Name: LUCAS DE ASSIS SOARES

Publication date: 23/10/2020
Advisor:

Name	Role
PATRICK MARQUES CIARELLI	Co-advisor *
EVANDRO OTTONI TEATINI SALLES	Advisor *

Examining board:

Name	Role
MARIO SARCINELLI FILHO	Internal Examiner *
KARIN SATIE KOMATI	External Examiner *
THOMAS WALTER RAUBER	External Examiner *
PATRICK MARQUES CIARELLI	Co advisor *
EVANDRO OTTONI TEATINI SALLES	Advisor *

Summary: Texture segmentation is a challenging problem in computer vision due to the subjective nature of textures, the variability in which they occur in digital images, their dependence on scale and illumination variation, and the lack of a precise definition of textures in the scientific literature. This thesis proposes a method to segment textures through a binary pixel-wise classification, thereby without the need for a predefined number of textures classes. Using a convolutional neural network, with an encoder–decoder architecture, each pixel is classified as being inside an internal texture region or in a border between
two different textures. The network is trained using the Prague Texture Segmentation Datagenerator and Benchmark and tested using the same dataset, besides the Brodatz textures dataset, and the Describable Textures Dataset. The method is also evaluated on the separation of regions in images from different applications, namely remote sensing images and H&E-stained tissue images. It is shown that the presented method has a good performance on different test sets, can precisely identify borders between texture regions
and does not suffer from over-segmentation.

Access to document