Table 2.

Different state-of-the-art techniques including featuring engineering and classification methods for facial gender recognition for FERET (adult faces) and UTK face dataset (juvenile faces).

Dataset	Authors	Feature extraction	Accuracy
		Classification	(%)
FERET	Leng and Wang [16]	Gabor-SVM, Fuzzy	98.0
	Rai and Khanna [17]	Gabor-2DPCA-SVM	98.2
	Aroussi et al. [18]	DWT-SVM	92
	Mohamed et al. [19]	DCT, DWT-SVM	95
	Wang et al. [20]	Gabor, SIFT -AdaBoost	97.0
	Ozbudak et al. [21]	DWT-PCA-FDA	9
	Lu and shi [22]	2D PCA-SVM (RBF)	94.8
	Bissoon and Viriri [23]	PCA-LDA	85
	Jain and Huang [24]	ICA-LDA	99.3
	Tapia and Perez [25]	LBP + Intensity+	99.1
		Shape-SVM
	Makinen and raisamo [26]	LBP, Haar-ANN, SVM	92.9
	Alamri et al. [27]	LBP, WLD-N.Neighbor	98.8
	Moeini et al. [28]	LGBP-SVM	98.5
	Patel et al. [29]	CoLBP-SVM	93.9
	Annalakshmi et al. [30]	SLBP + HOG-SVM	97.6
	Aslam et al. [31]	CNN (VGG-16)	98.9
	Afifi and Abdelhamed [32]	Foggy face-Deep CNN	99.3
UTK	Swaminathan et al. [33]	Face Embed (FE)-SVM	88.4
		FE-logistic regression	92.4
		FE-naive-bayes	89.4
		Fe-KNN	97.0
		FE-decision trees	93.2
	Teru and Chakraborty [1]	CNN	89.5
		CNN-WL (weight loss)	88.8
		Fader CNN	84.8
	Song and Shmatikov [34]	CNN	90.4
	Bragman et al. [35]	CNN	92.5
	Nagpal et al. [36]	CNN	94.6
	Das et al. [37]	MTCNN	98.2
	Abdolrashidi [38]	Ensemble of ResNet	96.5
AD	Hassner et al. [39]	LBP + FPLBP-SVM	79.3
	Khan et al. [40]	PCS-RDF	91.4
FG-NET	Nayak and Indiramma [41]	PCA	61.13