Výsledky vyhledávání - "Adilson Gonzaga"

A comparison among keyframe extraction techniques for CNN classification based on video periocular images

Autor: Marcelo G. Manzato, Carolina Toledo Ferraz, William Barcellos, Jose Hiroki Saito, Tamiris Trevisan Negri Borges, Osmando Pereira Junior, Adilson Gonzaga

Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP

Training and validation sets of labeled data are important components used in supervised learning to build a classification model. During training, most learning algorithms use all images from the given training set to estimate the model’s paramete

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a11badc0fc5f05a1a6fe8fd7729f37ab
https://doi.org/10.1007/s11042-020-10384-9

Zobrazit plný text záznamu

A Novel Fusion-Based Texture Descriptor to Improve the Detection of Architectural Distortion in Digital Mammography

Autor: Carolina Toledo Ferraz, Jose Hiroki Saito, Helder Cesar Rodigues de Oliveira, Marcelo Andrade da Costa Vieira, Osmando Pereira Junior, Adilson Gonzaga

Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP
J Digit Imaging

Architectural distortion (AD) is the earliest sign of breast cancer that can be detected on a mammogram, and it is usually associated with malignant tumors. Breast cancer is one of the major causes of death among women, and the chance of cure can inc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::138eb58efb0b27d6bf40a710d7bf55a1
https://doi.org/10.1007/s10278-020-00391-5

Zobrazit plný text záznamu

Periocular authentication in smartphones applying uLBP descriptor on CNN Feature Maps

Autor: William Barcellos, Adilson Gonzaga

Publikováno v: Anais do XVII Workshop de Visão Computacional (WVC 2021).

The outputs of CNN layers, called Activations, are composed of Feature Maps, which show textural information that can be extracted by a texture descriptor. Standard CNN feature extraction use Activations as feature vectors for object recognition. The

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3cc7d8a9441c32b229e63b5793e2f39b
https://doi.org/10.5753/wvc.2021.18890

Zobrazit plný text záznamu

Evaluating dynamic texture descriptors to recognize human iris in video image sequence

Autor: Virgílio de Melo Langoni, Adilson Gonzaga

Publikováno v: Pattern Analysis and Applications. 23:771-784

In the last decades, iris features have been widely used in biometric systems. Because iris features are virtually unique for each person, their usage is highly reliable. However, biometric systems based on iris features are not completely fraud-resi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e2895a65e7e687a937f7dc7158b84b64
https://doi.org/10.1007/s10044-019-00836-w

Zobrazit plný text záznamu

CLASSIFICAÇÃO DE TOMATES UTILIZANDO REDES NEURAIS ARTIFICIAIS

Autor: Michelle Magalhães Mendonça, Adilson Gonzaga, Antonio Henrique Figueira Louro

Publikováno v: Ciência e Tecnologia de Alimentos: pesquisa e práticas contemporâneas-Volume 2 ISBN: 9786589826941
Ciência e Tecnologia de Alimentos: pesquisa e práticas contemporâneas-Volume 2

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b83818cbde48dbb941a203d14a8cab86
https://doi.org/10.37885/210805897

Zobrazit plný text záznamu

Improving the classification of rotated images by adding the signal and magnitude information to a local texture descriptor

Autor: Adilson Gonzaga, Raissa Tavares Vieira, Tamiris Trevisan Negri

Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP

Texture image classification, especially for images with substantial changes in rotation, illumination, scale and point of view, is a fundamental and challenging problem in the field of computer vision. Natural images acquired under uncontrolled envi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::92e1d8ca5067f8847ea0e5d8ab16ce24
https://doi.org/10.1007/s11042-018-6204-1

Zobrazit plný text záznamu

Impact of Facial Expressions on the Accuracy of a CNN Performing Periocular Recognition

Autor: Carolina Toledo Ferraz, Raissa Tavares Vieira Queiroga, Rodolfo Coelho Dalapicola, Adilson Gonzaga, Jose Hiroki Saito, Tamiris Trevisan Negri Borges

Publikováno v: BRACIS

The biometric periocular trait refers to the face region in the vicinity of the eye, including the eyelids, eyelashes and eyebrows. The periocular region has emerged as a promising trait for unconstrained biometrics, due to recent advances of convolu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::790bbd5c6acde3b2bad6044a87363d15
https://doi.org/10.1109/bracis.2019.00077

Zobrazit plný text záznamu

Evaluation of Fine Tuning and Feature Extraction methods in Biometric Periocular Recognition

Autor: Carolina Toledo Ferraz, Raissa Tavares Vieira Queiroga, William Barcellos, Jose Hiroki Saito, Adilson Gonzaga, Nicolas Hiroaki Shitara

Publikováno v: Anais do XV Workshop de Visão Computacional (WVC 2019).

The aim of this paper is to evaluate the performance of Transfer Learning techniques applied in Convolucional Neural Networks for biometric periocular classification. Two aspects of Transfer Learning were evaluated: the technique known as Fine Tuning

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::03b979aa5c905b9d298833b5604ae9c2
https://doi.org/10.5753/wvc.2019.7626

Zobrazit plný text záznamu

Tecnologia para o reconhecimento do formato de objetos tri-dimensionais

Autor: Adilson Gonzaga

Publikováno v: Biblioteca Digital de Teses e Dissertações da USP
Universidade de São Paulo (USP)
instacron:USP

Apresentamos neste trabalho o desenvolvimento de um método para o reconhecimento do Formato de Objetos Tri-dimensionais. Os sistemas tradicionais de Visão Computacional empregam imagens bi-dimensionais obtidos através de câmeras de TV, ricas em d

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a1c8b075ef86911e4698dcf6a0d704e9
https://doi.org/10.11606/t.54.2009.tde-16042009-102057

Zobrazit plný text záznamu

Human iris feature extraction under pupil size variation using local texture descriptors

Autor: Jones Mendonça de Souza, Adilson Gonzaga

Publikováno v: Repositório Institucional da USP (Biblioteca Digital da Produção Intelectual)
Universidade de São Paulo (USP)
instacron:USP

The human iris texture is one of the most reliable biometric traits because it is unique, and the iris pattern remains stable for years. However, iris images acquired under uncontrolled illumination is one source of difficulties for iris recognition

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e78d57f87a05184cd5bf7142e5a86da

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání