Implementation of deep neural networks (DNN) with batch normalization for batik pattern recognition

Abstract

One of the most famous cultural heritages in Indonesia is batik. Batik is a specially made drawing cloth by writing Malam (wax) on the cloth, then processed in a certain way. The diversity of motifs both in Indonesia and the allied countries raises new research topics in the field of information technology, both for conservation, storage, publication and the creation of new batik motifs. In computer science research area, studies about Batik pattern have been done by researchers and some algorithms have been successfully applied in Batik pattern recognition. This study was focused on Batik motif recognition using texture fusion feature which is Gabor, Log-Gabor, and GLCM; and using PCA feature reduction to improve the classification accuracy and reduce the computational time. To improve the accuracy, we proposed a Deep Neural Network model to recognise batik pattern and used batch normalisation as a regularises to generalise the model and to reduce time complexity. From the experiments, the feature extraction, selection, and reduction gave better accuracy than the raw dataset. The feature selection and reduction also reduce time complexity. The DNN+BN significantly improve the accuracy of the classification model from 65.36% to 83.15%. BN as a regularization has successfully made the model more general, hence improve the accuracy of the model. The parameters tuning also improved accuracy from 83.15% to 85.57%.

Modernizing Batik Clothes for Community Enterprises Using Creative Design and Colorimetry

“…Nevertheless, a computer-aided design was not employed in this work to avoid overloading them with too many new things at once. Computer programs were previously proven successful in batik designs [17][18][19][20], but the local batik artisans were not keen to use them. The gradual incorporation of new techniques into traditional craftsmanship is an appropriate way to transform batik into modern fashion without losing its local identity and charm.…”

“…Laitupa et al demonstrated the computer-based creation of new batik motifs [17], whereas Tian et al developed automatic batik flower patterns based on fractal geometry [18]. For pattern recognition, neural networks and deep learning have been implemented on batik fabrics [19,20]. To characterize fabric colors, smartphone colorimetry was demonstrated and compared with the standard CIE L*a*b* color measurement using a HunterLab spectrophotometer [21].…”

Dropout, a basic and effective regularization method for a deep learning model: a case study

“…Method Explicit Dropout [19] Weight degradation [22] DropConnect [20] Adjust the network size [23] Pooling stochastique [21] Batch normalization [24] (a) (b)…”

Summarization of COVID-19 news documents deep learning-based using transformer architecture

“…Perform on small batch sizes dependent to reduce memory cost, normalization can rely for increase training accuracy [25]. The normalization layer minimize parameter change during propagated through the deep networks [26].…”