<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Connected-Components on Aayush Bajaj's Augmenting Infrastructure</title><link>https://abaj.ai/tags/connected-components/</link><description>Recent content in Connected-Components on Aayush Bajaj's Augmenting Infrastructure</description><generator>Hugo</generator><language>en</language><copyright>© 2026 Aayush Bajaj</copyright><lastBuildDate>Thu, 12 Nov 2026 02:04:46 +1100</lastBuildDate><atom:link href="https://abaj.ai/tags/connected-components/index.xml" rel="self" type="application/rss+xml"/><item><title>Classical Segmentation</title><link>https://abaj.ai/wiki/computer-vision/segmentation/</link><pubDate>Wed, 11 Nov 2026 21:00:00 +1100</pubDate><guid>https://abaj.ai/wiki/computer-vision/segmentation/</guid><description>&lt;p>Counting cells, measuring a tumour or picking nuts off a conveyor all need one step between &amp;ldquo;an image&amp;rdquo; and &amp;ldquo;numbers about what is in it&amp;rdquo;: deciding which pixels belong together. That step is &lt;em>segmentation&lt;/em>: give every pixel a region label so that pixels with the same label form one meaningful segment.&lt;span class="margin-note" data-note="Distils UNSW COMP9517 Week 5 (image segmentation) and the thresholding half of Week 1. Figures and numerical results come from the course notes&amp;#39; own scripts (seed 9517).">
 &lt;span class="margin-note-indicator">𐃏&lt;/span>
&lt;/span>
&lt;/p></description></item></channel></rss>