Indian Movie Face Database: A benchmark for face recognition under wide variations

Abstract

Abstract-Recognizing human faces in the wild is emerging as a critically important, and technically challenging computer vision problem. With a few notable exceptions, most previous works in the last several decades have focused on recognizing faces captured in a laboratory setting. However, with the introduction of databases such as LFW and Pubfigs, face recognition community is gradually shifting its focus on much more challenging unconstrained settings. Since its introduction, LFW verification benchmark is getting a lot of attention with various researchers contributing towards state-of-the-results. To further boost the unconstrained face recognition research, we introduce a more challenging Indian Movie Face Database (IMFDB) that has much more variability compared to LFW and Pubfigs. The database consists of 34512 faces of 100 known actors collected from approximately 103 Indian movies. Unlike LFW and Pubfigs which used face detectors to automatically detect the faces from the web collection, faces in IMFDB are detected manually from all the movies. Manual selection of faces from movies resulted in high degree of variability (in scale, pose, expression, illumination, age, occlusion, makeup) which one could ever see in natural world. IMFDB is the first face database that provides a detailed annotation in terms of age, pose, gender, expression, amount of occlusion, for each face which may help other face related applications.

A Survey of the Trends in Facial and Expression Recognition Databases and Methods

“…al. [27] Classification is performed by k-nearest neighbor (k-NN) and discriminant analysis on the FERET database [17] and an unconstrained database created similar to IMFD [28]. Recognition rate ranges from 12-91.81% for FERET Database [17] and 6.55-25.32% for the unconstrained database.…”

“…al. [76] (2014): Sparse framework with l 1 -minimization is used for facial recognition in the IMFD [28] database for robustness to age, illumination, pose, expression, lighting and storage limitations in images extracted from videos. Two kinds of features are extracted: Scale invariant feature transform (SIFT) and local binary patterns.…”

“…The features are reduced by performing principal component analysis (PCA) followed by supervised classification using k-NN and sparse representation classifier. For images in IMFD [28] (with at least 200 images per subject) from each of the 100 subjects, 100 images are used for training and the rest are used for testing. Recognition rates in the range 55-69% are achieved.…”

“…This database has steady illumination but it demonstrates the challenges in facial recognition due to makeup alterations. d. Indian Movie Face Database (IMFD) [28] contains 34512 images from 100 Indian actors collected from about 100 videos and cropped to include variations in pose, expression, lighting, resolution, occlusions and makeup. …”

Face Recognition in Videos by Label Propagation

“…IMFDB also includes large age variations through a careful selection of movies. More details can be found in our earlier work [16].…”