The automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.

A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures

Pavoni G;Corsini M;Scopigno R
2019

Abstract

The automatic recognition of natural structures is a challenging task in the supervised learning field. Complex morphologies are difficult to detect both from the networks, that may suffer from generalization issues, and from human operators, affecting the consistency of training datasets. The task of manual annotating biological structures is not comparable to a generic task of detecting an object (a car, a cat, or a flower) within an image. Biological structures are more similar to textures, and specimen borders exhibit intricate shapes. In this specific context, manual labelling is very sensitive to human error. The interactive validation of the predictions is a valuable resource to improve the network performance and address the inaccuracy caused by the lack of annotation consistency of human operators reported in literature. The proposed tool, inspired by the Yes/No Answer paradigm, integrates the semantic segmentation results coming from a CNN with the previous human labeling, allowing a more accurate annotation of thousands of instances in a short time. At the end of the validation, it is possible to obtain corrected statistics or export the integrated dataset and re-train the network.
2019
Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" - ISTI
Human-center Computing
Graphical User Interfaces
Visual Analytics
Image Segmentation
File in questo prodotto:
File Dimensione Formato  
prod_423390-doc_150891.pdf

accesso aperto

Descrizione: A Validation Tool For Improving Semantic Segmentation of Complex Natural Structures
Tipologia: Versione Editoriale (PDF)
Dimensione 2.15 MB
Formato Adobe PDF
2.15 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/405088
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
  • ???jsp.display-item.citation.isi??? ND
social impact