Search engine operators offer various services such as text-based keyword search, geographic-oriented search in online map services, or visual search for images, also known as visual search. However, image search can be limited to the caption and only display images in the results page where the keyword is in the caption. However, there is a more advanced approach where instead of keywords, images are entered into the search engine and the search engine provides information about the photos, sort of like augmented reality( AR).
The approach where images are entered into the search engine is called Visual Search by Google. In this process, photos are captured by cell phone or smartphone cameras and transmitted to the search engine's server. The server compares and analyzes the captured objects - buildings, animals or landscapes - with objects in the image database and provides the user with the desired information about the building or animal.
The data of the captured objects is linked to the position data from the GPS system, so that the Location Based Services( LBS) technology, which has been tested in practice, can be partially used for buildings. Other partial approaches to visual search technology include face recognition, gait recognition, and 2D code scanning.