Onur Kirman

I am a Senior Computer Science & Electrical and Electronics Engineering Senior Undergrad at Özyeğin University.
I have a goal of making our world a better place to live for all of us. Lately, I have been motivated to enhance my knowledge about the topics such as; AI, Deep Learning, Network, Computer Vision, and IoT areas and trying to find the best route for myself.

Education

• Özyeğin University (OzU)
  B.S.E. in Computer Science & Electrical and Electronic Engineering | Expect: Sept. 2015 - June 2021
  
  

  Some classes I have taken:

  • CS 468 – Contemporary Topics in Networking
  • CS 449 – Natural Language Processing
  • CS 447 – Computer Networks
  • CS 434 – Advanced Object-Oriented Programming
  • CS 423 – Computer Vision
  • CS 399 – Communication Security
  • CS 350 – Operating Systems
  • CS 333 – Analysis of Algorithms
  • CS 321 – Programming Languages
  • CS 320 – Software Engineering
  • CS 201 – Data Structures and Algorithms
  • CS 102 – Object Oriented Programming
  • IE 395 – Agile Management (Certificate Elective)
  • EE 341 – Fundam. of Communication Systems
  • EE 321 – Microprocessors
  • EE 302 – Digital Signal Processing

• Asiye Ağaoğlu Anatolian High School (ASAL)
  High School Education | Sept. 2011 - June 2015

Portfolio

Handwritten Text Segmentation &
Optical Character Recognition with Visual Transformer

I focused on the part of OCR called ‘Handwriting Line Segmentation’ to detect and segment text lines pixel-wise one by one from a given handwriting paper image. I used the Convolutional Neural Network model to train with handwritten images and their corresponding line masks to detect lines at a later step. As a final decision, I end up using U-net to segment every single pixel of the images. I used a mask that has two classes one background and one handwriting line where the background is black, and the handwriting line is white.

Sudoku Puzzle Recognition

The project focuses on finding Sudoku Puzzle boxes, with the help of PCA detection of each digit on the puzzles. It mainly focuses on implementing PCA (Principle Component Analysis) and with the help of 'MNIST' train dataset, detecting given digits using some classification algorithms.

Movie-App

Simplistic website that is similar to IMDb using React.js and Firebase. There are users Admins that can surf through the database from the prepared table like interface. Also, they can add/remove to their list as they wish. Table's are real-time so that every user sees the latest list of movies as DB updated. Also, it is secure and protected with token authentication at every page.

Experience

Contact