<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
    <channel>
      <title>Computer Vision Notes</title>
      <link>https://owenarink.github.io/computervision101uva</link>
      <description>Last 10 notes on Computer Vision Notes</description>
      <generator>Quartz -- quartz.jzhao.xyz</generator>
      <item>
    <title>CV101_LectureNotes</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/CV101_LectureNotes</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/CV101_LectureNotes</guid>
    <description><![CDATA[ university computervision lectures Public lecture-note pages: CV101_LectureNotes1b ComputerVision101_Theory_Week1 CV101_Lectures . ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>CV101_LectureNotes1b</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/CV101_LectureNotes1b</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/CV101_LectureNotes1b</guid>
    <description><![CDATA[ university computervision lecture1b Source: Computer Vision Lecture 1b This lecture continues the week 1 material with: interpolation recap 1D and 2D interpolation extrapolation image representation in NumPy/OpenCV domain iterators histograms point operators histogram-based contrast improvement Admi... ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>CV101_Lectures</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/CV101_Lectures</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/CV101_Lectures</guid>
    <description><![CDATA[ university computervision lectures CV101_LectureNotes1a CV101_LectureNotes1b. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Theory_Week1</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Theory_Week1</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Theory_Week1</guid>
    <description><![CDATA[ university computervision week1 theory Lecture notes: rvdboomgaard.github.io/ComputerVision_LectureNotes/LectureNotes/IP/index.html Lecture slides: Digitized lecture notes: CV101_LectureNotes1b Concepts: ComputerVision101_Week1_WhatIsAnImage ComputerVision101_Week1_ImageDefinition_DomainAndRange Com... ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_AlphaBlending</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_AlphaBlending</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_AlphaBlending</guid>
    <description><![CDATA[ university computervision week1 theory Alpha Blending Source: CV101_LectureNotes1b Alpha blending computes a weighted average of two images: h_\alpha = (1-\alpha)f + \alpha g Interpretation: \alpha = 0 gives only f \alpha = 1 gives only g values in between smoothly mix the two images . ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_CubicInterpolation</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_CubicInterpolation</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_CubicInterpolation</guid>
    <description><![CDATA[ university computervision week1 theory Cubic Interpolation Source: CV101_LectureNotes1b Idea Cubic interpolation fits a cubic polynomial between two neighboring samples. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_DomainIterators</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_DomainIterators</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_DomainIterators</guid>
    <description><![CDATA[ university computervision week1 theory Domain Iterators Source: CV101_LectureNotes1b Idea A domain iterator enumerates pixel index tuples so you can visit every image location systematically. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_Extrapolation</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_Extrapolation</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_Extrapolation</guid>
    <description><![CDATA[ university computervision week1 theory Extrapolation Source: CV101_LectureNotes1b Idea Extrapolation estimates image values outside the sampled image grid. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_HistogramContrastStretching</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_HistogramContrastStretching</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_HistogramContrastStretching</guid>
    <description><![CDATA[ university computervision week1 theory Histogram Contrast Stretching Source: CV101_LectureNotes1b Goal Use the full luminance range when the original image occupies only a narrow interval. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item><item>
    <title>ComputerVision101_Week1_HistogramEqualization</title>
    <link>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_HistogramEqualization</link>
    <guid>https://owenarink.github.io/computervision101uva/computer-vision/ComputerVision101_Week1_HistogramEqualization</guid>
    <description><![CDATA[ university computervision week1 theory Histogram Equalization Source: CV101_LectureNotes1b Goal Create a new image whose intensities are spread more evenly across the available range. ]]></description>
    <pubDate>Thu, 02 Apr 2026 09:18:20 GMT</pubDate>
  </item>
    </channel>
  </rss>