Face recognition based on eigen features of multi scaled face components and an artificial neural network

Reddy, K. Rama Linga; Babu, G. Rama Mohan; Kishore, Lal

doi:10.1016/j.procs.2010.11.009

Cited by 15 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average results for 20 trials are reported in Table 11a. We also compare our results with the previously reported results on this dataset [32,33]. Finally 9 random images of each person are used for training and the remaining image for testing (ratio of 9:1).…”

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 67%

“…To start with, an experiment is performed using ratios 4:6, 6:4, 7:3, 8:2 and, the respective average recognition rates for 10 trials have been obtained as tabulated in Table 10. The results reveal that the proposed method exhibits better performance when compared to the existing methods [32]. In the next phase, five images of each person are randomly selected for training and the remaining five for testing (ratio of 5:5).…”

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 97%

“…This is repeated for 10 trials and the average recognition rate obtained is compared with other existing techniques in Table 11b [34,35,36,37,38]. Graphs have been plotted for each of the [33] 93.4% HSemi-RS[E] [33] 94.2% PSemi-RS[M] [33] 94.5% PSemi-RS[E] [33] 95.0% PCA+BP [32] 96.4% PCA+RBF [32] 96.6% LDA+BP [32] 96.9% LDA+RBF [32] 97.1% Proposed method (Square) 97.1% …”

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 99%

See 2 more Smart Citations

DFT domain Feature Extraction using Edge-based Scale Normalization for Enhanced Face Recognition

Manikantan

Ramachandran²

2012

Journal of Advanced Computer Science &Amp; Technology

View full text Add to dashboard Cite

This paper proposes a novel preprocessing technique in order to improve the performance of a Face Recognition (FR) system. The proposed Edge-based Scale Normalization (ESN) process involves the use of scale normalization along with edge detection as a preprocessing technique in order to eliminate unwanted background details in face images. Feature extraction is performed on the preprocessed image using Discrete Fourier Transform (DFT). The DFT spectrums of these images extract the low frequency coefficients required for face recognition. These important features are selected through a rhombus-shaped mask around the center of the DFT spectrum. Further optimization in feature selection is achieved through Binary Particle Swarm Optimization (BPSO) technique. Experimental results, obtained by applying the proposed algorithm on Cambridge ORL and Extended YaleB face databases, show that the proposed system outperforms other FR systems. A significant increase in the recognition rate and a substantial reduction in the number of features is observed. Significant dimensionality reduction by more than 98.5% and improved recognition rate of 98% are achieved for both datasets.

show abstract

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 67%

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 97%

Section: Comparison With Other Face Recognition Systemsmentioning

confidence: 99%

See 1 more Smart Citation

DFT domain Feature Extraction using Edge-based Scale Normalization for Enhanced Face Recognition

Manikantan

Ramachandran²

2012

Journal of Advanced Computer Science &Amp; Technology

View full text Add to dashboard Cite

show abstract

“…Prof. K.Rama Linga Reddy, G.R. Babu, and Dr. Lal Kishore [10] present a paper based on face recognition using artificial neural network. The Principal Component Analysis (PCA) or Linear Discriminant Analysis (LDA) method is employed.…”

Section: Related Workmentioning

confidence: 99%

Boltay Hath for Indian Sign Language Recognition

kaur¹,

Banga²

2014

IJAIS

View full text Add to dashboard Cite

In this research work it is discussed that how a gesture recognition system for alphabetical hand gestures is built. The main motive was to develop a system that can simplify the way that the normal human being interact with the deaf and dump people without the need of interpretator . This system also provides the easy way of humans interaction with computers. This system is designed using MATLAB instead of neural network. In this system Eigen vector and Eigen value techniques only in MATLAB are used. The basis of our method is a fast detection process to obtain the meaningful hand region from the whole image, which is able to deal with a large number of hand gestures against different indoor backgrounds and lighting condition, and a recognition process that identifies the hand gestures from the images of the normalized hand. Experiments show that the system can achieve a 99% recognition rate and is suitable for real-time applications.

show abstract

“…We use SVD to discover the features in X-ray images that are relevant for classification. Although SVD has been used to generate the input to the neural network [21,22] and to improve the training of the networks [23,24,25], to the best of our knowledge, the analysis of the statistical correlations of the feature maps in the early layers of a CNN has not been utilized to discriminate X-ray images of samples of epoxy resins.…”

Section: Introductionmentioning

confidence: 99%

Visible fingerprint of X-ray images of epoxy resins using singular value decomposition of deep learning features

Avalos

Akagi

Nishiura

2021

Computational Materials Science

View full text Add to dashboard Cite

Face recognition based on eigen features of multi scaled face components and an artificial neural network

Cited by 15 publications

References 18 publications

DFT domain Feature Extraction using Edge-based Scale Normalization for Enhanced Face Recognition

DFT domain Feature Extraction using Edge-based Scale Normalization for Enhanced Face Recognition

Boltay Hath for Indian Sign Language Recognition

Visible fingerprint of X-ray images of epoxy resins using singular value decomposition of deep learning features

Contact Info

Product

Resources

About