• Irfan Ayoub
• Dr Bhawna Sharma
• Imtiyaz Hussain
• Neelesh Singh Katoch
• Manthan Kaushal

Abstract— This paper mainly addresses the building of face recognition system by using Haar Cascade and Principal Component Analysis (PCA) and their percentage efficiency in different cases. Haar Cascade is a machine learning algorithm used in object detection and to determine the object in an image. It uses function called Haar wavelet to determine features called Haar features. In Haar-features we find the difference in pixel intensities of the regions inside the detection window. Though PCA is a measurable methodology utilized for lessening the quantity of factors in face acknowledgment. Each picture in the preparation set is addressed as a straight blend of weighted eigen vectors. These eigen vectors are called Eigen faces. The weights are obtained by selecting most relevant vectors from covariance matrix. The recognition is done by comparing a projected test image with the subspace of Eigen faces. The minimum Elucidean distance is measured for classification of faces. Various investigations were performed to assess the presentation of the face recognition system.

Face detection, Face recognition, Pattern recognition, Haar Cascade, Cascade Classifier, Haar Features, Local Binary Patterns Histograms(LBPH), Principle component analysis (PCA), Histogram of Oriented Gradients(HOG),Percentage Efficiency Comparison.

"FACE RECOGNITION SYSTEM USING MACHINE LEARNING ALGORITHMS (HAAR-CASCADE & PCA) AND THEIR EFFICIENCY COMPARISON", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 8, page no.a683-a694, August-2022, Available :http://www.jetir.org/papers/JETIR2208085.pdf

"FACE RECOGNITION SYSTEM USING MACHINE LEARNING ALGORITHMS (HAAR-CASCADE & PCA) AND THEIR EFFICIENCY COMPARISON", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 8, page no. ppa683-a694, August-2022, Available at : http://www.jetir.org/papers/JETIR2208085.pdf