<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Image on ZL Labs Ltd</title>
    <link>https://zl-labs.tech/tags/image/</link>
    <description>Recent content in Image on ZL Labs Ltd</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Fri, 27 Jun 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://zl-labs.tech/tags/image/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>XKCD Finder</title>
      <link>https://zl-labs.tech/post/2025-06-27-xkcd-rag/</link>
      <pubDate>Fri, 27 Jun 2025 00:00:00 +0000</pubDate>
      <guid>https://zl-labs.tech/post/2025-06-27-xkcd-rag/</guid>
      <description>&lt;p&gt;XKCD comics have become a cornerstone of internet culture, particularly in technical circles, with their witty takes on science,&#xA;programming, and mathematics. However, finding the perfect XKCD for a particular topic or reference can be challenging -&#xA;there are now over 3,000 comics in the archive, and traditional search methods rely heavily on exact keyword matches or&#xA;remembering specific comic numbers.&lt;/p&gt;&#xA;&lt;p&gt;This project explores how modern Natural Language Processing (NLP) techniques can be used to search XKCD comics semantically,&#xA;understanding the underlying meaning rather than just matching keywords. By applying vector embeddings and Retrieval&#xA;Augmented Generation (RAG) to comic descriptions, we can now perform a search based on concepts, themes, and abstract ideas.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Let it Segment: A Gift from SAM</title>
      <link>https://zl-labs.tech/post/2024-12-20-adventures-with-sam/</link>
      <pubDate>Fri, 20 Dec 2024 00:00:00 +0000</pubDate>
      <guid>https://zl-labs.tech/post/2024-12-20-adventures-with-sam/</guid>
      <description>&lt;p&gt;With the release of the Segment Anything Model&lt;sup id=&#34;fnref:1&#34;&gt;&lt;a href=&#34;#fn:1&#34; class=&#34;footnote-ref&#34; role=&#34;doc-noteref&#34;&gt;1&lt;/a&gt;&lt;/sup&gt; (SAM) released by Meta AI Research last year, the lie of the land changed&#xA;quite substantially in Computer Vision, as now images could be segmented easily, with great results even zero-shot. With&#xA;the release of SAM2&lt;sup id=&#34;fnref:2&#34;&gt;&lt;a href=&#34;#fn:2&#34; class=&#34;footnote-ref&#34; role=&#34;doc-noteref&#34;&gt;2&lt;/a&gt;&lt;/sup&gt; earlier this year, I wanted to get hands on and experiment with these models myself.&lt;/p&gt;&#xA;&lt;p&gt;This post walks you through how SAM2 could be used in practice, provides a mini analysis of segmentation results and will&#xA;be released with code so that you can explore further if you want to. This could be expanded to interesting use cases,&#xA;such as facilitating object grasping in robotic systems, branded product addition or removal in marketing images, or&#xA;mapping changes in forested areas from satellite imagery over time for environmental monitoring.&lt;/p&gt;</description>
    </item>
    <item>
      <title>Image Selector</title>
      <link>https://zl-labs.tech/post/2021-05-26-image-selector/</link>
      <pubDate>Wed, 26 May 2021 00:00:00 +0000</pubDate>
      <guid>https://zl-labs.tech/post/2021-05-26-image-selector/</guid>
      <description>&lt;p&gt;Duplicate photos are annoying and unwanted. Wouldn&amp;rsquo;t you rather make those post-holiday rundowns with the family as impressive (short) as possible? The burden of boiling your photo set&#xA;down to the most memorable and ones with the best angle is greatly reduced by this app. It works because you can visualize all images &lt;em&gt;together&lt;/em&gt; in the order they were taken.&lt;/p&gt;&#xA;&lt;p&gt;I now use my Dash app routinely after every holiday, as it makes the deduplication process much faster, yielding a cleaner set of photos without maxing out your hard drive!&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
