A robust face recognition using automatically detected facial attributes

Immense amount of face image presence led to the dire need for an efficient face recognition approach that can automatically retrieve the preferred face image from the database. Thereby, this paper introduces the use of attributes for efficient face image search. The appearance of images can be described by labelling them with these attributes. This paper mainly focuses on face images and the attributes associated with them. Age, Race, Hair Color, Smiling, Bushy Eyebrows etc., are some of the face attributes. The benefit of using attribute-based face representation is that the face images can be categorized into multiple levels based on the attribute descriptions. For example, one can describe "brown female" for a group of people or "brown female long hair black eyes" for a specific person. We demonstrate the effectiveness of the proposed method by measuring the attribute scores for face images present in PubFig image database. Further, this paper presents a novel and efficient face image representation based on Local Octal Pattern (LOP) texture features. The standard methods (LBP, LTP, LTrP) are able to encode with a maximum of four distinct values about the relationship between the referenced pixel and its corresponding neighbors. The proposed method encodes eight distinct values by calculating the horizontal, vertical and diagonal directions of the pixels using first-order derivatives. The performance of the proposed method is analyzed with the standard methods in terms of average precision and average recall results obtained on PubFig image database.