Face recognition with Symmetric Local Graph Structure (SLGS)

Abdullah, Mohd Fikri Azli; Sayeed, Shohel; Anbananthen, Kalaiarasi Sonai Muthu; Bashier, Housam Khalifa; Azman, Azreen; Ibrahim, Siti Zainab

doi:10.1016/j.eswa.2014.04.006

Cited by 93 publications

(33 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recognition rate ThBPSO [17] 95.00 SLGS [14] 78.00 KLDA [15] 92.92 NNRW [18] 89.80 2D-NNRW [16] 91.90 The proposed method 97.50 …”

Section: Methodsmentioning

confidence: 99%

“…The CMC curves indicate a high recognition rate even at rank 1. We have shown some of the state of the art works [14], [15], [16] and [17] (the image size used in those experiments are same as ours i.e, 112x92) compared with our work in Table.I. In [14], using a symmetric region of 2 pixels width surrounding the central pixel, they computed a symmetric local graph structure around each pixel of the image to compute a LBP like pattern.…”

Section: B Experimentation On Orl Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Logarithmic dyadic wavelet transform based face recognition

Shekar

Rajesh

Kumari³

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

In this paper, we present a new local descriptor based on logarithmic dyadic wavelet transform. The interest points at different scales have been identified and a region of size 40x40 is considered around each interest point to obtain gradientorientation histogram in the transformed space. The chi square distance metric is used for classification. Extensive experiments have been conducted on standard face datasets such as ORL and LFW to demonstrate the suitability of the proposed descriptor for face recognition. A comparative analysis with some of the well known methods is also provided to argue that the proposed method is comparatively perform much better than the existing methods.

show abstract

“…Recognition rate ThBPSO [17] 95.00 SLGS [14] 78.00 KLDA [15] 92.92 NNRW [18] 89.80 2D-NNRW [16] 91.90 The proposed method 97.50 …”

Section: Methodsmentioning

confidence: 99%

Section: B Experimentation On Orl Datasetmentioning

confidence: 99%

Logarithmic dyadic wavelet transform based face recognition

Shekar

Rajesh

Kumari³

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

show abstract

“…Recognition rate ThBPSO [9] 95.00 SLGS [10] 78.00 KLDA [11] 92.92 NNRW [12] 89.80 2D-NNRW [13] 91.90 The proposed method 97.14 incorporates a wide variety of challenging illumination, pose, occlusion and scale variations. In our work, we have used the view-2 dataset for experimentation and according to the dataset protocol, we used images restricted training protocol without using the labels of the training faces.…”

Section: Methodsmentioning

confidence: 99%

Approximate radial gradient transform based face recognition

Shekar

Rajesh

2015

2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI)

View full text Add to dashboard Cite

In this paper, we propose a new local descriptor based on the approximate radial gradient transform. Initially, the interest points are detected using the difference of box filters. Then, the circular region of certain size around these interest points is represented using the approximate radial gradient transform and hence the descriptor is formed. We have conducted experiments on some of the well known face datasets such as ORL and LFW datasets to reveal the success of the proposed method and comparative analysis is provided to argue that the proposed method is on par with the other contemporary face recognition methods. 978-1-4799-8792-4/15/$31.00 c 2015 IEEE

show abstract

“…The simplicity of grayscale domain is commonly used in computer vision for moving object detection systems (Barcellos, Bouvie, Escouto, & Scharcanski, 2015;Karasulu & Korukoglu, 2012). Next, intelligent watermarking in biometric systems, that deals with grayscale texture masks, was discussed in Rabil, Tliba, Granger, and Sabourin (2013) whereas in Abdullah et al (2014) is presented a novel approach for face recognition by using Symmetric Local Graph Structure (SLGS). Moreover, a new method of using empirical mode decomposition (EMD) technique for facial emotion recognition was discussed in Ali, Hariharan, Yaacob, and Adom (2015).…”

Section: Introductionmentioning

confidence: 99%