336 lines
9.4 KiB
HTML
336 lines
9.4 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en" dir="ltr">
|
|
|
|
<head>
|
|
<meta name="generator" content="Hugo 0.96.0" />
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<meta name="description" content="This week is the first week of the project. I researched academic papers, existing code and dataset relating to the topic of determining aesthetics.
|
|
Papers # Photo Aesthetics Analysis via DCNN Feature Encoding1 - Predicting aesthetic performance using a bespoke CNN solution
|
|
AVA: A large-scale database for aesthetic visual analysis2 - Making of an aestehtic visual analysis dataset
|
|
Code # Image Quality Assessment - Convolutional Neural Networks to predict the aesthetic and technical quality of images.">
|
|
<meta name="theme-color" content="#FFFFFF"><meta property="og:title" content="Week 1" />
|
|
<meta property="og:description" content="This week is the first week of the project. I researched academic papers, existing code and dataset relating to the topic of determining aesthetics.
|
|
Papers # Photo Aesthetics Analysis via DCNN Feature Encoding1 - Predicting aesthetic performance using a bespoke CNN solution
|
|
AVA: A large-scale database for aesthetic visual analysis2 - Making of an aestehtic visual analysis dataset
|
|
Code # Image Quality Assessment - Convolutional Neural Networks to predict the aesthetic and technical quality of images." />
|
|
<meta property="og:type" content="article" />
|
|
<meta property="og:url" content="https://mmp.oscar.blue/posts/week-1/" /><meta property="article:section" content="posts" />
|
|
<meta property="article:published_time" content="2022-02-06T12:46:51+00:00" />
|
|
<meta property="article:modified_time" content="2022-02-06T12:46:51+00:00" />
|
|
|
|
<title>Week 1 | MMP | Oscar Pocock</title>
|
|
<link rel="manifest" href="/manifest.json">
|
|
<link rel="icon" href="/favicon.png" type="image/x-icon">
|
|
<link rel="stylesheet" href="/book.min.68be0b7a9674f2a612ce0e9b2e9447ff4b7ac96546e06b642bfd3ded0ca490ef.css" integrity="sha256-aL4LepZ08qYSzg6bLpRH/0t6yWVG4GtkK/097QykkO8=">
|
|
<script defer src="/en.search.min.0c8af0cffc76d081a5a819e52dfdb147c344002d63293b8ad6697c1cbe08a5f2.js" integrity="sha256-DIrwz/x20IGlqBnlLf2xR8NEAC1jKTuK1ml8HL4IpfI="></script>
|
|
|
|
<script defer src="/sw.min.6f6f90fcb8eb1c49ec389838e6b801d0de19430b8e516902f8d75c3c8bd98739.js" integrity="sha256-b2+Q/LjrHEnsOJg45rgB0N4ZQwuOUWkC+NdcPIvZhzk="></script>
|
|
<!--
|
|
Made with Book Theme
|
|
https://github.com/alex-shpak/hugo-book
|
|
-->
|
|
|
|
|
|
</head>
|
|
|
|
<body dir="ltr">
|
|
<input type="checkbox" class="hidden toggle" id="menu-control" />
|
|
<input type="checkbox" class="hidden toggle" id="toc-control" />
|
|
<main class="container flex">
|
|
<aside class="book-menu">
|
|
<div class="book-menu-content">
|
|
|
|
<nav>
|
|
<h2 class="book-brand">
|
|
<a href="/"><span>MMP | Oscar Pocock</span>
|
|
</a>
|
|
</h2>
|
|
|
|
|
|
<div class="book-search">
|
|
<input type="text" id="book-search-input" placeholder="Search" aria-label="Search" maxlength="64" data-hotkeys="s/" />
|
|
<div class="book-search-spinner hidden"></div>
|
|
<ul id="book-search-results"></ul>
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li class="book-section-flat" >
|
|
|
|
|
|
|
|
|
|
|
|
