New API startup solution makes it easier to categorize and tag items in real estate listings and on other sites
Register for full access
Our library content is no longer freely available. Please register to gain access to more than 12,000 innovations, updated daily. Our content is global in scope and covers solutions to the world's biggest challenges across 18 sectors.
Founded in early 2016, Restb.ai is a Barcelona based start-up specialising in image recognition for real estate. Image recognition is part of Computer Vision, a branch of Artificial Intelligence (AI) technology in which the software learns to recognise objects, features, and settings in images relevant to what customers are looking for. RestB’s system is different from similar API services offered by big players such as Microsoft, IBM and Google in that it can pull a large number of specific details from images.
Given the focus on real estate images, Restb.ai’s plug-n-play solution manages to identify, categorise, and deliver results on property-related images, with an accuracy on search results of 99 percent. By using the software, real estate portals can attract more visitors, keep them engaged, and ultimately, gain more profits.
We have recently seen innovations in image analysis, such as software that can animate a still image and AI that can analyse photos of food and suggest recipes, but the RestB.ai algorithm is a step forward. It is designed around convolutional neural networks. This is a deep-learning technique in which individual pieces of information are extracted and then linked together. The network is trained to recognise images using publicly-available datasets, such as ImageNet. Initial uses of the system include real estate applications, such as tagging and sorting images from different parts of a house.
Restb.ai has already partnered with letsbutterfly™ to identify features and room types in listings of properties for sale, and with Voiceter Pro to create a seamless voice search experience. Moreover, Restb.ai’s software also helped in identifying and categorising illegal products in images, as in the case of Wallapop, a second-hand marketplace mobile app. What other uses are there for a plug-n-play solution that can extract detailed information from images?