An Optimized Face Recognition System Using Cuckoo Search

Malhotra, Preeti; Kumar, Dinesh

doi:10.1515/jisys-2017-0127

Cited by 16 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results proved the superiority of proposed method (97.5% recognition rate with just 24 features) over other leading optimization techniques such as CS (97% with 48 features), GA(96.5% with 28 features) and PSO (96.5% with 28 features). They further carried forward their research in 2017 in whichPreeti et al [33]suggested anFR system using the Cuckoo Search (CS) optimization technique where features were extracted using combination of PCA and DCT in order to achieve high accuracy rates. Results show that CS gave 88% recognition rate with 10 features only which are equivalent to just 10% of the features used in PCA and gave 96.50% recognition rate with just 34 features which is approximately 35% of the features used in DCT-PCA approach.…”

Section: Feature Selectionmentioning

confidence: 99%

A Comprehensive Survey of Feature Extraction and Feature Selection Techniques of Face Recognition System

Saini¹,

Malhotra²

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

Self Cite

View full text Add to dashboard Cite

Among various types of biometric techniques it is the face recognition that gains huge popularity in the last few decades due to its vast applicationsand more user friendly nature.Face Recognition is the procedure of identification and verification of a person's identity using his face. Main steps involved in a FR System are Face Detection, Feature Extraction, Feature Selection and Recognition. Feature Extraction and Feature Selection are the two main phases to be focused on in order to get a good FR System. In this paper, we have carried out anextensive literature review on face recognition focusing on feature extraction and feature selection phases a bit more.

show abstract

Section: Feature Selectionmentioning

confidence: 99%

A Comprehensive Survey of Feature Extraction and Feature Selection Techniques of Face Recognition System

Saini¹,

Malhotra²

2021

Proceedings of the Fist International Conference on Advanced Scientific Innovation in Science, Engineering and Technology, ICA

Self Cite

View full text Add to dashboard Cite

show abstract

“…These works mainly use some features like Gabor features [12], wavelet [14] and fused them with dimensionality reduction techniques like LDA [12] or PCA [5] and then used classifiers like SVM citea31 or ANN [12], [14], [5]. In addition to this, many techniques reported in the literature have implemented nature-inspired optimization techniques like cuckoo search [13], PSO (Particle Swarm Optimization) [32] for face recognition. Recently, due to the promising success of deep architectures like CNN (Convolutional Neural Network), researchers have started using these architectures for face recognition.…”

Section: Fig 2: Flow Of Feature Extractionmentioning

confidence: 99%

Smart Gate: Intelligent Security System Based on Face Recognition

Shah*,

Shukla,

Pandya

2020

IJITEE

View full text Add to dashboard Cite

Features of Human face is one of the unique biometrics used for identifying and recognizing humans. This makes face recognition system an integral component of numerous applications like identity verification of personnel at gates in many organizations, for controlled access of confidential resources, recognizing intruders by nationwide defense institutions, and such many more. Due to this the unavoidable need of face recognition system, practitioners and researchers are putting their continuous efforts to rectify and optimize the face recognition system for different perspectives in terms of accuracy, time, and storage. The techniques are also optimized for face captured at different degree of orientation, change of facial expression with time, lighting condition, with and without eyeglass and other props, but as isolated solutions. The main aim of the paper is to propose a system that can be installed at any door or gate which would operate based on integrated face recognition. The major contribution of this paper is twofold: i) An integrated face recognition solution optimized for recognizing multiple people faces captured at different orientations and even wearing eyeglasses of different shapes, sizes and materials ii) Smart Gate system being activated upon successful recognition of all faces captured simultaneously.

show abstract

“…Such algorithms are developed on the basis of physical and biological system's behaviour that exist in nature. Examples include genetic algorithms (GA) (Harandi et al, 2004), Differential Evolution (DE) (Khushaba et al, 2008; Yang et al, 2016), Cuckoo Search (CS) (Malhotra & Kumar, 2019), particle swarm optimization (PSO) (Ramadan & Abdel‐Kader, 2009), harmony search, and so on. Apart from these, new hybrid algorithms are reported by researchers to improve the recognition and selection accuracy.…”

Section: Introductionmentioning

confidence: 99%

Modified spider monkey optimization algorithm based feature selection and probabilistic neural network classifier in face recognition

Balasubramanian¹,

Periyasamy

Kishore

2022

Expert Systems

View full text Add to dashboard Cite

This paper proposes a novel and robust predictive method using modified spider monkey optimization (MSMO) and probabilistic neural network (PNN) for face recognition. The limitation of the traditional spider monkey optimization (SMO) approach to obtaining an optimal solution for classification problems is overcome by enhancing the performance of SMO by modifying the perturbation rate with a non-linear function, thereby improving the convergence of SMO. The framework comprises image preprocessing, feature extraction using dual tree complex wavelet transform (DT-CWT), feature selection using the modified spider monkey optimization algorithm (MSMO), and classification using PNN. The proposed method is tested on the Yale and AR Face datasets. Experimental outcomes reveal that the proposed framework attain an accuracy of 99.4% with appreciable sensitivity, specificity, and G-mean. To examine the efficacy of MSMO, parametric studies are conducted, which showed that MSMO converges faster with high fitness when compared to similar evolutionary algorithms like Genetic Algorithm (GA), Grey Wolf Optimization Algorithm (GWO), Particle Swarm Algorithm (PSO), and Cuckoo Search (CS) in selecting the optimal feature set. The MSMO-PNN method outperforms similar state-of-the-art methods, which reveals that the method proposed is competitive. The proposed model is robust to Gaussian and salt-pepper noise, obtaining the highest accuracy of 97.89% for varied noise density and variance.

show abstract

An Optimized Face Recognition System Using Cuckoo Search

Cited by 16 publications

References 30 publications

A Comprehensive Survey of Feature Extraction and Feature Selection Techniques of Face Recognition System

A Comprehensive Survey of Feature Extraction and Feature Selection Techniques of Face Recognition System

Smart Gate: Intelligent Security System Based on Face Recognition

Modified spider monkey optimization algorithm based feature selection and probabilistic neural network classifier in face recognition

Contact Info

Product

Resources

About