Ronak Kosti, Ph.D.


Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 10.136
Martensstr. 3
91058 Erlangen


  • ICONOGRAPHICS: Computational Understanding of Iconography and Narration in Visual Cultural Heritage

    (FAU Funds)

    Term: April 1, 2019 - March 31, 2021

    The interdisciplinary research project Iconographics is dedicated to innovative possibilities of digital image recognition for the arts and humanities. While computer vision is already often able to identify individual objects or specific artistic styles in images, the project is confronted with the open problem of also opening up the more complex image structures and contexts digitally. On the basis of a close interdisciplinary collaboration between Classical Archaeology, Christian Archaeology, Art History and the Computer Sciences, as well as joint theoretical and methodological reflection, a large number of multi-layered visual works will be analyzed, compared and contextualized. The aim is to make the complex compositional, narrative and semantic structures of these images tangible for computer vision.

    Iconography and Narratology are identified as a challenging research questions for all subjects of the project. The iconography will be interpreted in its plot, temporality, and narrative logic. Due to its complex cultural structure; we selected four important scenes:

    1. The Annunciation of the Lord
    2. The Adoration of the Magi
    3. The Baptism of Christ
    4. Noli me tangere (Do not touch me)
EMOTIC (Emotion Recognition in Context)
  • The goal of this project is providing machines with the ability of understanding what a person is feeling from his/her frame of reference, taking into account the scene context: where is this person, what is this person doing, how does this person look, etc
    Project Details: Link


Journal Articles


Conference Contributions


Journal Articles

Conference Contributions


Conference Contributions

Computer Vision Lectures for Summer Semester 2020

Running Thesis/Projects:
Title Type Status Student
Similarity and duplicate search in artwork images MA thesis open Yinan Shao
Enhancing the robustness and efficiency of multimodal emotion estimation models MA thesis running Ahmed Gomaa
Enhanced Generative Learning Methods for Real-World Super-Resolution Problems in Smartphone Images BA thesis running Alexander Schmidt
Network Deconvolution as Sparse Representations for Medical Image Analysis BA thesis running Emad Wahid
Continual Learning for Object Detection in Art Historical Images MA thesis running Rami Mahfoud
Content-based Image Retrieval based on compositional elements for art historical images BA thesis finished Tilman Marquart
Pose Based Image Retrieval in Greek Vase Paintings MA thesis finished Angel Villar-Corrales
Adversarial Modeling of Emotions in Visual Scenes BA thesis finished Benedikt Mielke
Emotion Recognition Guided by Gaze and Context on Images MA thesis finished Luis Carlos Rivera Monroy

Find different projects/topics for Forschungspraktikum, Bachelors/Masters thesis at this link: Google Drive Link

These projects will be co-supervised by Prathmesh Madhu