Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 5 versions
addClaim

Reconocimiento de gestos manuales mediante red neuronal artificial

Authors: San Martín Garaluce, Jon;

Reconocimiento de gestos manuales mediante red neuronal artificial

Abstract

Las redes neuronales artificiales forman parte del conjunto de tecnologías que conocemos como Inteligencia Artificial y que, hoy en día, son usadas en infinidad de aplicaciones y además poseen un gran potencial de cara al futuro. Ellas se basan en modelos matemáticos que intentan asemejarse a las neuronas biológicas, proviniendo de ahí su nombre. En este trabajo se ha desarrollado una red neuronal artificial capaz de detectar y reconocer gestos manuales. Para ello, se han estudiado los principios de estas redes, así como las mejores tecnologías existentes para su implementación. Acto seguido, usando estas tecnologías, se han codificado varias aplicaciones para crear, entrenar y usar la red neuronal artificial objetivo. El entrenamiento de la red neuronal, por su parte, ha sido un proceso iterativo, como es normal en el desarrollo de las redes neuronales artificiales. Se ha partido de una arquitectura de red inicial, y tras numerosas iteraciones y cambios de parámetros, se ha llegado a una arquitectura óptima y eficiente, como se ha demostrado con una serie de pruebas realizadas finalmente.

Artificial neural networks are part of the group of technologies that we know as Artificial Inteligence, which are used nowdays in lots of applications and have a great potential looking to the future. They are based on mathematical models that try to resemble biological neurons, hence its name. In this project, an artificial neural network capable of detecting and recognizing hand gestures has been developed. To that end, the principles of this networks have been studied, as well as the best existing technologies for its implementation. Thereupon, using these technologies, various applications have been codified to create, train and use the targeted artificial neural network. For its part, the training of the neural network has been an iterative process, as is normal in the development of artificial neural networks. An initial architecture has been the starting point, and from there, after a series of iterations and parameter changes, an optimal and efficient architecture has been reached, as shown in a series of tests.

Sare neuronal artifizialak, Adimen Artifiziala bezala ezagutzen ditugun teknologien parte dira eta, gaur egun, teknologia hauek hainbat aplikazioetan erabiliak izaten dira, eta gainera potentzial handia daukate etorkizunari begira. Sare neuronal artifizialak neurona biologikoen antza daukaten eredu matematikoetan oinarritzen dira, hortik datorkie izena. Lan honetan, esku keinuak detektatzeko eta sailkatzeko gai den sare neuronal artifizial bat sortu da. Horretarako, sare hauen printzipioak ikasi dira, baita beren implementazioa lortzeko dauden teknologia onenak ere. Ondoren, teknologia hauen bidez, sare neuronal artifiziala sortzeko, entrenatzeko eta erabiltzeko hainbat aplikazio kodetu dira. Sare neuronal entrenamendua iterazio-prozesu bat izan da, sare neuronal artifizialak sortzean normala den moduan. Hasierako arkitektura batetik abiatu da, eta hainbat iterazio eta parametro aldaketa ondoren, arkitektura optimo eta eraginkor batera heldu da, egindako proba multzo batekin frogatu den moduan.

Country
Spain
Keywords

redes neuronales, inteligencia artificial, TensorFlow, reconocimiento de gestos manuales, Keras

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green
Related to Research communities