Uğurcan Akyüz

I'm Computer Vision Researcher

About

With more than 5 years of expertise in developing deep learning-based computer vision solutions, I have engaged in projects related to object recognition, semantic segmentation, and image classification. My current focus is on addressing domain shift issue to enhance the efficacy of machine learning models.

Skills

Programming Languages

Python, SQL, C#

Frameworks & Libraries

PyTorch, Ray Tune, Detectron, YOLO, OpenCV, Pydicom, Nibabel, Sklearn, Pandas

Technologies

Linux, AWS (Lambda, S3, API Gateway), Docker, Git, JIRA, Multithreading, Multiprocessing

Industry Knowledge & Others

DICOM Standard, Medical Imaging Modalities (X-Ray, MRI, Endoscopy/Colonoscopy)

Resume

Education

Master's in Computer Engineering

2019 - 2023

Erciyes University, Kayseri, Türkiye

Thesis Title: Fetal Brain Tissue Segmentation Using Deep Learning

Context: To segment fetal brain tissues precisely and efficiently, state-of-the-art 3D segmentation models and patch-based training approaches have been researched. A new 3D U-Net model based on dilated convolutions has been developed. GitHub link of the project

Bachelor's in Computer Engineering

02 - 06/2018

Thomas Bata University, Zlin, Czech Republic

Program: Erasmus+ Student Exchange Program Student

Bachelor's in Computer Engineering

2014 - 2019

Erciyes University, Kayseri, Türkiye

Final Project: Mini Self-Driving Car Prototype

Task: Development of perception module for self-driving.

Professional Experience

Computer Vision Engineer

08/2022 - Present

ICterra, Ankara, Türkiye

  • Working on image classification task. Developing a computer vision solution using more than 100,000 images with deep learning models.
  • Achieved an average PR-AUC score of 0.88 across different datasets. Currently addressing the domain shift problem.

Computer Vision Engineer

07/2021 - 07/2022

Akgun Technology, Ankara, Türkiye

  • Worked on a real-time medical object detection project. Developed and packaged a deep learning system that reached a score of 0.86 mAP running at 22 FPS on the GPU.
  • Contributed to the migration of on-premise machine learning solutions to AWS, leveraging cloud capabilities for enhanced efficiency and performance.

Research and Development Engineer

10/2019 - 06/2021

Spark Calibration Services Inc., Ankara, Türkiye

  • Development and deployment of automatic measurement recognition software using deep learning. RESTful service has been implemented to be integrated with Metrology.NET.
  • Developed a data processing program, reducing the processing time for large Excel files from 45 minutes to just a few minutes.
  • Development of the SparkS script language (DSL) that is used to calibrating RF and Microwave devices.

Publications

Segmentation of fetal brain tissues using 3D U-Net and the effect of gestational age on segmentation performance

Authors: Uğurcan Akyüz, Tayyip Özcan
Journal/Conference: Nigde Omer Halisdemir University Journal of EngineeringSciences, 12 (3) , 637-643.
DOI: https://doi.org/10.28948/ngumuh.1228788

Deep Learning & Artificial Intelligence can Solve Measurement Problems with Known Confidence

Authors: Uğurcan Akyüz, Michael Schwartz
Workshop & Symposium: 2020 NCSLI Workshop & Symposium, Aurora, Colorado, USA

Contact

You can reach me via LinkedIn.

Address

Ankara, Türkiye

Loading
Your message has been sent. Thank you!