<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Tech on Alex Here - Blog</title><link>https://blog.alexhere.me/tags/tech/</link><description>Recent content in Tech on Alex Here - Blog</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Tue, 07 Apr 2026 16:08:00 +0700</lastBuildDate><atom:link href="https://blog.alexhere.me/tags/tech/index.xml" rel="self" type="application/rss+xml"/><item><title>Structural Similarity Index (SSIM)</title><link>https://blog.alexhere.me/2026/04/07/structural-similarity-index-ssim/</link><pubDate>Tue, 07 Apr 2026 16:08:00 +0700</pubDate><guid>https://blog.alexhere.me/2026/04/07/structural-similarity-index-ssim/</guid><description>&lt;h1 id="why-i-built-ssim-from-scratch-for-my-vss-project"&gt;Why I Built SSIM From Scratch for My VSS Project&lt;/h1&gt;
&lt;p&gt;I&amp;rsquo;ve been working on a project called Visual Secret Sharing (VSS) for my final project in uni. It&amp;rsquo;s been a deep dive, taking color images, breaking them into shares that look like static noise (or not), and then reconstructing them. Along the way, I hit a problem: how do you actually measure if your reconstruction is any good?&lt;/p&gt;
&lt;p&gt;Most developers instinctively reach for MSE or PSNR when evaluating image quality. I did too at first. The problem is they measure pixel differences, not what the eye actually notices. They&amp;rsquo;re simple to compute, sure, but they don&amp;rsquo;t match what our eyes actually see. And when you&amp;rsquo;re working on something as visual as image reconstruction, that&amp;rsquo;s a pretty big problem.&lt;/p&gt;</description></item></channel></rss>