Projects funded by the NCN


Information on the principal investigator and host institution

Information of the project and the call

Keywords

Equipment

Delete all

Detectors and descriptors of the key points based on the topological information

2015/19/D/ST6/01215

Keywords:

Topology persistent homology persistent diagrams and images detectors and descriptors of the key points computer vision

Descriptors:

  • ST6_7: Artificial intelligence, intelligent systems, multi-agent systems
  • ST6_8: Computer graphics, image processing, computer vision, multimedia, computer games

Panel:

ST6 - Computer science and informatics: informatics and information systems, computer science, scientific computing, intelligent systems

Host institution :

Uniwersytet Jagielloński, Wydział Matematyki i Informatyki

woj. małopolskie

Other projects carried out by the institution 

Principal investigator (from the host institution):

dr Bartosz Zieliński 

Number of co-investigators in the project: 2

Call: SONATA 10 - announced on 2015-09-15

Amount awarded: 197 300 PLN

Project start date (Y-m-d): 2016-06-14

Project end date (Y-m-d): 2020-06-13

Project duration:: 48 months (the same as in the proposal)

Project status: Project settled

Project description

Download the project description in a pdf file

Note - project descriptions were prepared by the authors of the applications themselves and placed in the system in an unchanged form.

Equipment purchased [PL]

  1. Matlab + Toolboxes (Parallel Computing Toolbox, Statistics and Machine Learning Toolbox, Neural Network Toolbox, Signal Processing Toolbox, Image Processing Toolbox, Computer Vision System Toolbox, Image Acquisition Toolbox, Database Toolbox) (10 500 PLN)
  2. NVIDIA GEFORCE GTX TITAN Z 12GB (6 000 PLN)
  3. Wydajny obliczeniowo komputer stacjonarny (8 000 PLN)

Information in the final report

  • Publication in academic press/journals (6)
  1. Deep learning approach to bacterial colony classification
    Authors:
    Bartosz Zieliński, Anna Plichta, Krzysztof Misztal, Przemysław Spurek, Monika Brzychczy-Włoch, Dorota Ochońska
    Academic press:
    PLOS ONE (rok: 2017, tom: 12 (9), strony: 45305), Wydawca: PLOS
    Status:
    Published
    DOI:
    10.1371/journal.pone.0184554 - link to the publication
  2. Persistence codebooks for topological data analysis
    Authors:
    Bartosz Zieliński, Michał Lipiński, Mateusz Juda, Matthias Zeppelzauer, Paweł Dłotko
    Academic press:
    Artificial Intelligence Review (rok: 2021, tom: 54, strony: 1969-2009), Wydawca: Springer
    Status:
    Published
    DOI:
    10.1007/s10462-020-09897-4 - link to the publication
  3. A Study on Topological Descriptors for the Analysis of 3D Surface Texture
    Authors:
    Matthias Zeppelzauer, Bartosz Zieliński, Mateusz Juda, Markus Seidl
    Academic press:
    COMPUTER VISION AND IMAGE UNDERSTANDING (rok: 2018, tom: 167, strony: 74-88), Wydawca: Elsevier
    Status:
    Published
  4. Deep learning approach to describe and classify fungi microscopic images
    Authors:
    Bartosz Zieliński, Agnieszka Sroka-Oleksiak, Dawid Rymarczyk, Adam Piekarczyk, Monika Brzychczy-Włoch
    Academic press:
    PLOS ONE (rok: 2020, tom: 15 (6), strony: 45307), Wydawca: PLOS
    Status:
    Published
    DOI:
    10.1371/journal.pone.0234806 - link to the publication
  5. Persistence Bag-of-Words for Topological Data Analysis
    Authors:
    Bartosz Zieliński, Michał Lipiński, Mateusz Juda, Matthias Zeppelzauer, Paweł Dłotko
    Academic press:
    Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI) (rok: 2019, tom: -, strony: 4489-4495), Wydawca: International Joint Conferences on Artificial Intelligence
    Status:
    Published
    DOI:
    10.24963/ijcai.2019/624 - link to the publication
  6. Processing of missing data by neural networks
    Authors:
    Marek Śmieja, Łukasz Struski, Jacek Tabor, Bartosz Zieliński, Przemysław Spurek
    Academic press:
    Advances in Neural Information Processing Systems (NeurIPS) (rok: 2018, tom: 31, strony: 2724-2734), Wydawca: Curran Associates, Inc.
    Status:
    Published