Automatic Face Recognition for Film Character Retrieval in Feature-Length Films

Abstract

The objective of this work is to recognize all the frontal faces of a character in the closed world of a movie or situation comedy, given a small number of query faces. This is challenging because faces in a feature-length film are relatively uncontrolled with a wide variability of scale, pose, illumination, and expressions, and also may be partially occluded. We develop a recognition method based on a cascade of processing steps that normalize for the effects of the changing imaging environment. In particular there are three areas of novelty: (i) we suppress the background surrounding the face, enabling the maximum area of the face to be retained for recognition rather than a subset; (ii) we include a pose refinement step to optimize the registration between the test image and face exemplar; and (iii) we use robust distance to a sub-space to allow for partial occlusion and expression change. The method is applied and evaluated on several feature length films. It is demonstrated that high recall rates (over 92%) can be achieved whilst maintaining good precision (over 93%).

Taking the bite out of automated naming of characters in TV video

“…As has previously been noted authors [1,2] such material is extremely challenging visually as characters exhibit significant variation in their imaged appearance due to changes in scale, pose, lighting, expressions, hair style etc. There are additional problems of poor image quality and motion blur.…”

Automatic vertebrae localization from CT scans using volumetric descriptors

“…From these the best estimate of the vertebra centroid needs to be estimated [1]. We achieve this by employing the well-known mean shift algorithm which operates in an iterative fashion, adjusting the current estimate to be at the point to the average point of neighbourhood density until the local maximum is reached [3].…”

Face Recognition and Retrieval in Video

“…Arandjelovic and Zisserman [11,12] built a system to retrieve film shots based on the presence of specific characters, given one or multiple query face images. To address the variations on scale, pose, and illumination, as well as occlusion, encountered in films, they proposed to obtain a signature image by a cascade of processing steps for each detected face.…”

“…Although most of the existing research has been focused on the biometric identification paradigm, recently face recognition has been considered in the content-based video retrieval setup [11,96]. Face information is important in different kinds of videos, especially in news programs, dramas, and movies.…”