Development of an algorithm and new facial recognition method, based on cranial structure, allowing greater accuracy in the identification of individuals

• Grant number: 20/09797-2
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: July 01, 2021
• End date: June 30, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Jose Soares Guerrero
• Grantee: Jose Soares Guerrero
• Company: Fullface Biometric Solutions Participações S/A
• CNAE: Desenvolvimento de programas de computador sob encomenda ; Desenvolvimento e licenciamento de programas de computador customizáveis ; Desenvolvimento e licenciamento de programas de computador não-customizáveis
• City: São Paulo

Abstract

Nowadays FullFace Biometric Solutions promotes the use of facial biometrics as a primary tool in the identification and recognition of individuals for all processes that require personal identification. Within this scope, we use technology to treat the object under analysis, facial impression, as normalization of the object, based on histogram and LBP, previous treatment of light incidence and shadow areas, which may cause interference in the process, in order to provide an optimum level of assertiveness. In order for the entire process to take place so that it does not require constant re-registration or validation, we use bone structure points to determine the basic biometric information model focus object. Being hardware agnostic, we can be used in common and low investment equipment, in addition to also making technology available for consumption as a service (Saas), within a structure based on cloud computing or edge processing. In order to make the use of facial biometrics feasible in critical processes, as the main objective of our entry in this Public Notice, we will develop anti-spoofing and proof of life (Liveness) processes, being decisive in some processes that require, besides the identification, a higher level of certainty in their characteristics and real-time recognition on remote devices, where the presence of a verification agent is not possible. As accessory processes to the main objective of our project, we will develop an analysis and determination of gender, age group and basic analysis of emotional state. (AU)