Handshape recognition for Argentinian Sign Language using ProbSom
Fuente:
Redalyc
Gespeichert in:
| 1. Verfasser: | |
|---|---|
| Format: | Artículo científico |
| Sprache: | en |
| Veröffentlicht: |
Universidad Nacional de La Plata
2016
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1876424284216229888 |
|---|---|
| author | Franco Ronchetti |
| author_facet | Franco Ronchetti |
| contents | Handshape recognition for Argentinian Sign Language using ProbSom Franco Ronchetti Facundo Quiroga César Estrebou Laura Lanzarini Computación SOM sign lan Radon transform guage recognition Handshape recognition Automatic sign language recognition is an impor-tant topic within the areas of human computerinteraction and machine learning. On the onehand, it poses a complex challengethat requiresthe intervention of various knowledge areas, suchas video processing, image processing, intelligentsystems and linguistics. On the other hand, robustrecognition of sign language could assist in thetranslation process and the integration of hearing-impaired people.This paper offers two main contributions: first,the creation of a database of handshapes for theArgentinian Sign Language (LSA), which is a topicthat has barely beendiscussed so far. Secondly,a technique for image processing, descriptor ex-traction and subsequent handshape classificationusing a supervised adaptation of self-organizingmaps that is called ProbSom. This technique iscompared to others in the state of the art, such asSupport Vector Machines (SVM), Random Forests,and Neural Networks.The database that was built contains 800 im-ages with 16 LSA conjurations, and is a first steptowards building a comprehensive database of Ar-gentinian signs. The ProbSom-based neural clas-sifier, using the proposed descriptor, achieved anaccuracy rate above 90%. 2016 otro 1666-6046 https://www.redalyc.org/articulo.oa?id=638067263003 en http://www.redalyc.org/revista.oa?id=6380 Journal of Computer Science and Technology application/pdf Universidad Nacional de La Plata Journal of Computer Science and Technology (Argentina) Num.01 Vol.16 |
| format | Artículo científico |
| id | redalyc_638067263003 |
| institution | Redalyc |
| language | en |
| publishDate | 2016 |
| publisher | Universidad Nacional de La Plata |
| spellingShingle | Handshape recognition for Argentinian Sign Language using ProbSom Franco Ronchetti Computación SOM sign lan Radon transform guage recognition Handshape recognition Handshape recognition for Argentinian Sign Language using ProbSom Franco Ronchetti Facundo Quiroga César Estrebou Laura Lanzarini Computación SOM sign lan Radon transform guage recognition Handshape recognition Automatic sign language recognition is an impor-tant topic within the areas of human computerinteraction and machine learning. On the onehand, it poses a complex challengethat requiresthe intervention of various knowledge areas, suchas video processing, image processing, intelligentsystems and linguistics. On the other hand, robustrecognition of sign language could assist in thetranslation process and the integration of hearing-impaired people.This paper offers two main contributions: first,the creation of a database of handshapes for theArgentinian Sign Language (LSA), which is a topicthat has barely beendiscussed so far. Secondly,a technique for image processing, descriptor ex-traction and subsequent handshape classificationusing a supervised adaptation of self-organizingmaps that is called ProbSom. This technique iscompared to others in the state of the art, such asSupport Vector Machines (SVM), Random Forests,and Neural Networks.The database that was built contains 800 im-ages with 16 LSA conjurations, and is a first steptowards building a comprehensive database of Ar-gentinian signs. The ProbSom-based neural clas-sifier, using the proposed descriptor, achieved anaccuracy rate above 90%. 2016 otro 1666-6046 https://www.redalyc.org/articulo.oa?id=638067263003 en http://www.redalyc.org/revista.oa?id=6380 Journal of Computer Science and Technology application/pdf Universidad Nacional de La Plata Journal of Computer Science and Technology (Argentina) Num.01 Vol.16 |
| title | Handshape recognition for Argentinian Sign Language using ProbSom |
| topic | Computación SOM sign lan Radon transform guage recognition Handshape recognition |
| url | https://www.redalyc.org/articulo.oa?id=638067263003 |