYN="N">Finger tracking</Keyword><Keyword MajorTopicYN="N">Haptics</Keyword><Keyword MajorTopicYN="N">Variance</Keyword></KeywordList></MedlineCitation><PubmedData><History><PubMedPubDate PubStatus="entrez"><Year>2015</Year><Month>7</Month><Day>16</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="pubmed"><Year>2015</Year><Month>7</Month><Day>16</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate><PubMedPubDate PubStatus="medline"><Year>2015</Year><Month>7</Month><Day>16</Day><Hour>6</Hour><Minute>0</Minute></PubMedPubDate></History><PublicationStatus>ppublish</PublicationStatus><ArticleIdList><ArticleId IdType="pubmed">26174712</ArticleId><ArticleId IdType="doi">10.3758/s13428-015-0610-3</ArticleId><ArticleId IdType="pii">10.3758/s13428-015-0610-3</ArticleId></ArticleIdList></PubmedData></pubmed></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/HapticV1/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000297 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000297 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= HapticV1
|flux= PubMed
|étape= Corpus
|type= RBID
|clé= pubmed:26174712
|texte= Determining the bias and variance of a deterministic finger-tracking algorithm.
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:26174712" \
| HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \
| NlmPubMed2Wicri -a HapticV1
| This area was generated with Dilib version V0.6.23. |  |