<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Machine Learning on funinkina's corner</title><link>https://funinkina.co.in/tags/machine-learning/</link><description>Recent content in Machine Learning on funinkina's corner</description><generator>Hugo</generator><language>en</language><lastBuildDate>Thu, 06 Feb 2025 22:57:22 +0530</lastBuildDate><atom:link href="https://funinkina.co.in/tags/machine-learning/index.xml" rel="self" type="application/rss+xml"/><item><title>Enhancing Screenshots in GNOME with OCR</title><link>https://funinkina.co.in/blog/enhancing-screenshots-in-gnome-with-ocr/</link><pubDate>Thu, 06 Feb 2025 22:57:22 +0530</pubDate><guid>https://funinkina.co.in/blog/enhancing-screenshots-in-gnome-with-ocr/</guid><description>&lt;p&gt;A while ago, I was working on a project, and the way error was being displayed, I could not copy the text directly to paste it in ChatGPT. I had to type the whole error message manually, which was a bit frustrating. I thought, what if I could just take a screenshot and extract the text from the image directly? That&amp;rsquo;s when I decided to enhance GNOME Screenshot with OCR. I mean windows snipping tool has this feature, why not GNOME Screenshot?&lt;/p&gt;</description></item><item><title>DEM Super Resolution</title><link>https://funinkina.co.in/projects/dem-super-resolution/</link><pubDate>Tue, 30 Jul 2024 20:52:14 +0530</pubDate><guid>https://funinkina.co.in/projects/dem-super-resolution/</guid><description>&lt;h2 id="project-description"&gt;Project Description&lt;/h2&gt;
&lt;p&gt;This project explores upscaling of Digital Elevation Model (DEM) data using a state-of-the-art super-resolution model. The model used is from the 2023 paper, &lt;em&gt;&amp;ldquo;A Global-Information-Constrained Deep Learning Network for Digital Elevation Model Super-Resolution.&amp;rdquo;&lt;/em&gt;. For more details and original implementation see the &lt;a href="https://www.mdpi.com/2072-4292/15/2/305" target="_blank" rel="noreferrer nofollow"&gt;paper&lt;/a&gt;
.
The article demonstrated the model&amp;rsquo;s ability in enhancing the resolution of DEM data beyond traditional bicubic interpolation methods, which are often considered the baseline to beat for super-resolution models on DEM data.&lt;/p&gt;</description></item></channel></rss>