<a href="https://mmp.oscar.blue/docs/developer/" class="">Developer Documentation</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li class="book-section-flat" >
|
|
|
|
|
|
|
|
|
|
|
|
<a href="https://mmp.oscar.blue/docs/user/" class="">User Documentation</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
<li>
|
|
<a href="/posts/" >
|
|
Blog
|
|
</a>
|
|
</li>
|
|
|
|
<li>
|
|
<a href="https://teaching.dcs.aber.ac.uk/mmp" target="_blank" rel="noopener">
|
|
Aberystwyth MMP Site
|
|
</a>
|
|
</li>
|
|
|
|
<li>
|
|
<a href="https://git.oscar.blue" target="_blank" rel="noopener">
|
|
Source Code
|
|
</a>
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</nav>
|
|
|
|
|
|
|
|
|
|
<script>(function(){var e=document.querySelector("aside.book-menu nav");addEventListener("beforeunload",function(){localStorage.setItem("menu.scrollTop",e.scrollTop)}),e.scrollTop=localStorage.getItem("menu.scrollTop")})()</script>
|
|
|
|
|
|
|
|
</div>
|
|
</aside>
|
|
|
|
<div class="book-page">
|
|
<header class="book-header">
|
|
|
|
<div class="flex align-center justify-between">
|
|
<label for="menu-control">
|
|
<img src="/svg/menu.svg" class="book-icon" alt="Menu" />
|
|
</label>
|
|
|
|
<strong>Week 1</strong>
|
|
|
|
<label for="toc-control">
|
|
|
|
<img src="/svg/toc.svg" class="book-icon" alt="Table of Contents" />
|
|
|
|
</label>
|
|
</div>
|
|
|
|
|
|
|
|
<aside class="hidden clearfix">
|
|
|
|
|
|
<nav id="TableOfContents">
|
|
<ul>
|
|
<li><a href="#papers">Papers</a></li>
|
|
<li><a href="#code">Code</a></li>
|
|
<li><a href="#datasets">Datasets</a></li>
|
|
<li><a href="#project-idea-from-research">Project idea from research</a></li>
|
|
<li><a href="#weekly-11-meeting">Weekly 1:1 meeting</a></li>
|
|
</ul>
|
|
</nav>
|
|
|
|
|
|
|
|
</aside>
|
|
|
|
|
|
</header>
|
|
|
|
|
|
|
|
<article class="markdown">
|
|
<h1>
|
|
<a href="/posts/week-1/">Week 1</a>
|
|
</h1>
|
|
|
|
<h5>February 6, 2022</h5>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<p>This week is the first week of the project. I researched academic papers, existing code and dataset relating to the topic of determining aesthetics.</p>
|
|
<h1 id="papers">
|
|
Papers
|
|
<a class="anchor" href="#papers">#</a>
|
|
</h1>
|
|
<p>
|
|
<a href="https://ieeexplore.ieee.org/document/7886320">Photo Aesthetics Analysis via DCNN Feature Encoding</a><sup id="fnref:1"><a href="#fn:1" class="footnote-ref" role="doc-noteref">1</a></sup> - Predicting aesthetic performance using a bespoke CNN solution</p>
|
|
<p>
|
|
<a href="https://ieeexplore.ieee.org/document/6247954">AVA: A large-scale database for aesthetic visual analysis</a><sup id="fnref:2"><a href="#fn:2" class="footnote-ref" role="doc-noteref">2</a></sup> - Making of an aestehtic visual analysis dataset</p>
|
|
<h1 id="code">
|
|
Code
|
|
<a class="anchor" href="#code">#</a>
|
|
</h1>
|
|
<p>
|
|
<a href="https://github.com/idealo/image-quality-assessment">Image Quality Assessment</a> - Convolutional Neural Networks to predict the aesthetic and technical quality of images.</p>
|
|
<h1 id="datasets">
|
|
Datasets
|
|
<a class="anchor" href="#datasets">#</a>
|
|
</h1>
|
|
<p>
|
|
<a href="https://github.com/aimerykong/deepImageAestheticsAnalysis">AADB</a></p>
|
|
<p>AVA:
|
|
<a href="https://github.com/imfing/ava_downloader">https://github.com/imfing/ava_downloader</a>,
|
|
