It's obvious that Google finds an image if exactly the same file is embedded by a web page or there's a link to that file. Google also finds images if you resize them, crop them or apply various photo effects.
Here's an image from a Wikipedia page, after resizing it and applying the pixelate effect from Picasa. Can Google find it?
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhrLpZzgNhOTB2rG2WLceXTRxw6d40Myf3ARXKrjWE03U7CiC-iO4VbzRrcmZFs_ywlPzSWL2EDUTW1iIgQCwhIIkpiWon7HxrzGkm_fz798H3_Ha4xg8sNHK1MqMTrWFmX4wnMbs6qjJ6i/s640/pixelated-photo.jpg)
Google can't find other sizes of the image, but if you look at the "Pages that include matching images" section, you'll find the image.
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheZBznnwUOK3z3rpQx1trZzJkIQcdkhPdDqWLtA7mp7aYzu8THvQcPpqnJBVqhCWnSetM5nheHqhGNf65FwpWxhHiOHOzNk3G_zPrHcsNWz8tTI8NJ39eO7SKXGH2rgdpQm8XlF3hYDDLb/s640/google-reverse-image-search.png)
What if you convert the photo to black and white? Will Google's reverse image search engine be able to find it?
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEhNfgfA9VXcorG_SaOQMK7JqwGVytOAD9lv4VYhWkAa_qdrISZzYUzXAVZ4ZW1lUaoYOquMb_kgFc4vfz81IvzZ2-lnXUJ_wZXzYwzbZmP6qfA2NOgHZ073RkHUN7m91me16B4sP81szvEl/s640/bw-photo.jpg)
You'll get the same pages that include matching images:
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEheZBznnwUOK3z3rpQx1trZzJkIQcdkhPdDqWLtA7mp7aYzu8THvQcPpqnJBVqhCWnSetM5nheHqhGNf65FwpWxhHiOHOzNk3G_zPrHcsNWz8tTI8NJ39eO7SKXGH2rgdpQm8XlF3hYDDLb/s640/google-reverse-image-search.png)
Let's try something more difficult - apply multiple Picasa effects: soft focus, tint, filtered black-and-white and posterize. There's no way to recognize this image, right?
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh42_IRGBlgRNRSuos02DOfu4pbpCcIWL7WjyVKdn6Vtko6_M8R20TVQ2zQKLerfB6DXT-2RdPUY1xE1REDKoiTqMtZbGXI5WsBfo1LjOgslgER6Zw-VxCfkv3nedjuoF38sZa6Xh3usnvT/s640/multi-effects-photo.jpg)
Wrong.
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEi7gqGxQye1-CCggfJ_VlscDgAZrkQBsnOiK00yNv1zGoTEXfag0IjWbOQBVUWnoPOm1UOLTOzQqtZUb9EpsgKL9Jpd5LYgf4KENo9-2B-yDQ48YC9UWw8gsobw9MBQcgGp8WtpdfjVQ5RP/s640/google-reverse-image-search-2.png)
I used IrfanView to remove EXIF data and compress the image above a lot more. Here's what I got:
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjLZ6hjGbZL4ki7gt6RsgJ49SQwa5vlc80jLgLlG1vUrxA9Jcr29sxGVscCs2EiIsPqkHghR6dJMcAg39PHUSGwAhOM-03W1zin9EPkcA7S7awDMrojvK5IKInPvaZzSjFVsHtPz9wgeBud/s640/google-reverse-image-search-3.png)
I edited the image in Paint and added some random shapes:
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgjD8y2PhZ7iBih31q-dxxqxVK6a6CxrA9cUbiRrTP0rI2Msty3s4wD62HapAUI3RQANAEEZwdqYtGymf6atDKo5ovRnba_IWWwsj7EZwKOs_dt939-uqRQ9vDutdlLJiFofJF8G0nvifyL/s640/multi-effects-photo-compressed-paint.jpg)
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjLZ6hjGbZL4ki7gt6RsgJ49SQwa5vlc80jLgLlG1vUrxA9Jcr29sxGVscCs2EiIsPqkHghR6dJMcAg39PHUSGwAhOM-03W1zin9EPkcA7S7awDMrojvK5IKInPvaZzSjFVsHtPz9wgeBud/s640/google-reverse-image-search-3.png)
Here's the original photo:
![](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEgRJSs_C5blUJy2nipVXRXN-2i-d8kH4cEVjK5QGaZp1JeDtqXS-vNfuwvG1M0WEjZiLQ3nqUkUA25Moo1zSLd-Q6WKtpn6jYuN_3rGHb64Tq_cHmGaWFIPE7MpNN5ighk5xWuLZcOlaNKp/s640/original-photo.jpg)
To call this impressive is an understatement. It's a resilient algorithm that goes beyond matching pixels, colors, shapes - it understands the structure of the image, its essence.
{ The image from this post ("a red flower in the Philippines") has been licensed as Creative Commons Attribution by bingbing. Thanks, Brian Anderson. }
0 comments:
Post a Comment