Skip links to main content
Logo of Geometric Image Processing Laboratory,
Computer Science Department Home
Technion Home Page

Projects Proposed Projects

Please see propose projects for Spring and Winter upcoming semesters. This is a 4 academic point course. For further details please contact the laboratory engineer Yaron Honen (04-8295535, room 441).

Project Title:

Color dithering in 3D printing

Picture of Color dithering in 3D printing
Abstract:

Printers use a finite set of colors. Given a regular 24 bit (8 bits per color) image, with opacity (Alpha channel) we would like to explore the state-of-the-art in color dithering and have an implementation of such an algorithm. This specific implementation will be used for driving a high-end 3D color printer in the CS department. This specific printer have support for up to 4 different colors (typically yellow, cyan. Magenta and white). 

Supervisors:
Requirements:
  • Some background in Image and Signal Processing.
  •  Implementation must be as a C module (due to legacy reasons!)
Project Title:

Deep Semantic Shape Reconstruction

Picture of Deep Semantic Shape Reconstruction
Abstract:

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals by semantic segmentation. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650

Supervisors:
Requirements:
Some background in Image and Signal Processing. An elementary course in Deep Learning (e.g. 236605) and hands-on experience with Tensorflow/PyTorch/Keras. The project is reserved for dedicated excellent students with exceptional hands-on programming and system engineering skills. It is research-oriented, and the best fit for future M.Sc. students interested in an article publication
Project Title:

Deep Precise Shape Reconstruction

Picture of Deep Precise Shape Reconstruction
Abstract:

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals via supervised and unsupervised learning methods. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650

Supervisors:
Requirements:
Some background in Image and Signal Processing. Elementary course in Deep Learning (e.g. 236605) and hands-on experience with Tensorflow/PyTorch/Keras. The project is reserved for dedicated excellent students with exceptional hands-on programming and system engineering skills. It is research oriented, and a best fit for future M.Sc. students interested in an article publication
Project Title:

Virtual Try On

Picture of Virtual Try On
Abstract:

Deep Learning architectures have revolutionized the field of Computer Vision, completely altering the way we view 2D and 3D signals. In this project, we tackle the problem of precise and realistic reconstruction of 3D signals by semantic segmentation. The student will take part in creating novel architectures to push current state-of-the-art benchmarks one step further. More details: @https://arxiv.org/abs/2001.09650

Supervisors:
Requirements:
Some background in Image and Signal Processing. An elementary course in Deep Learning (e.g. 236605) and hands-on experience with Tensorflow/PyTorch/Keras. The project is reserved for dedicated excellent students with exceptional hands-on programming and system engineering skills. It is research-oriented, and the best fit for future M.Sc. students interested in an article publication
Project Title:

ZoomEmotion

Picture of ZoomEmotion
Abstract:

In this project, we would like to develop the ZoomEmotion - an algorithm that detects the emotional state of the child in real time and signals the teacher when the child is experiencing a negative emotion.
A previous very successful students’ project performed recently in the GIP lab in cooperation with the Educational neuroimaging center, trained a deep learning network to recognize facial expressions in children. The results of the network gave very high sensitivity and specificity rates. In this project we would like to expand the previous project to recognize the faces of the children and their emotional state in real time. We would also like to quantify the time that negative emotions are present and to provide a feedback

Goals: Recognize the children’s faces, Improve the existing facial emotional recognition networks of adults and children (separate networks) to fit faces frames taken from different angles. Apply the emotion recognition software to the adult and the children simultaneously.  Calculate the emotional synchrony between the childrento the teacher. In other words, if several children are demonstrating negative emotions, the teacher will get an additional signaling.

Supervisors:
Requirements:
  • Excellence students
  • Programming experience in C++ and/or Python
  • Advantage courses in Machine/Deep Learning and/or Image Processing
Project Title:

Neuro feedback based Virtual reality for practicing mindfulness principles

Picture of Neuro feedback based Virtual reality for practicing mindfulness principles
Abstract:

In this project we would like to expend the previous project by adding more channels of physiological input from the user together with more sensory feedback to the user. In addition new VR scenes will be designed. 
The project’s main objectives are - 
1. Getting to know the current system.
2. Integrate new physiological inputs of Heart rate and breathing (which are additional outputs of the muse 2) to the system software.
3. integrate a tactile sensory feedback to the user.
4. Create new VR scenes.

