Οπτική αυτόματη αναγνώριση φυτού από εικόνες φύλλων του

Πλατής, Φίλιππος

Master Thesis

Author

Πλατής, Φίλιππος

Date

2016-05

Abstract

This research is based on image processing and analysis to extract the features required for clustering and recognition of images. Specifically the purpose of the project is the production of an automated system for identification of plants through snapshots of leaves. The system should be handy, reliable and independent of the user. The user of the system is required to take a snapshot of an ideal leaf of the unknown plant on a white background. The system input sample modified by optimization, conversion and morphological processing to produce shape measurements. The sample is classified by its measurements and compared with the images of the database to extract the largest similarity percentage. The algorithms which are used to measure image similarity are mean squared error (MSE), peak signal to noise ratio (PSNR), structural similarity (SSIM), visual information fidelity (VIF), gradient magnitude similarity deviation (GMSD) and universal image quality index (UIQI).

Postgraduate Studies Programme

Πληροφορική

Department

Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Πληροφορικής

Number of pages

100

Language

Greek

URI

https://dione.lib.unipi.gr/xmlui/handle/unipi/10097

Collections

Τμήμα Πληροφορικής

Show full item record

Except where otherwise noted, this item's license is described as
Attribution-NonCommercial-NoDerivatives 4.0 Διεθνές