2007
DOI: 10.1007/978-3-540-74695-9_27
|View full text |Cite
|
Sign up to set email alerts
|

Probabilistic Video-Based Gesture Recognition Using Self-organizing Feature Maps

Abstract: Present work introduces a probabilistic recognition scheme for hand gestures. Self organizing feature maps are used to model spatiotemporal information extracted through image processing. Two models are built for each gesture category and, along with appropriate distance metrics, produce a validated classification mechanism that performs consistently during experiments on acted gestures video sequences.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
8
0
2

Year Published

2010
2010
2021
2021

Publication Types

Select...
1
1
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(10 citation statements)
references
References 13 publications
0
8
0
2
Order By: Relevance
“…Given that u i is the index of a map unit the function BM U (x i , y i ) creates S -set of indices of all map units treated as a set of symbols. As explained by the authors in [4], because the u i value of consequent points of a gesture remains the same -this is because, although continuous hand movement is described by distinct points, consequent points are generally close in the input data space. (Note: although we are talking about 2D SOM in this case, we can once more see the property of the SOM for smoothly varying data and even though we are projecting data from high-dimensional space into lowerdimensional space, we still see a correlation between the similarity distance between the input data and its mapping onto the SOM lattice).…”
Section: Gesture Recognition Using Self-organizing Maps and Trajectoriesmentioning
confidence: 94%
See 1 more Smart Citation
“…Given that u i is the index of a map unit the function BM U (x i , y i ) creates S -set of indices of all map units treated as a set of symbols. As explained by the authors in [4], because the u i value of consequent points of a gesture remains the same -this is because, although continuous hand movement is described by distinct points, consequent points are generally close in the input data space. (Note: although we are talking about 2D SOM in this case, we can once more see the property of the SOM for smoothly varying data and even though we are projecting data from high-dimensional space into lowerdimensional space, we still see a correlation between the similarity distance between the input data and its mapping onto the SOM lattice).…”
Section: Gesture Recognition Using Self-organizing Maps and Trajectoriesmentioning
confidence: 94%
“…These results will be improved by taking into account the frequency of the posture transitions discussed in the next Section. [2] 90.5 Approach in [3] 98.25 Approach in [4] 93 thesis for example, does not impose domain specific knowledge reaching similar performance in terms of correctly classified gestures. In terms of complexity, approach 4 is much simpler with nearly the same recognition result as in [47].…”
mentioning
confidence: 99%
“…Another novel approach to Video-Based Gesture Recognition Using Self-Organizing Feature Maps was also created by G. Caridakis, C. Pateritas and A. Drosopoulos in [4] and [26].…”
mentioning
confidence: 99%
“…Στην δεύτερη προσέγγιση παρουσιάστηκαν μεθοδολογίες εξαγωγής συμβολικών κα νόνων που αποτελούν και μία μορφή απεικόνισης της εξαγόμενης από τα δεδο μένα γνώσης, η οποία είναι κατανοητή και χρηστική από τον άνθρωπο. Οι δύο αυτές προσεγγίσεις παρουσιάζονται στις εργασίες [10] και [55] αντίστοιχα.…”
Section: συνεισφορά της διατριβήςunclassified
“…Αυτο-οργανούμενοι χάρτες και συμβολική αναπαράσταση γνώσης Στο κεφάλαιο αυτό παρουσιάζονται δύο μεθοδολογίες, οι οποίες εκμεταλλεύ ονται τα πλεονεκτήματα που παρουσιάζει το μοντέλο των αυτο-οργανούμενων χαρτών με σκοπό να μετασχηματίσουν την γνώση που ενσωματώνεται σε έναν εκπαιδευμένο χάρτη σε συμβολική μορφή. Στην πρώτη μεθοδολογία [10], ο μετασχηματισμός αυτός αφορά την δημιουργία συμβολικών καταστάσεων που χρησιμοποιούνται για την δημιουργία πιθανοτικών μοντέλων, ενώ στην δεύτερη περίπτωση παρουσιάζεται μία προσέγγιση σε μεθόδους εξαγωγής κανόνων από έναν εκπαιδευμένο χάρτη [55].…”
Section: συζήτηση -συμπεράσματαunclassified