Artificial Intelligence Starts To Create Photographs

A new AI system which was introduced by the scientists, surprised everyone with photographs created from scratch that are indistinguishable from their originals. This new system does not require any details other than the features defined by the user in writing.

For example, when you make a request like “a blonde woman wearing a dress with red and blue stripes walks down the 5th Avenue in Manhattan”, the AI creates this photograph for you. This ability of the AI is a result of analyzing trillions of photographs on the internet.

The system first searches through the samples it has seen before according to what is written in the description and then combines them into a composition in the most suitable way. This way, the AI creates a scene which does not actually exist pixel by pixel and presents it to us like it is a real photo.

This new AI system is created as a result of the joint study of Rutgers University, North Carolina University, Lehigh University and Hong Kong University may be the cause of big changes in media, publishing and social media.

My Workflow for Efficient Keywording of a Stock Photo

Keywording determines the fate of the stock photos. I want to explain this important process with a sample photo of a cat.

First of all, there is no point in tagging a photo of cat with the keyword “cat” only, because when you search for “cat” on iStock, you are seeing 457000 results today. So if you cannot find any other interesting keywords to tag a cat’s photo, do not waste your time by uploading the image.

Supposing that you want to upload the image in any way. In that case, you can make some adjustments on the image. For example: changing colour of only one eye of the cat may be an option to add new keywords and separate it from other cats.

But this small change does not remove the necessity from adding keywords “cat”, “animal”, “outdoor” etc. for the image. I hate dealing with things that are far below my abilities. Isn’t it a boring routine to look a photo, see the cat and write the keyword “cat”? Do you know that there are applications that do this routine for you and generate keywords automatically? My motto as an engineer is “if something can be done by machines, it’s inefficient to do it manually.”

Here is my workflow of keywording a photo:

  1. I drag and drop the image on Keywordsready and let the tool generates keywords for me. I copy and paste the keywords to where I want to upload the image. (Keywordsready.com is a completely free keywording tool that uses artificial intelligence technology.)
  2. I ask myself the following question “What is in this image different from others?” and add a few more keywords that will help my image to separate from others. For this example, after editing eye of the cat: “heterochromia”, “variety”, “colourful”, “anomaly” etc.
  3. I ask myself the following question “if I were a buyer, which keywords would I use to find my image?” and add a few strong keywords which are conceptual generally.

Sometimes I skip the steps 2 and 3 because Keywordsready might have generated all necessary keywords for me.

An example how Keywordsready can increase your productivity

Assuming that you are a travel photographer and you have a Canon 5D Mark IV. Last month you traveled a few countries and shoot hundreds of images of streets, natural landmarks, buildings, people etc. Now you are at home and want to upload your images but you think that keywording is an annoying work because you have to remember where the images have been taken and name of the landmarks. Don’t worry! If GPS of your camera is turned on during your travel, leave the rest to Keywordsready that can find not only country, city, district of the image but also name of the landmarks. Although only this feature is enough to increase your efficiency, there are more features like finding number and ages of people visible in the image, technical properties of the image and many more…

Can Artificial Intelligence Really Criticize Photography?

How do you define the best photos in a large database that hosts thousands of images sent from all over the world? The visual bank EyeEm has developed its artificial intelligence system to make an objective choice of the best photographs on its platform. EyeEm Vision AI analyzes the light, color and quality of the image according to exact criteria. Using this artificial intelligence, the site picked the best photos from 2016.

According to the website, “EyeEm Vision is a powerful, proprietary, patented computer vision technology that automatically understand and tags photos” EyeEm Vision can also determine the aesthetic qualities of a photo based on commercial potential and curator preferences.

8 Photo Apps Using AI To Give Your Photos an Artistic Look

Painnt

Painnt (free from the iTunes Store) is not only about selecting pre-set styles for your photo, but also adjusting them to get a completely unique look. More than 100 styles in seven categories are available for desktop Macs and mobile devices (all effects are filtered on the local device). Select the aspect ratio (up to 16: 9) and extract the final picture in small, medium, large and original resolutions. Option settings like Transparency, Brightness, Contrast, Tint and Saturation allow you to experiment dynamically when combined with color composition options and settings such as Grain Consolidation and Soft Light. Detail shifters allow you to increase clarity and smoothness. You can view previous and next views of your images side by side, split view, or import.

Prisma

From Prisma (free from the iTunes Store), Van Gogh, Picasso, Lichtenstein, Mondrian, Kandinsky and more, your photos are moving to a new place as a popular iPhone mobile app that allows you to present engaging artistic styles, and these are often new, Original entries.

Styler

Styler (free on Mac App Store), which works with both still image and video, is an easy-to-use Mac desktop application that lets you drag your artwork to the main window of the whole action. You can choose from 13 different styles like Candy, Hundertwasser and Seurat, or you can combine all the styles together.

Pikazo

Pikazo (free from the iTunes Store) uses a technology that mimics the human visual cortex to create a new image based on your original photo and a style you choose. Unlike some other apps in this genre, Pikazo allows you to select the subject and style instead of selecting from the available styles. Start with Pikazo’s built-in styles, buy additional style packs, or choose an original style from your own photo rolls photos. With these two items, the algorithm of the application then creates an original picture.

Malevich

This AI photo filter editor for IPhone (free from the iTunes Store) gives you a choice: unlimited low-resolution images of your favorite painters – Van Gogh, Monet, Picasso, Warhol, Munch, Renoir or Dali – free, It is the Pro level that matches eight bones. Both levels quickly and easily picture your photos.

Lucid

With Lucid (free from the iTunes Store), Dali, Van Gogh, Picasso, Kandinsky, Lautrec, and others, you can instantly see how a view of the camera roll will look like if it is painted by one of its masters. The app supports a variety of generic styles such as Street Arts, Geometric Art and Stained Glass. The appropriate part is that you will see all the low-resolution views of the 20 main styles without having to navigate them, so you’ll have a faster way of picking your favorite style. The app also implies which filters may look best with specific photos. Once you’ve selected your favorite item, you can share it via social networks or save it in a drop-down box or email it to yourself.

Artisto

Artisto (free from the iTunes Store) is one of the few AI apps on the list of hits that include both phone and video. After you start the application, take a photo or video from your Camera Roll or take a new 10 second video, a second ring video or photo and pair it with one of the 20 styles in the app; Van Gogh, Dali, Picasso and other masters. It is enough to take a video and apply a filter. The application will then create a short video of the same stille.

DeepArt

DeepArt uses a proprietary algorithm that blends elements of a visual style to reproduce the content of a different view or video to apply photos or video-style styles with a web-based application.

When you upload a destination image, you choose from a variety of style presets or a second photo to derive style. The app offers just 18 popular styles for you to start working for 500×500 pixels free of charge in an unlimited number. Because viewing video requires frame-by-frame continuity, the application tracks images over time.