Podrobno

Razpoznavanje šarenice z uporabo globokega učenja
ID Lozej, Juš (Avtor), ID Peer, Peter (Mentor) Več o mentorju... Povezava se odpre v novem oknu, ID Štruc, Vitomir (Komentor)

.pdfPDF - Predstavitvena datoteka, prenos (4,76 MB)
MD5: 1B6EEE8CDAEEFE3EC6708E83A62F21FC

Izvleček
Kljub izjemni rasti globokega učenja v zadnjih letih, do sedaj še ni bil razvit globok cevovod za razpoznavo šarenice. V nadaljevanju predstavljamo splošno arhitekturo za razpoznavo šarenice navdihnjeno po strukturi tradicionalnega cevovoda za razpoznavo šarenice. Naš cevovod je zaključena konvolucijska nevronska mreža sestavljena iz dveh visoko-nivojskih gradnikov: segmentacije in razpoznave. Z množenjem izhoda segmentacijskega dela model izloči področja, ki ne pripadajo šarenici in jih poda razpoznavi. Razpoznavni del iz šarenice izlušči značilke, katere uporabimo pri razpoznavi oseb. Naša metoda je na testnih podatkovnih zbirkah dosegla visoke rezultate. Na zbirki Casia-Iris-Thousand je dosegla natančnost prvega ranga 95,12 % in na zbirki SBVPI natančnost 92,33 %. Implementirali smo tudi med-podatkovni model, naučen na vzorcih obeh zbirk, ki je na sklopu zbirk dosegel natančnost 88,53 %. Naša metoda je presegla uspešnost in hitrost tradicionalnega cevovoda. Naš cevovod, kolikor vemo, predstavlja prvo implementacijo globoke nevronske mreže, ki znotraj svoje strukture segmentira področje šarenice in to nato razpozna. Za razliko od trenutnih pristopov naš razpozna osebo na podlagi izvorne nenormalizirane slike očesa.

Jezik:Slovenski jezik
Ključne besede:Razpoznavanje šarenice, globoko učenje, konvolucijske nevronske mreže, biometrija
Vrsta gradiva:Magistrsko delo/naloga
Organizacija:FRI - Fakulteta za računalništvo in informatiko
Leto izida:2018
PID:20.500.12556/RUL-105260 Povezava se odpre v novem oknu
Datum objave v RUL:15.11.2018
Število ogledov:3977
Število prenosov:268
Metapodatki:XML DC-XML DC-RDF
:
LOZEJ, Juš, 2018, Razpoznavanje šarenice z uporabo globokega učenja [na spletu]. Magistrsko delo. [Dostopano 27 marec 2025]. Pridobljeno s: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=slv&id=105260
Kopiraj citat
Objavi na:Bookmark and Share

Sekundarni jezik

Jezik:Angleški jezik
Naslov:Iris recognition using deep learning
Izvleček:
Despite the large increase of deep learning solutions in recent years, no deep learning iris pipelines have yet been developed. Inspired by conventional iris recognition pipelines, we present our general deep architecture for iris recognition. The presented deep iris pipeline is an end-to-end convolutional neural network consisting of two high-level blocks: segmentation and recognition. The segmentation part is tasked with the generation of binary mask, which corresponds with the surface of the iris. These masks are multiplied with the original iris image and then fed to the recognition part. The recognition part extracts meaningful iris features, which are then used for matching. Our model achieved high results on both testing datasets. On Casia-Iris-Thousand it achieved a Rank-1 accuracy of 95.12% and on SBVPI an accuracy of 92.33%. We also implemented a cross-database model, trained on samples from both dataset, which achieved an accuracy of 88.53%. Our deep pipeline outperformed a conventional iris pipeline in speed and accuracy. As far as we are aware, our pipeline is the rst implementation of an end-to-end deep neural network, which is able to segment and recognize the iris image. As opposed to current deep models, which perform recognition on a pre-normalized iris image, our method uses original iris images.

Ključne besede:Iris recognition, deep learning, convolutional neural networks, biometrics

Podobna dela

Podobna dela v RUL:
  1. Iris recognition using deep learning
  2. Part of speech tagging of slovene language using deep neural networks
  3. Automatic classification of buildings with deep learning
  4. DEEP LEARNING METHODS FOR BIOMETRIC RECOGNITION BASED ON EYE INFORMATION
  5. Detection of air voids in composite structures based on image processing with convolutional neural networks
Podobna dela v drugih slovenskih zbirkah:
  1. Time series classification based on convolutional neural networks
  2. Prediction of geospatial raster data using convolutional neural networks
  3. Development of an advanced system for lane detection on GPU platforms
  4. Person age estimation based on digital images using convolutional neural networks
  5. Comparison of different deep neural network learning algorithms in autonomous driving

Nazaj