Appearance and shape based facial recognition system using PCA and HMM

Islam, Rafiul; Toufiq, Rizoan; Rahman, Fayzur

doi:10.1109/icece.2012.6471469

Cited by 5 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use the median filtering and histogram equalization [6] to enhance the human face image, eliminate image noise and improve image quality, so that high accuracy and detection rate can be achieved.…”

Section: B Preprocessingmentioning

confidence: 99%

Viewing distance measurement using a single camera

Pang

Zhao

Chen

et al. 2014

2014 IEEE 7th Joint International Information Technology and Artificial Intelligence Conference

View full text Add to dashboard Cite

In order to determine the viewing distance with low complexity and high transportability, a measurement method using a single camera is proposed in this paper. After the image of the face of the viewer is taken by a single camera, it is input to the preprocessing component and the resolution of the image is transformed into a given resolution for fitting function. The pixel distance between binocular pupils in the image is determined in the image processing component. Then, the viewing distance is calculated by applying the data of the binocular pupil pixel distance into the fitting function. Experimental results show that the relative error between the detected viewing distance and the actual viewing distance of the proposed method can be controlled within ± 1.2% and the standard deviation can be controlled below 2.1631 cm within 120cm distance. And the proposed method has also stability and universal implantable capability.

show abstract

Section: B Preprocessingmentioning

confidence: 99%

Viewing distance measurement using a single camera

Pang

Zhao

Chen

et al. 2014

2014 IEEE 7th Joint International Information Technology and Artificial Intelligence Conference

View full text Add to dashboard Cite

show abstract

“…The Wavelet Transform (WT) is also used either in continuous or discrete form as in [15,16,17,18,19,20,21,22,23,24]. In [15,17]; [26,27], Singular Value Decomposition (SVD) [28], Fast Fourier Transform (FFT) and the Partial Least Squares (PLS) [29], Canonical Correlation Analysis (CCA) [30], Active Appearance Model and Shape Model [31], and Separable Lattice [32,33].…”

Section: Related Workmentioning

confidence: 99%

“…In [19], 64 states were used, while in [24], the authors used 9-state HMM for Yale database and 15state HMM for ORL database. Some researchers used variable number of states; (5-25) states and the best is 12 states [31], states and the best is 40 [32], (4)(5)(6)(7)(8)(9)(10)(11)(12) states and the best is 8 [33]. The first effort of using 3-state HMM in FR is carried out in [14].…”

Section: Related Workmentioning

confidence: 99%

Face Recognition using Maximum Variance and SVD of Order Statistics with only Three States of Hidden Markov Model

Farhan¹,

Al-Muifraje²,

Saeed³

2016

IJCA

View full text Add to dashboard Cite

This paper presents a fast face recognition (FR) method using only three states of Hidden Markov Model (HMM), where the number of states is a major effective factor in computational complexity. Most of the researchers believe that each state represents one facial region, so they used five states or more according to the number of facial regions. In this work, a different idea has been proven, where the number of states is independent of the number of facial regions. The image is resized to 56x56, and order-statistic filters are used to improve the preprocessing operations and thereby reducing the influence of the illumination and noise. Up to three coefficients of Singular Value Decomposition (SVD) are utilized to describe overlapped blocks of size 5x56. Experimental results show that the proposed work manages to achieve 100% recognition rate on ORL face database using the maximum variance and two coefficients of SVD and can, therefore, be considered as the fastest face recognition type.

show abstract

“…; Toufiq, R. and Rahman, M.F. described appearance and shape based facial recognition system using PCA and HMM [8]. In the same year Singh, K.R.…”

Section: Literature Surveymentioning

confidence: 99%

A novel method to achieve optimization in facial expression recognition using HMM

Devi¹,

Rao²

2015

2015 International Conference on Signal Processing and Communication Engineering Systems

View full text Add to dashboard Cite

Human-Computer Interaction is an emerging field ofComputer Science where, Computer Vision, especially facial expression recognition occupies an essential role. There are so many approaches to resolve this problem, among them HMM is a considerable one. This paper aims to achieve optimization in both, the usage of number of states and the time complexity of HMM runtime. It also focusses to enable parallel processing which aims to process more than one image simultaneously.

show abstract

Appearance and shape based facial recognition system using PCA and HMM

Cited by 5 publications

References 27 publications

Viewing distance measurement using a single camera

Viewing distance measurement using a single camera

Face Recognition using Maximum Variance and SVD of Order Statistics with only Three States of Hidden Markov Model

A novel method to achieve optimization in facial expression recognition using HMM

Contact Info

Product

Resources

About