Histogram Equalization and Gaussian Filtering Combination Method for Face Image optimization

Good image plays an important role in the delivery of information, where the image quality is often influenced by the process of image retrieval or storage. As a result, there is a decrease in the intensity of image quality as the image will contain defects or noise, the color will be contrast or blur. Histogram Equalization and Gaussian Filtering Combination Method can be used to improve the image quality. The test result that we used is the comparison between the original image and filtered image. In the initial process, the system used facial images that have the RGB format converted to grayscale format. Furthermore, there was an equalization of the light intensity value in the grayscale image. The next process was image filtering using Gaussian Filtering method to reduce noise. The noise measurement in the image was calculated using the Peak Signal-to-Noise Ratio (PSNR). Meanwhile, the measurement of signal quality used Signal-to-Ratio (SNR). The test was performed on a standard deviation of 0.5 to 1 and obtained the highest value of the $3\mathrm{x}3$ Gaussian filter at a standard deviation of 0.5 where the values of SNR $=45.7757$ and PSNR = 32.948. The greater the value of PSNR image, the image will be closer to the original image as well as the larger the SNR value, the better the signal quality generated.