<a href="https://github.com/ylogx/aesthetics/tree/master/data/ava">https://github.com/ylogx/aesthetics/tree/master/data/ava</a></p>
|
|
<h1 id="project-idea-from-research">
|
|
Project idea from research
|
|
<a class="anchor" href="#project-idea-from-research">#</a>
|
|
</h1>
|
|
<p>Based on the research, I decided a machine learning approach would result in higher quality outputs. Although, I was slightly concerned that following a deep-learning would limit interesting discussion in my report.</p>
|
|
<p>The idea was to create a program that can take a video, break it down into frames and use a trained CNN to predict the most aesthetic frames and return them to the user.</p>
|
|
<h1 id="weekly-11-meeting">
|
|
Weekly 1:1 meeting
|
|
<a class="anchor" href="#weekly-11-meeting">#</a>
|
|
</h1>
|
|
<p>During the meeting I mentioned my concerns following a deep learning approach. Although this approach might provide quality results, it doesn’t provide much room to discuss or develop interesting solutions. Instead, as Hannah put, it mostly depends on throwing the problem at powerful hardware to get the best output which doesn’t make for an interesting project. Hannah suggested I take a hybrid approach where I could use deep-learning for the last step in the pipeline, depending more on conventional engineering techniques to reduce the input data before passing it to the deep-learning stage.</p>
|
|
<p>She mentioned ‘dumb’ ways in which I could reduce the set of input frames:</p>
|
|
<ul>
|
|
<li>Comparing file sizes and removing the small ones (might infer single colour images / less complex images)</li>
|
|
<li>Fourier frequency analysis</li>
|
|
<li>Brightness and contrast analysis</li>
|
|
</ul>
|
|
<section class="footnotes" role="doc-endnotes">
|
|
<hr>
|
|
<ol>
|
|
<li id="fn:1" role="doc-endnote">
|
|
<p>H. -J. Lee, K. -S. Hong, H. Kang and S. Lee, “Photo Aesthetics Analysis via DCNN Feature Encoding,” in IEEE Transactions on Multimedia, vol. 20, no. 8, pp. 1921-1932, Aug. 2017, doi: 10.1109/TMM.2017.2687759. <a href="#fnref:1" class="footnote-backref" role="doc-backlink">↩︎</a></p>
|
|
</li>
|
|
<li id="fn:2" role="doc-endnote">
|
|
<p>N. Murray, L. Marchesotti and F. Perronnin, “AVA: A large-scale database for aesthetic visual analysis,” 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 2408-2415, doi: 10.1109/CVPR.2012.6247954. <a href="#fnref:2" class="footnote-backref" role="doc-backlink">↩︎</a></p>
|
|
</li>
|
|
</ol>
|
|
</section>
|
|
</article>
|
|
|
|
|
|
|
|
<footer class="book-footer">
|
|
|
|
<div class="flex flex-wrap justify-between">
|
|
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</footer>
|
|
|
|
|
|
|
|
<div class="book-comments">
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<label for="menu-control" class="hidden book-menu-overlay"></label>
|
|
</div>
|
|
|
|
|
|
<aside class="book-toc">
|
|
<div class="book-toc-content">
|
|
|
|
|
|
<nav id="TableOfContents">
|
|
<ul>
|
|
<li><a href="#papers">Papers</a></li>
|
|
<li><a href="#code">Code</a></li>
|
|
<li><a href="#datasets">Datasets</a></li>
|
|
<li><a href="#project-idea-from-research">Project idea from research</a></li>
|
|
<li><a href="#weekly-11-meeting">Weekly 1:1 meeting</a></li>
|
|
</ul>
|
|
</nav>
|
|
|
|
|
|
|
|
</div>
|
|
</aside>
|
|
|
|
</main>
|
|
|
|
|
|
</body>
|
|
|
|
</html>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|