An Effective Age Classification Using Topological Features Based on Compressed and Reduced Grey Level Model of The Facial Skin

Abstract

The present paper proposes an innovative technique that classifies human age group in to five categories i.e 0 to 12, 13 to 25, 26 to 45, 46 to 60, and above 60 based on the Topological Texture Features (TTF) of the facial skin. Most of the existing age classification problems in the literature usually derive various facial features on entire image and with large range of gray level values in order to achieve efficient and precise classification and recognition. This leads to lot of comp lexity in evaluating feature parameters. To address this, the present paper derives TTF's on Second Order image Co mpressed and Fuzzy Reduced Grey level (SICFRG) model, which reduces the image dimension fro m 5 x 5 into 2 x 2 and grey level range without any loss of significant feature in formation. The present paper assumes that bone structural changes do not occur after the person is fully grown that is the geometric relationships of primary features do not vary. That is the reason secondary features i.e TTF's are identified and exp loited. In the literature few researchers worked on TTF for classification of age, but so far no research is implemented on reduced dimensionality model. The proposed Second order Image Co mpressed and Fuzzy Reduced Grey level (SICFRG) model reduces overall co mplexity in recognizing and finding histogram of the TTF on the facial skin. The experimental evidence on FG-NET aging database and Google Images clearly indicates the high classification rate of the proposed method. Index Term — Topology; texture features; bone structure; geometrical changes; compressed model; grey value reduction