Sub-regional Fuzzy Features for Image Retrieval
Mrinal Mandai, Tapobrata Lahiri, Uma Ranjan Jena, Arghya Mandal · 2000
The use of pre-attentive sub-regions ofa face instead of the whole face while searching 'similar' faces in an image database is investigated. This is especially relevantin situations where the face is artificially distorted using make-up or disguise toavoid detection. It has been found that the sub-regionfacial features are much more effectivein ordering similarity of faces compared to that obtained with whole face features inthe sense that if one feature ina sub-region fails for some reason, other features may fulfil the task. Individual ranking of each sub-regional features is utilized as truth values of fuzzy predicates in similarity measure and the Combined Rank Set produced very good result in image retrieval process. Use of fuzzy predicate emphasizes the interrelations between the regional features in a face and thus re-occurrence of an element in the combined rank set can be explained as strongrecommendation or that feature in similar faces. Thestorage space may be reduced in a large image database by storing only preattentive features of sub-regions in vector form instead of storing allsub-regional features in matrix form. Experimentally, it is shown that these pre-attentive features can he used for image queryin a personal computer with a huge saving in storage space - aslarge as 128:3 for face images ofsize 64 by 64.