Modeling Two-Dimensional Face from DNA Using the Face Embedding Approach in Deep Learning

Please enable javascript in your browser.

Mirzaei, Mohammad Amin | 2022

212 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 55761 (19)
University: Sharif University of Technology
Department: Computer Engineering
Advisor(s): Hossein Khalaj, Babak
Abstract:
the purpose of this research is to construct the facial image of a person from corresponding DNA. In this problem, we have a set of DNAs and facial images and we want to find the relation between the DNA and the features of facial images.using this relation we can find the facial Image of a person using the DNA. for this purpose we should first extract the features of faces that have the most variation among the population. by studying the feature extraction methods in this field, we borrow the deep neural network method that is used in face recognition fields.we found significant relations between DNA and extracted features from this network. finally using this relation we can predict the face of a person using the DNA
Keywords:
DNA Molecule ; Human Face ; Deep Neural Networks ; Two Dimentional Modeling ; Genome Data ; Significant Relation ; Face Feature Extraction