<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>WebML on AI VOID</title><link>https://ai-blog.noorshomelab.dev/tags/webml/</link><description>Recent content in WebML on AI VOID</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sun, 26 Oct 2025 00:00:00 +0000</lastBuildDate><atom:link href="https://ai-blog.noorshomelab.dev/tags/webml/index.xml" rel="self" type="application/rss+xml"/><item><title>Visual Intelligence: Computer Vision Tasks</title><link>https://ai-blog.noorshomelab.dev/transformers-js-guide/visual-intelligence-computer-vision-tasks/</link><pubDate>Sun, 26 Oct 2025 00:00:00 +0000</pubDate><guid>https://ai-blog.noorshomelab.dev/transformers-js-guide/visual-intelligence-computer-vision-tasks/</guid><description>&lt;h1 id="4-visual-intelligence-computer-vision-tasks"&gt;4. Visual Intelligence: Computer Vision Tasks&lt;/h1&gt;
&lt;p&gt;Computer Vision (CV) enables computers to &amp;ldquo;see&amp;rdquo; and interpret visual information from images and videos. Transformers.js brings powerful CV models directly to the browser, allowing for client-side image processing, analysis, and understanding. This chapter explores common CV tasks.&lt;/p&gt;
&lt;h2 id="41-image-classification"&gt;4.1. Image Classification&lt;/h2&gt;
&lt;p&gt;Image classification involves assigning a label (or class) to an entire image, determining what the main subject of the image is.&lt;/p&gt;
&lt;h3 id="411-detailed-explanation"&gt;4.1.1. Detailed Explanation&lt;/h3&gt;
&lt;p&gt;An image classification pipeline takes an image (as a URL, &lt;code&gt;File&lt;/code&gt; object, or &lt;code&gt;HTMLImageElement&lt;/code&gt;) and outputs a list of predicted labels with confidence scores. Models are trained on vast datasets like ImageNet, learning to recognize patterns associated with thousands of different categories.&lt;/p&gt;</description></item></channel></rss>