Supervisors:
Requirements:
  • Excellence students
  • Programming experience in C++ and/or Python 
  • Advantage courses in Machine/Deep Learning and/or Image Processing
Project Title:

VR CAD

Picture of VR CAD
Abstract:

פיתוח מערכת VR אשר תאפשר צפייה וחקירה אטראקטיבית של מודל CAD הכולל מכלול מורכב.
מימוש ממשק אינטראקטיבי לחקירת המודל מזוויות צפייה שונות במערכת VR (התייחסות למיקום הצופה יחסית למודל וסיבוב והזזה של המודל באמצעות מחוות ידיים)
פרוק והרכבה של המכלול לרכיביו השונים תוך הצגתם בנפרד.
בחלק זה, בהינתן מחווה מסוימת, תוצג אנימציה אשר בה כל אחד ממרכיבי המכלול נע במרחב למיקום חדש והמכלול מוצג כמפורק (בשלב זה נתון המסלול בו כל אחד מהמרכיבים נע במרחב). בהינתן מחווה אחרת, תוצג אנימציה אשר בה כל אחד ממרכיבי המכלול נע למיקומו הנכון במכלול המורכב.
אופציה מתקדמת – חישוב התנועה של כל אחד מהרכיבים עבור פרוק המכלול

Supervisors:
Project Title:

Sight beyond sight

Picture of Sight beyond sight
Abstract:

 A bucket of tools which enhancements the human vision sight for specific sessions: 

  • ‘lighting’ a dark.
  • enhance specific important details.
  • Focus on understanding the scenario   

Supervisors:
Requirements:
Excellent students
Project Title:

A video-based detector for attention-slips in children

Picture of A video-based detector for attention-slips in children
Abstract:

This project is a collaboration between Geometric Image Processing Lab (GIP) and Educational Neuroimaging Center (ENC). 

Attention abilities and regulation are fundamental for success in school as well as in social interactions.
An innovative intervention program of joint storytelling was used to promote cognitive abilities, sustained attention and language abilities in 4-6 year old children. Videos of these children during the intervention sessions were recorded using a web camera. We aim to quantify the children’s movement levels along the intervention sessions in order to explore an early bio-marker for ADHD and its relation to school readiness.
The project’s main objectives are -
1. Detect children from the video and follow their movements.
2. Operate a motion parameter to receive a movement score for each child over each intervention session.
3. Compare the motion parameter with different behavioral tests scores preformed with this cohort of children. 

Supervisors:
Requirements:
• Programming experience: C++ and Python
• Courses: one of the following - Computer Vision, Image Processing, Excellence students
Project Title:

R-Password a 3D password

Picture of R-Password a 3D password
Abstract:

A new approach for password in the AR/VR domains
Use RealSense to generate a 3d password by drawing a 3d scribble

Supervisors:
Project Title:

Analysis of teachers movements in classroom

Picture of Analysis of teachers movements in classroom
Abstract:

Using videos of apprentice teachers in classroom, we will inspect their body movements and face orientation. Quantitative and qualitative results will help them perform better in class.

Supervisors:
Requirements:
One of the following: course in geometry, image processing/computer vision, 3D graphics or excellent students.
Project Title:

Computer Vision Based Bike Fit

Picture of Computer Vision Based Bike Fit
Abstract:

In this project we will implement a system that can find the right parameters for adapting the bicycle to the rider.  We will use 3D or 2D camera to capture the scene and than analyze the angles and distances. 





Supervisors:

Ron Kimmel

Yaron Honen

Requirements:
Bicycle fan, bike  rider  and one of the followings: course in geometry, image processing/computer vision, 3D graphics or excellent students 
Copyright © 2016 by Geometric Image Processing Lab. All rights reserved.