<![CDATA[In this work, it was proposed to compress the color image after de-noise by proposing a coding for the discrete transport of new wavelets called discrete chebysheve wavelet transduction (DCHWT) and linking it to a neural network that relies on the convolutional neural network to compress the color image. The aim of this work is to find an effective method for face recognition, which is to raise the noise and compress the image in convolutional neural networks to remove the noise that caused the image while it was being transmitted in the communication network. The work results of the algorithm were calculated by calculating the peak signal to noise ratio (PSNR), mean square error (MSE), compression ratio (CR) and bit-per-pixel (BPP) of the compressed image after a color image (256×256) was entered to demonstrate the quality and efficiency of the proposed algorithm in this work. The result obtained by using a convolutional neural network with new wavelets is to provide a better CR with the ratio of PSNR to be a high value that increases the high-quality ratio of the compressed image to be ready for face recognition.]]>
Copyrights © 2021
