Gender Classification with Weighted Principal Component (ωPC) using BPN
Janaki Sivakumar1, K. Thangavel2
1Janaki Sivakumar, Research Scholar, PRIST University, Thanjavur (Tamil Nadu), India.
2Dr. K. Thangavel, Professor and Head, Department of Computer Science, Periyar University, Salem (Tamil Nadu), India.
Manuscript received on 13 April 2017 | Revised Manuscript received on 20 April 2017 | Manuscript Published on 30 April 2017 | PP: 106-111 | Volume-6 Issue-4, April 2017 | Retrieval Number: D4924046417/17©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Gender Classification in the field of forensic Science becomes essential in the case of criminal investigation. Automated tools can help forensic experts by reducing their manual efforts. Soft computing techniques like Fuzzy Computing, Neural Networks and Genetic Algorithm are all helpful to develop automated tools for human identification. Lateral Cephalogram plays a vital role in Gender Classification from skeletal remains. Principal component analysis (PCA) is a technique that is useful for the compression and classification of data. This study proposes Weighted Principal Components of lateral Cephalogram landmarks as an ideal measure .Also this study recommends BPN as an optimal classifier for Gender Classification from lateral Cephalogram.
Keywords: Lateral Cephalogram, Forensic Anthropology, Cephalofacial Landmarks, Linear Measurements, GLCM Features, Principal Components, Weighted Principal Components, Feature Extraction and Back Propagation Neural Network
Scope of the Article: Classification