Growing neural gas for information extraction in gesture recognition and reproduction of robot partners

Botzheim, János; Kubota, Naoyuki

doi:10.1109/mhs.2012.6492471

Cited by 9 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A suggestion is to incorporate Gro (GNG) into the system. More information can be obtained from [36]. Due to re recognition via non-metric similarity measu probability evaluator can be used similarity measure for the GNG.…”

Section: Cross-domain Mergence Recognitionmentioning

confidence: 99%

Robust face recognition via transfer learning for robot partner

Tay

Botzheim

Loo

et al. 2014

2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space (RiiSS)

Self Cite

View full text Add to dashboard Cite

Face recognition is crucial for human-robot interaction. Robot partners are required to work in real-time under unconstrained condition, yet, do not restrict the personal freedom of human occupants. On the other hand, due to its limited computational capability, a tradeoff between accuracy and computational load needs to be made. This tradeoff can be alleviated via the introduction of informationally structured space. For this paper, transfer learning is employed to perform unconstrained face recognition, where templates are constructed from domains acquired from various image-capturing devices, which is a subset of sensors from the informationally structured space. Given the environmental conditions, appropriate templates are used for recognition. Currently, different database images are used to simulate different environmental conditions. The templates can be easily learned and merged via a reformulated joint probabilistic face verification method, which reduces significantly the processing load. Tested on standard databases, experimental studies show that specific and small target domain samples can boost the recognition performance without imposing strain on computation.

show abstract

Section: Cross-domain Mergence Recognitionmentioning

confidence: 99%

Robust face recognition via transfer learning for robot partner

Tay

Botzheim

Loo

et al. 2014

2014 IEEE Symposium on Robotic Intelligence in Informationally Structured Space (RiiSS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Unlike classical clustering algorithms, the GNG algorithm has an adaptable network structure that makes it suitable for the task of learning the topology of highdimensional data sets (Zaki and Yin, 2008;Linda and Manic, 2009;Bouguelia et al, 2015). This algorithm has gained significant interest in a number of fields, especially in the field of computer vision such as: image compression (García-Rodríguez et al, 2007); human gestures recognition (Angelopoulou et al, 2011;Botzheim and Kubota, 2012;García-Rodríguez et al, 2012), three-dimensional feature extraction (Donatti and Würtz, 2009;Viejo et al, 2012;Morell et al, 2014), and three-dimensional surface reconstruction (Noguera et al, 2008;Cretu et al, 2008;Rêgo et al, 2010;Fišer et al, 2013;Orts-Escolano et al, 2014;Jimeno-Morenilla et al, 2013, 2016. The GNG algorithm is also gaining increasing interest in a number of other fields such as medicine (Cselényi, 2005;Oliveira Martins et al, 2009;Angelopoulou et al, 2015); robotics (Carlevarino et al, 2000;Ferrer, 2014); economics (Lisboa et al, 2000;Decker, 2005); industrial applications (Cirrincione et al, 2011;; communications (Bougrain and Alexandre, 1999), astronomy (Hocking et al, 2015);geography (Figueiredo et al, 2007); and biology (Ogura et al, 2003).…”

Section: Introductionmentioning

confidence: 99%

Regional frequency analysis using Growing Neural Gas network

Abdi

Hassanzadeh

Ouarda

2017

Journal of Hydrology

View full text Add to dashboard Cite

The delineation of hydrologically homogeneous regions is an important issue in regional hydrological frequency analysis. In the present study, an application of the Growing Neural Gas (GNG) network for hydrological data clustering is presented. The GNG is an incremental and unsupervised neural network, which is able to adapt its structure during the training procedure without using a prior knowledge of the size and shape of the network. In the GNG algorithm, the Minimum Description Length (MDL) measure as the cluster validity index is utilized for determining the optimal number of clusters (subregions). The capability of the proposed algorithm is illustrated by regionalizing drought severities for 40 synoptic weather stations in Iran. To fulfill this aim, first a clustering method is applied to form the sub-regions and then a heterogeneity measure is used to test the degree of heterogeneity of the delineated sub-regions. According to the MDL measure and considering two different indices namely CS and Davies-Bouldin (DB) in the GNG network, the entire study area is subdivided in two sub-regions located in the eastern and western sides of Iran. In order to evaluate the performance of the GNG algorithm, a number of other commonly used clustering methods, like K-means, fuzzy Cmeans, self-organizing map and Ward method are utilized in this study. The results of the heterogeneity measure based on the L-moments approach reveal that only the GNG algorithm successfully yields homogeneous sub-regions in comparison to the other methods.

show abstract

Structured Learning for Extraction of Daily Life Log Measured by Smart Phone Sensors

Botzheim

Kubota

2015

Knowledge-Based Information Systems in Practice

View full text Add to dashboard Cite

Growing neural gas for information extraction in gesture recognition and reproduction of robot partners

Cited by 9 publications

References 13 publications

Robust face recognition via transfer learning for robot partner

Robust face recognition via transfer learning for robot partner

Regional frequency analysis using Growing Neural Gas network

Structured Learning for Extraction of Daily Life Log Measured by Smart Phone Sensors

Contact Info

Product

Resources

About