Face recognition via Deep Stacked Denoising Sparse Autoencoders (DSDSA)

Görgel, Pelin; ŞİMŞEK>, Ahmet

doi:10.1016/j.amc.2019.02.071

Cited by 48 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 4 showed our results for three configurations of (P, R), respectively, suggesting that our WSBP and CLBP S M(m 1 , μ 2 ) achieved the highest recognition rate. Table 5 compared our results with a deep learning approach based on Deep Stack Denoising Sparse Autoencoders (DSDSA) [13]. As can be seen from these tables, even using one single small scale (P, R) = (4, 2), our descriptor WSBP (Ours 1), CLBP S M(m 1 , μ 2 ) reached the recognition rate of 98.83%, 98.96%, respectively, which were greater than the performance of DSDSA.…”

Section: Results With Caltech 1999 and Kdef Datasetsmentioning

confidence: 99%

Weighted statistical binary patterns for facial feature representation

2021

View full text Add to dashboard Cite

We present a novel framework for efficient and robust facial feature representation based upon Local Binary Pattern (LBP), called Weighted Statistical Binary Pattern, wherein the descriptors utilize the straight-line topology along with different directions. The input image is initially divided into mean and variance moments. A new variance moment, which contains distinctive facial features, is prepared by extracting root k-th. Then, when Sign and Magnitude components along four different directions using the mean moment are constructed, a weighting approach according to the new variance is applied to each component. Finally, the weighted histograms of Sign and Magnitude components are concatenated to build a novel histogram of Complementary LBP along with different directions. A comprehensive evaluation using six public face datasets suggests that the present framework outperforms the state-of-the-art methods and achieves 98.51% for ORL, 98.72% for YALE, 98.83% for Caltech, 99.52% for AR, 94.78% for FERET, and 99.07% for KDEF in terms of accuracy, respectively. The influence of color spaces and the issue of degraded images are also analyzed with our descriptors. Such a result with theoretical underpinning confirms that our descriptors are robust against noise, illumination variation, diverse facial expressions, and head poses.

show abstract

Section: Results With Caltech 1999 and Kdef Datasetsmentioning

confidence: 99%

Weighted statistical binary patterns for facial feature representation

2021

View full text Add to dashboard Cite

show abstract

“…Autoencoder (AE) layer is a specific type of artificial neural network composed of an encoder and a decoder. It is used to extract complex feature from data complex and to generate new data [26] with as much accuracy and low error as possible. The output of the first layer AE is taken as the input of the following layer.…”

Section: Deep Network Using Autoencoder (Dn-ae)mentioning

confidence: 99%

Application and Comparison of Machine Learning Algorithms for Predicting Mass Loss of Cement Raw Materials due to Decarbonation Process

Boukhari¹

2020

RIA

View full text Add to dashboard Cite

The purpose of this work is to predict the mass loss of cement raw materials during the decarbonation process. The mass loss is influenced by the interaction of several parameters such as chemical composition of raw material, particle size, temperature range of decarbonation and time exposed. Therefore, predicting mass loss based on experimental parameters data is often challenging. For this reason, various machine learning algorithms such as deep networks using autoencoder DN-AE, artificial neural networks optimized by particle swarm optimization PSO-ANN, ANN optimized by ant colony optimization ACO-ANN and ANN are proposed to predict the mass loss. In this research, all models have been applied successfully to predict the mass loss with high accuracy. The results obtained have shown the superiority of DN-AE compared to PSO-ANN, ACO-ANN and ANN. In addition, PSO-ANN and ACO-ANN have a better performance than the individual use of ANN. The values of adjusted R2 indicate that 99.11%, 98.66%, 98.27% and 97.03% of data are explained by DN-AE, ACO-ANN, PSO-ANN and ANN respectively with scatter index (SI) less than 0.1 and maximum error less than 3.32%. Finally, the results justify that all models proposed can be employed to predict the mass loss as alternative tools.

show abstract

“…Deep autoencoders have been widely used in pre-trained deep neural networks, such as in coevolution neural networks (CNNs) and recurrent neural networks (RNNs), and reported as a useful way to represent the original variables. In addition, deep autoencoders have been successfully used in the fields of speech recognition [31], 3D shape retrieval [32], face recognition [33][34][35], and more. Next, we introduce the proposed algorithm.…”

Section: Deep Autoencodermentioning

confidence: 99%

Double Deep Autoencoder for Heterogeneous Distributed Clustering

Chen

Huang

2019

Information

View full text Add to dashboard Cite

Given the issues relating to big data and privacy-preserving challenges, distributed data mining (DDM) has received much attention recently. Here, we focus on the clustering problem of distributed environments. Several distributed clustering algorithms have been proposed to solve this problem, however, previous studies have mainly considered homogeneous data. In this paper, we develop a double deep autoencoder structure for clustering in distributed and heterogeneous datasets. Three datasets are used to demonstrate the proposed algorithms, and show their usefulness according to the consistent accuracy index.

show abstract

Face recognition via Deep Stacked Denoising Sparse Autoencoders (DSDSA)

Cited by 48 publications

References 28 publications

Weighted statistical binary patterns for facial feature representation

Weighted statistical binary patterns for facial feature representation

Application and Comparison of Machine Learning Algorithms for Predicting Mass Loss of Cement Raw Materials due to Decarbonation Process

Double Deep Autoencoder for Heterogeneous Distributed Clustering

Contact Info

Product

Resources

About