What is a Visual Vocabulary?

Using the eVe SDK API, you can enable a user to search through a library of images and videos using a Visual Vocabulary. A Visual Vocabulary is a representative list of images that fit a certain set of criteria. In other words, hundreds of thousands of images can automatically be distilled down to a representative set of images that can be used to quickly search the entire inventory of images. This set of representative images is referred to as a Visual Vocabulary.


A Visual Vocabulary allows a user to base an entire search on an image, rather than on a text entry. After a search, eVe will return a sortable set of images and videos based on visual similarity to the original image.


A simple Visual Vocabulary can be built using a method such as the following: given a pre-existing list of categories (such as jewelry, clothing, and sunsets), select an image from each category and add it to a vocabulary list. Do this until at least one image for each category has been added. Then, use these images as the basis for visual searches within their corresponding categories.


The following illustrates how you can use a visual vocabulary to perform different searches.