Dynamic classifier selection based on class skew

Abstract

A classification system classifies different aspects of content of an input image stream, such as faces, landmarks, events, and so forth. The classification system includes a general classifier and atleast one specialized classifier template. The general classifier is trained to classify a large number of different aspects of content, and a specialized classifier can be trained based on a specialized classifier template during operation of the classification system to classify a particular subset of the multiple different aspects of content. The classification system determines when to use the general classifier and when to use a specialized classifier based on class skew, which refers to the temporal locality of a subset of aspects of content in the image stream.

Description

Background technique [0001] With the development of computing technology, computing devices have become more and more present in our lives. One way computing devices are used is to analyze images to identify specific objects, such as human faces, in those images. While this identification of objects is beneficial, it is not without problems. One such problem is that such analysis of images can be computationally expensive and slow, which can cause users to become frustrated with their devices. Contents of the invention [0002] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. [0003] According to one or more aspects, an image stream is received. A determination is made as to when a dedicated ...

AI Technical Summary

Problems solved by technology

One such problem is that such analysis of images can be computationally expensive and slow, which can cause users to become frustrated with their devices

Images