In graphic design, stock photos are often paired with text or more graphics. The new Shutterstock compositional search tool allows designers who are looking for a specific layout to find the right image without sifting through all the options that don’t have the right layout.
Inside the tool, designers can search for one or more keywords. Those keywords then pop up inside a layout square. Dragging the keyword icons within that space will put the matching images in the search results first. Multi-keyword capability means that you can search specifically for a photo with, for example, a cat on the right and a dog on the left.
In addition to adding keywords, designers can also add a “copy space” icon to the compositional tool. This tells the search engine to look for images that have empty space suitable for adding text in that portion of the image.
Shutterstock built the new tool using a combination of machine vision and natural language processing, along with advanced information retrieval or search techniques.
“Shutterstock is on the front lines of improving the future of visual search technology using pixel data, deep learning, and artificial intelligence. What’s remarkable about this breakthrough is that we only trained our model to learn what things are, but our deep network learned how to represent where things are, ” Jon Oringer, founder and CEO of Shutterstock, said in a press release. “For marketers, searching for an image with copy space using this tool will save a significant amount of time. We continue to innovate on this valuable search technology and invest in machine learning to improve the customer experience and provide more time for productivity and creativity.”
The compositional search tool has some similar functionality to the platform’s reverse image search tool that finds similar images, but doesn’t require a photo as a starting point. The tool also joins Shutterstock’s AI-powered auto keyword tool.
