Publication Type:

Journal Article

Source:

Advances in Intelligent Systems and Computing, Springer Verlag, Volume 709, p.445-456 (2018)

URL:

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85056259590&doi=10.1007%2f978-981-10-8633-5_44&partnerID=40&md5=6d90009daa53fa212ef4231375e36503

Keywords:

Classification (of information), Classification accuracy, Classification algorithm, Classification performance, Computer vision, Convolution, Convolutional neural network, Convolutional Neural Networks (CNN), Deep learning, extraction, Feature extraction, Feature extraction methods, Hierarchical agglomerative clustering, image classification, Neural networks, Probabilistic ensemble, Program processors

Abstract:

For the customary classification algorithms, performance depends on feature extraction methods. However, it is challenging to extract such unique features. With the advancement of Convolutional Neural Networks (CNN), which is the widely used Deep Learning Framework, there seems to be a substantial improvement in classification performance combined with implicit feature extraction process. But, training a CNN is an intensive process that often needs high computing machines (GPU) and may take hours or even days. This may confine its application in a few situations. Considering these factors, an ensemble architecture is modelled, that is trained on a subset of mutually exclusive classes, grouped by Hierarchical Agglomerative Clustering based on similarity. A new Probabilistic Ensemble-Based Classifier is designed for classifying an image. This new model is trained in comparatively lesser time with classification accuracy comparable to the traditional ensemble model. Also, GPUs are not necessary for training this model, even for large datasets. © Springer Nature Singapore Pte Ltd. 2018

Notes:

cited By 0

Cite this Research Publication

A. Neena and M. Geetha, “Image classification using an ensemble-based deep CNN”, Advances in Intelligent Systems and Computing, vol. 709, pp. 445-456, 2018.