Photographs and videos contain a lot of information about both the content and the device the content is made on. Here we explain the techniques we use to obtain this information from large quantities of footage.
Various techniques exist for comparing the contents of photos and videos with the contents of a database. Some of these techniques are used to find duplicates, such as MD5 and SHA1, but they only work when photos are exact copies. Photos get altered and are therefore no longer a duplicate. In 2007, ZiuZ developed its own ZZ40 algorithm for detecting ‘near duplicates’. Working closely with Microsoft, ZiuZ integrated their PhotoDNA technology with VizX2 to create an additional means of matching. PhotoDNA is a little more tolerant to changes in an image than ZZ40.
Digital cameras and smartphones that record images and video store additional information in the so-called Exif format. The Exif information usually contains the geolocation where the image was taken and the type of camera used. This information can be fully disclosed using the various ZiuZ solutions.