Table 8.

Performance evaluation on Caltech-101 dataset

Author	Year	Features	Technique used	Number of classes	Accuracy (%)	Time (min)
Mahmood et al	2017	ResNet-152	ResNet features with PCA-SVM classifier	101	94.7
Rashid et al	2018	VGG16, AlexNet and SIFT	Hybrid of Deep CNN and SIFT Features along with entropy-controlled selection method and ensemble boosted tree	101	89.7	5.04
Singh et al	2019	Color Histogram (CH), Zernike Moments (ZMs), Gradient ZMs (GZMs), Multi-channel ZMs. (MZMs), Rotation Quaternion ZMs (RQZMs),	Fusion of these features with multi kernel learning (MKL) approach	10	84.60	0.08
Our system	2020	SIFT, SURF, ORB, Shi Tomasi	Fusion of these features with eXtreme Gradient Boosting Classifier	101	89.7	6.26
Proposed system	2020	VGG19, SIFT, SURF, ORB and Shi Tomasi corner detector	Fusion of these features with Random Forest Classifier	101	93.73	0.39