Banca de QUALIFICAÇÃO: MAYSA LOPES FERNANDES

Uma banca de QUALIFICAÇÃO de MESTRADO foi cadastrada pelo programa.
STUDENT : MAYSA LOPES FERNANDES
DATE: 02/07/2021
TIME: 14:30
LOCAL: Link da videochamada: https://meet.google.com/mcf-twag-afg
TITLE:

Identification of forest species through the use of NIR spectroscopy

KEY WORDS:

Botanical identification; Technology; Infrared spectroscopy; Automatic identification.

PAGES: 25
BIG AREA: Ciências Exatas e da Terra
AREA: Ciência da Computação
SUBÁREA: Sistemas de Computação
SPECIALTY: Arquitetura de Sistemas de Computação
SUMMARY:

Forest botanical identification becomes more complex when only wood is available to define the species, as this subjective and difficult process requires a deeper analysis of its characteristics by specialists, increasingly scarce and not always available depending on the situation. , where the result may take weeks to be issued. Thus, the objective of this work is to use infrared spectroscopy in an automatic identification process as a guarantee of great accuracy and speed in the recognition of wood species. For the development, a portable spectrometer will be used to capture infrared spectra, with reflectance values within 740-1070 nm of a sample quantity of 10 Amazonian species with 100 dry wood specimens of different origins at 12% humidity each , being collected the spectra in two cut planes with 1000 repetitions per species/plane, resulting in 20,000 spectra in the database. The project is in the development phase, where the spectra were collected and the verification and testing phase started with the creation of an automatic recognition system. The species were selected according to criteria of local commercial importance and defined by commercial groups. So far it can be seen that out of the 10 species collected we have obtained some identifications, which validates the importance of developing this project. These collections will serve as a local collection and with the creation of an identification model for each species according to their characteristics informed by the spectra, it will be possible to have the development of a technology for automatic forest identification.

BANKING MEMBERS:
Presidente - 1743612 - MARCIO JOSE MOUTINHO DA PONTE