Protecting Privacy with Image Processing: How Blurring and Masking Help Keep Us Safe Online

Abstract

Because more people are using technological networks, it is now easier to share pictures that contain private information. PSNR, SSIM and a custom Privacy Preservation Score. Median blur, Box Blur (Average Blur), Pixelation and Masking methods to an array of facial images or license plates or background objects We measured how well they worked using we investigate the effectiveness of image obfuscation techniques such as pixelization, masking, and blurring in protecting privacy during online sharing for images. We were applied a certain range of filters, such as Gaussian blur, about identity theft, privacy and the unauthorized use of your information. In this work, Now people are worried The results show that Gaussian blur keeps things clear to the eye while also providing a good level of anonymity. Average blur, on the other hand, keeps the structural boundaries but may leave hints that help you figure out what the object is. Pixelation makes things more private by changing the size of the blocks, which is especially useful for organized elements. Masking methods give it is the highest level of confidentiality achievable because they eliminate of each identifiable knowledge. A glance at how people see images supports the idea that masking is an effective method to circulate pictures safely, regardless of whether it may not appear as good. The results show that there is no one best way to do things; instead, the choice should depend on how sensitive the information is and what the image will be used for. For social networking companies, application developers, and individuals looking to enhance digital safety, this study offers practical insights. While identification algorithms advance, it also emphasizes the requirement that more robust private measures which artificial intelligence cannot violate.