Picollator – Hybrid Search Engine

Picollator is the sole web and multimedia search and indexing engine which understands text and digital images like people do it in real life. Picollator scans the Internet, processes texts, collects digital pictures and makes the index, matching visual objects in the images by pattern recognition with texts and vice a versa. Picollator finds what user wants with or without the words.

Picollator engine is capable to process combined and hybrid request, including visual queries and words, to get relevant search results according to any type of the query. The system looks right inside the content and understands its essence using both pattern recognition technology and text indexing.

Picollator is able to help you find web pages and photos more easily than any existing search system. It the future it will provide the only ranking hybrid system to deliver best search results based on all data types.

Start its web search in the lab right now.

How it works?

The hybrid ranking is performed across all resources found depending on image-based ratios and text-based ratios together. Picollator is able to understand the visual meaning of some words. It does not mean that it just count the words attached to the pictures or web pages. Its engine also uses some estimation of how text can fit visual similarity of known objects.

At the moment, Recogmission indexing engine mainly processes human faces. It means that if you want to find photos with people you need simply to upload a sample picture. You may submit a text, or a text along with a picture. All those options are unique in the web. As a result, you obtain all photos and resources containing faces which look similar to the ones from your picture. Using the same way, you may find the web pages containing the information relevant to your hybrid or simple query.

We are working to make it possible to find images with many other graphical objects rather than people faces. We did it for faces, and we will implement similar technology for other content. We did the most difficult part of the work, because two different faces look much closer than, for instance, two incompatible buildings.