Age‐invariant face recognition system using combined shape and texture features

Abstract

This work presents an approach for combining texture and shape feature sets towards age-invariant face recognition. Physiological studies have proven that the human visual system can recognise familiar faces at different ages from the face outline alone. Based on this scientific fact, the phase congruency features for shape analysis were adopted to produce a face edge map. This was beneficial in tracking the craniofacial growth pattern for each subject. Craniofacial growth is common during childhood years, but after the age of 18, the texture variations start to show as the effect of facial aging. Therefore, in order to handle such texture variations, a variance of the well-known local binary pattern (LBP) texture descriptor, known as LBP variance was adopted. The results showed that fusing the shape and the texture features set yielded better performance than the individual performance of each feature set. Moreover, the individual verification accuracy for each feature set was improved when they were transformed to a kernel discriminative common vectors presentation. The system achieved an overall verification accuracy of above 93% when it was evaluated over the FG-NET face aging database.

Facial recognition using multi edge detection and distance measure

“…The combination technique is an approach that researchers take to obtain maximum feature extraction results. The technique is to combine the edge detection of Robert (Gx1), Prewitt (Gx2), Sobel (Gx3), and Canny (Gx4) based on (17) and (18). The pixel mapping for each image on each edge detection will be aggregated by row horizontally and vertically.…”

“…𝐺 𝑦 = 𝐺 𝑦1 + 𝐺 𝑦2 + 𝐺 𝑦3 + 𝐺 𝑦4 (18) In ( 17) and (18) show the process of the sum of edge detections in the horizontal (Gx) and vertical (Gy) directions. Each edge detection will give each other a strengthening effect on the image object.…”

Age-Invariant Face Recognition to Aid Visually Impaired People

“…O método foi comparado com os descritores de características locais, sendo usados individualmente ou em conjunto, e o método proposto superou todos. Ali et al [Ali et al 2015] propuseram um algoritmo Phase Congruency (PC) combinado com Local Binary Pattern Variance (LBPV) para acomodar diferentes grupos etários durante a execução do AIFR. Os resultados dos experimentos mostraram que o desempenho das características combinadas podem superar o desempenho dos conjunto de recursos individuais (PC e LBPV).…”

Fuzzy integrals for combining multiple SVM and histogram features for writer's gender prediction

“…LBP was introduced by Ojala et al [27] to perform statistical and structural analysis of textural patterns. It has been successfully used in various domains such as gender prediction [16] and face recognition [28]. LBP is calculated by comparing the grey-level value of the central pixel with neighbouring grey levels.…”