DWT based Feature Extraction using Edge Tracked Scale Normalization for Enhanced Face Recognition

Rinky, B.P.; Mondal, Payal; Manikantan, K.; Ramachandran, S.

doi:10.1016/j.protcy.2012.10.041

Cited by 32 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Average RR(%) DFT + DCT [21] 80.23 Selective Illumination Enhancement + Thresholded DWT [22] 85.41 Histogram Equalization + Laplacian-Gradient Masking + DWT [23] 85.71 Background Removal + Scale Normalization + Log Transform [24] 86.14 Edge Tracked Scale Normalization + Log Transform [25] 88.00 DWT Dual-subband Frequency-domain Feature Extraction (DDFFE) + Threshold-Based Binary Particle Swarm Optimization (ThBPSO) [26] 86.81 Proposed Technique 91.21 (1,1,9,9) was chosen due to the high RR obtained. The Experimental Results for CMUPIE pose database for different training to testing ratios are shown in Fig.…”

Section: Methodsmentioning

confidence: 99%

Face recognition using Gabor-Feature-based DFT shifting

Bhamidipati

rana

Manikantan

et al. 2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

Self Cite

View full text Add to dashboard Cite

The appearance of the face varies drastically when background and pose change. Variations in these conditions make Face Recognition (FR) an even more challenging and difficult task. In this paper we propose two novel techniques, viz., Gabor-Feature-based DFT Shifting (GFDS) and Skin-detectionbased Background Removal, to improve the performance of the FR system. GFDS is used to detect and neutralize the image variations like location, scale, pose etc., thereby enhancing Face Recognition. Skin-detection-based Background Removal is used to ascertain the shape of the face and distance from the camera to eliminate complex backgrounds. Experimental results show the promising performance of the proposed techniques for Face Recognition on three benchmark face databases, namely, Color FERET, Pointing Head Pose and CMUPIE databases.

show abstract

Section: Methodsmentioning

confidence: 99%

Face recognition using Gabor-Feature-based DFT shifting

Bhamidipati

rana

Manikantan

et al. 2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Beside classical implementations of DWT (Surabhi et al;Yaji et al;Rinky et al;Roohi et al;Prabhu et al;Niveditha et al;, other versions were employed, such as Threshold based DWT (Vidya et al;Murthy et al;, Raster Scan Discrete Wavelet Transform (RDWT) (Khashu et al; and a hybrid approach using Thresholded Wavelet Edge Enhancement Transform (TWEET) and DWT (Hegade et al;. Methods employing modi ed versions of BPSO were proposed, such as Threshold Binary Particle Swarm Optimization (ThBPSO) (Krisshna et al;.…”

Section: Particle Swarm Optimizationmentioning

confidence: 99%

Swarm intelligence and evolutionary computation approaches for 2D face recognition: a systematic review

Plichoski

Chidambaram

Parpinelli

2018

RBCA

View full text Add to dashboard Cite

A wide range of approaches for 2D face recognition (FR) systems can be found in the literature due to its high applicability and issues that need more investigation yet which include occlusion, variations in scale, facial expression, and illumination. Over the last years, a growing number of improved 2D FR systems using Swarm Intelligence and Evolutionary Computing algorithms have emerged. The present work brings an up-to-date Systematic Literature Review (SLR) concerning the use of Swarm Intelligence and Evolutionary Computation applied in 2D FR systems. Also, this review analyses and points out the key techniques and algorithms used and suggests some directions for future research.Key words: Bio-inspired algorithms; Evolutionary algorithms; Face Recognition; Natural Computing; Optimization; Swarm algorithms ResumoUma ampla gama de abordagens para sistemas de reconhecimento facial (FR) 2D pode ser encontrada na literatura devido a sua alta aplicabilidade e também por questões que necessitam de mais investigação, incluindo oclusão, variações de escala, expressão facial e iluminação. Nos últimos anos, um número crescente de sistemas de FR 2D usando algoritmos de Inteligência de Enxame e Computação Evolucionária surgiram. O presente trabalho traz uma Revisão Sistemática de Literatura (SLR) atualizada sobre o uso da Inteligência de Enxame e Computação Evolucionária aplicada em sistemas de FR 2D. Além disso, esta revisão analisa e aponta as principais técnicas e algoritmos utilizados e sugere alguns direcionamentos para pesquisas futuras.

show abstract

“…Scale Normalization is done to eliminate the shift variance in an image and extract only the face. The contours of the face is identified using edge detection and pixels outside these edges are removed [6].…”

Section: A Pre-processing Techniquesmentioning

confidence: 99%

“…[19] uses Selective Illumination Enhancement Technique (SIET) to obtain uniform illumination over the entire image. Edge Tracked Scale Normalization (ETSN) is employed to overcome the presence of background in [6]. Ref.…”

Section: E Comparison With Other Fr Systemsmentioning

confidence: 99%

Face Recognition using Wavelet filtering and Dual Pose testing

Smrthi

Soumya

Manikantan

et al. 2013

2013 Annual IEEE India Conference (INDICON)

Self Cite

View full text Add to dashboard Cite

Face Recognition (FR) under varying pose, background and illumination conditions is challenging. In this paper, we propose four novel techniques, viz., Dual Pose testing (DPT), Color Based Background Removal (CBBR), Wavelet filtering and Modified Binary Particle Swarm Optimization (MBPSO), to improve the performance of a FR system. DPT is used to neutralize pose variations, CBBR removes cluttered background, Wavelet filtering is used for denoising and MBPSO, along with a modified fitness function, is used to reduce the number of selected features for recognition. Individual stages of the FR system are examined and an attempt is made to improve each stage. Experimental results show the promising performance of the proposed techniques for face recognition on four benchmark face databases, namely, Color FERET, Pointing Head Pose, CMUPIE and Extended YaleB.

show abstract

DWT based Feature Extraction using Edge Tracked Scale Normalization for Enhanced Face Recognition

Cited by 32 publications

References 9 publications

Face recognition using Gabor-Feature-based DFT shifting

Face recognition using Gabor-Feature-based DFT shifting

Swarm intelligence and evolutionary computation approaches for 2D face recognition: a systematic review

Face Recognition using Wavelet filtering and Dual Pose testing

Contact Info

Product

Resources

About