Open AccessFace Detection for Color Image Based on MATLAB
Author(s) -
Shahad laith abd al_galib,
Asma Abdulelah Abdulrahman,
Fouad Shaker Tahir Al-azawi
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1879/2/022129
Subject(s) - computer science , artificial intelligence , convolutional neural network , face detection , matlab , computer vision , face (sociological concept) , field (mathematics) , deep learning , facial recognition system , artificial neural network , convolution (computer science) , pattern recognition (psychology) , mathematics , social science , sociology , pure mathematics , operating system
Amazing results in many works in the field of deep convolutional neural networks using them in many fields of machine learning such as image classification control of atrial play, and image annotation. Mathematical analysis of deep convolutional neural networks (CNN) has a broad role in many applications including image classification applications. Face recognition technology has occupied a wide field in research that is still continuing in this work. Face recognition technology is being developed depending on the MATLAB program to develop the subjecting of the color image to the neural convolution network and the work of a program to reduce the time the network deals with the image to reduce the number of layers to only two layers and access the algorithm Suggested in this work. Computer vision of a color image in a face detection study. In this work, the researcher created a fast algorithm to reach the research goal based on new standards in the field of face detection. A new face detection program was designed using MATLAB, CascadeObjectDetector and trainCascadeObjectDetector the face detection devices were developed. In this work, a technique for panning and color image using the convolutional neural network for deep learning is proposed, the method used to reach the goal of this work.