Approximate nearest neighbor search using self-organizing map clustering for face recognition system

Yodkhad, Paitoon; Kawewong, Aram; Patanukhom, Karn

doi:10.1109/icsec.2014.6978186

Cited by 2 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also important to apply our approach with the modern features for unconstrained face recognition [29]. Another direction for further research is the usage of complex clustering techniques [34] to achieve the better classification accuracy and performance.…”

Section: Discussionmentioning

confidence: 99%

“…Nevertheless, it seems that the proposed approach is more efficient. For instance, the clustering with the self-organized map makes it possible to decrease the processing time in 3.8 times in comparison with an exhaustive search [34]. And our approach with the SC is as accurate as the brute force (3) ( Table 3), but it is 13-20 times faster (Table 4).…”

Section: Real Datamentioning

confidence: 98%

“…Centroid-based classification [30]. In order to reduce the time consumption in the NN search, the whole training set {X r } is clustered in order to perform search (3) only among centroids/prototypes of each cluster [34]. 2.…”

Section: Proposed Approachmentioning

confidence: 99%

See 2 more Smart Citations

Clustering and maximum likelihood search for efficient statistical classification with medium-sized databases

Savchenko

2015

Optim Lett

View full text Add to dashboard Cite

This paper addresses the problem of insufficient performance of statistical classification with the medium-sized database (thousands of classes). Each object is represented as a sequence of independent segments. Each segment is defined as a random sample of independent features with the distribution of multivariate exponential type. To increase the speed of the optimal Kullback-Leibler minimum information discrimination principle, we apply the clustering of the training set and an approximate nearest neighbor search of the input object in a set of cluster medoids. By using the asymptotic properties of the Kullback-Leibler divergence, we propose the maximal likelihood search procedure. In this method the medoid to check is selected from the cluster with the maximal joint density (likelihood) of the distances to the previously checked medoids. Experimental results in image recognition with artificially generated dataset and Essex facial database prove that the proposed approach is much more effective, than an exhaustive search and the known approximate nearest neighbor methods from FLANN and NonMetricSpace libraries.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Real Datamentioning

confidence: 98%

See 1 more Smart Citation

Clustering and maximum likelihood search for efficient statistical classification with medium-sized databases

Savchenko

2015

Optim Lett

View full text Add to dashboard Cite

show abstract

“…These feature vectors are known as class labels which is later used by classifiers to map the input unit with output unit in pattern recognition. Kohonen's self-organizing map [7] is applied to extract the discriminative feature from the problem space. The underlying principle of SOM-based feature extraction is that by removing the redundant data from problem space, the small size feature sets which contain discriminating information is retained.…”

Section: Som-based Feature Extractionmentioning

confidence: 99%

“…SOM is a variation of artificial neural network which applies unsupervised learning mechanism to study its residing environment. SOM has been widely used in clustering, predictive system and data compression [7]- [11]. Natita, Wiboonsak and Dusadee [12] reported that learning rate and neighbourhood functions are necessary parameters in SOM which can influence the results.…”

Section: Introductionmentioning

confidence: 99%

Effect of Neighbourhood Size Selection in SOM-Based Image Feature Extraction

Ng¹,

Chan²

2019

IJMLC

View full text Add to dashboard Cite

Feature extraction is one of the processes in pattern recognition systems. It is the procedure of selecting the best possible subset of input features from a high dimensional problem space and transforming them into a lower dimensional space. Mathematically, feature extraction can be perceived as dimensionality reduction problem. Kohonen's self-organizing map (SOM) is an unsupervised learning approach in which a group of neurons regularly adjusts their basic structure as a function of its experience and environment. Preliminary research reported that neighbourhood functions is one of the necessary parameters that influence the results. The neighbourhood size refers to the region covered by the activated neighbouring neurons in relation to the winner neuron in each iteration of learning. This study aims to evaluate the implementation of SOM in image feature extraction. Different neighbourhood size value was tested in the SOM learning process to observe the quality of the extracted feature. Gaussian neighbourhood function was applied to the SOM-based feature extraction in current study. This study also compared the feature extraction performance of different neighbourhood functions. Experimental results show that the resulting feature loses its details as the neighbourhood size increases. Gaussian neighbourhood function gives more significant extracted feature.Index Terms-Feature extraction, Gaussian neighbourhood function, high dimensionality, self-organizing map (SOM).

show abstract

Approximate nearest neighbor search using self-organizing map clustering for face recognition system

Cited by 2 publications

References 13 publications

Clustering and maximum likelihood search for efficient statistical classification with medium-sized databases

Clustering and maximum likelihood search for efficient statistical classification with medium-sized databases

Effect of Neighbourhood Size Selection in SOM-Based Image Feature Extraction

Contact Info

Product

Resources

About