Researchers at the University of Northumbria, England, have developed a new method that uses artificial intelligence (AI) to improve visual search engines. The Deep Discoveries project creates a research platform that identifies and combines digital images to facilitate user experience.
- Are artificial intelligence and machine learning healthy the same thing? Understand
- Artificial intelligence facts you need to know
- Artificial intelligence acquires the ability to “imagine” the world around you
Instead of typing a keyword into a conventional search box, the new visual search uses a main query image and built-in computer vision to find similar collections based on pre-programmed criteria such as colors, texture patterns. and geometric shapes.
“We have found objective ways to visually demonstrate the reasoning of artificial intelligence to improve search criteria within the platform. After several attempts, we were able to improve the visual search engine by using much more complex image comparison functions, ”explains design professor Jo Briggs, co-author of the study.
Want to keep up to date with the hottest tech news of the day? Go subscribe to our new youtube channel, Canaltech News.
Every day a summary of the main news from the tech world for you!
The new visual search method has been implemented in the British National Archives collection to catalog thousands of digital collections. The idea is to create an interface that can make search engines more precise, using specific parts of images to find similar elements.
Deep Discoveries is one of eight projects funded by the Culture Program which aims to open the collection of the British National Archives to the world. The five-year initiative will benefit the public and researchers, making heritage collections more accessible to all users.
“The design process led us to a common understanding that allowed us to create a prototype in real time, taking into account the different points of view between the teams involved in this multidisciplinary project. With this, it was possible to develop a robust and easy-to-use platform, ”adds UK National Archives software engineer Bernard Ogden.
The Deep Discoveries project uses new machine learning methods to create a computer vision research platform capable of identifying and matching images in digitized collections at scale. Research technology focuses on specific themes, for example, it can recognize a rose in a textile pattern and the same flower in a herbarium or in a ceramic vase.
Visual search identifies common patterns in different objects (Image: Reproduction / British National Archive) 660
With this visual search system, researchers want to create a network of collections with specific images from across the UK, eliminating the need for a single type of unifying collection based on keyword research such as prints on wood, paintings, frescoes or photographs.
“Creating an integrated and accessible digital collection requires research and implementation of many standards and new technologies. But the initiative also opens the door to new playful and creative methods of research and discovery, such as computer vision research, which can lead to unexpected ways of engaging the public with digitized images ”, concludes the head of research at the British National Archives Lora Angelova. .
Source: University of Northumbria
Did you like this article?
Subscribe to your email on Canaltech to receive daily updates with the latest news from the world of technology.