Zeynep Cipiloglu Yildiz

ALGI - TUBITAK 1001 Project

The goal of this project is to apply the principles of human perception to 3D computer graphics rendering. For this purpose, the project will investigate techniques and develop a system that optimizes a given 3D scene for a better user perception. The project includes the following topics: perceptual saliency and visual attention, depth perception, and 3D rendering technologies.

Enhancing Depth Perception in Computer Graphics

We introduce a solution that can either be used for automatically enhancing the depth perception of a given scene, or as a component that suggests suitable rendering methods to application developers.

We propose a framework that decides on the suitable depth cues for a given 3D scene and the rendering methods which provide these cues. First, the system calculates the importance of each depth cue using a fuzzy logic based algorithm which considers the user's tasks in the application and the spatial layout of the scene. Then, a knapsack model is constructed to keep the balance between the rendering costs of the graphical methods that provide these cues and their contribution to depth perception.

Publication: ACM TAP 2013, APGV 2010

Materials: Fuzzy Logic Tutorial, Fuzzy Rules, Presentation, video1, video2, video3 

EU 7th Framework 3DPhone Project

The 3DPHONE project aims to develop technologies and core applications enabling a new level of mobile 3D experience, by developing an all-3D imaging mobile phone.

I was responsible for researching the rendering methods on 3D displays and developing 3D user interfaces considering the mobile constraints.

Demo: video

A Face Tracking Algorithm for User Interaction in Mobile Devices

A color-based face tracking algorithm is proposed to be used as a human-computer interaction tool on mobile devices. The solution provides a natural means of interaction enabling motion parallax effect in applications. The algorithm considers the characteristics of mobile use -constrained computational resources and varying environmental conditions. The solution is based on color comparisons and works on images gathered from the front camera of a device.

Publications: Cyberworlds Conference Paper, The Visual Computer Journal

Demo: video

A Perceptual Approach for Stereoscopic Rendering Optimization

The traditional way of stereoscopic rendering requires rendering the scene for left and right eyes separately; which doubles the rendering complexity. In this study, we propose a perceptually-based approach for accelerating stereoscopic rendering. This optimization approach is based on the Binocular Suppression Theory, which claims that the overall percept of a stereo pair in a region is determined by the dominant image on the corresponding region. We investigate how binocular suppression mechanism of human visual system can be utilized for rendering optimization. Our aim is to identify the graphics rendering and modeling features that do not affect the overall quality of a stereo pair when simplified in one view. By combining the results of this investigation with the principles of visual attention, we infer that this optimization approach is feasible if the high quality view has more intensity contrast.

Publication: Computers & Graphics Journal

An Interactive Watercolor Painting Tool

We present a simple, efficient solution for real-time watercolor painting simulation, based on Navier-Stokes equations. We have developed an interactive painting system that allows user to paint on a wet paper by considering different characteristics of the watercolor medium, such as paper, brush and paint.

Demo: video

Recognizing Turkish Licence Plates in Images

This is a software that is developed for recognizing the Turkish licence plates in images and can be used to automate the control process in car parks. The program is written in Java.

Licence plate recognition process consists of three main stages: locating the licence plate, optical character recognition, and processing for Turkish licence plate standards. In order to find the location of the licence plate, several image processing operations, which eliminate the pixels that cannot belong to a licence plate, are performed on the image. Then, the text is extracted from the cropped image using javaOCR library. Lastly, the recognized text is processed according to the Turkish licence plate standards.