Federico Bolelli

Thesis Proposals

This is a list of thesis proposals, both for bachelor (BSc) and master degree (MSc). Any additional idea is welcome.

Stitching of Shipping Boxes Images

Target:Master Degree
Requirements:C++
Requirements (suggested):Multimedia Data Processing - MDP"
Goals:

The goal is to implement a fast (real time) and accurate tool for stitching multiple images of shipping boxes running on a conveyor roller. The tool must produce a single image (smaller that the initial set of images) containing the entire box and preserving the barcode.

Curriculator

Target:Bachelor Degree
Requirements:Python
Requirements (suggested):Django
Goals:

Design and implementation of a Django application to write fancy, reusable, and adaptable, curriculum vitae in a smart, versatile, and fast way.

Literature: Django
  1. Tutorial

Online Judge (OLJ) - Improvements and Optimization

Target:Bachelor Degree
Requirements:Python, C
Requirements (suggested):Django
Goals:

This thesis aims at improving the current version of the OLJ web application, working both client and server side. Some of the features that should be implemented (not necessary all together in the same thesis) are:

  • Design and development of a C++ library (and it’s documentation) that implements all the basic functions used for writing tests’ code, i.e., the code that test student solutions during exam and exercises;
  • Improve and optimize the handling of student frames during exams;
  • Implement client-side build toolchain for C code;
  • Improve live chat using WebSockets;
  • Many others …

Literature: Django
  1. Tutorial

Handling Beer Recipe and Inventory

Target:Bachelor Degree
Requirements:Python
Requirements (suggested):Django, HTML, Javascript
Goals:

This thesis aims at design and develop a Django-based web application to handle beer recipes and raw material inventory.

Literature: Django
  1. Tutorial

Flow-Chart Builder

Target:Bachelor Degree
Requirements:Flow-Chart
Requirements (suggested):Django, HTML, Javascript, dot (graphviz)
Goals:

The goal is to design and develop ad-hoc language (possibly based on existing markup languages, e.g., YAML, json, or others) to define a flow-chart. Moreover, a script that converts the flow-chart definition into dot code and finally draws the chart must be develop.

Literature: Django
  1. Tutorial
dot
  1. DOT Language

Support UNIMORE Administration

Target:Bachelor Degree
Requirements:Python
Requirements (suggested):Django, HTML, Javascript
Goals:

This thesis aims at design and develop a web application to simplify, speed-up, and improve the daily work of UNIMORE administrative staff. The specific task to tackle can be discussed face to face. An example of previously developed application is the one that handle the student stage request/approval. It is available at services.ing.unimore.it.

Literature: Django
  1. Tutorial

GPU Programming and Algorithms Optimization

Target:Master Degree
Requirements:C++
Goals:

GPU programming with CUDA and optimization of Image Processing algorithms with particular attention to Connected Components Labeling and Thinning.

Literature: CUDA
  1. Programming Guide
Papers
  1. Optimized Block-Based Algorithms to Label Connected Components on GPUs, IEEE Transactions on Parallel and Distributed Systems
  2. A New Algorithm for Parallel Connected-Component Labelling on GPUs, IEEE Transactions on Parallel and Distributed Systems
  3. How does Connected Components Labeling with Decision Trees perform on GPUs?, 18th International Conference on Computer Analysis of Images and Patterns

A Web Application to Collect, Preview, Annotate, and Distribute Medical Data Collections

Target:Bachelor/Master Degree
Requirements:Python
Requirements (suggested):Django, Multimedia Data Processing - MDP
Goals:

This thesis aims to develop a django-based web application to collect, preview, annotate, and distribute medical datasets. The application design can be inspired by the ISIC archive website and must support 2D images, Virtual Slides, and 3D volumes.

Literature: Django
  1. Tutorial

Medical Imaging

Target:Master Degree
Requirements:Python
Requirements (suggested):PyTorch or equivalent frameworks
Goals:

Analysis and development of Deep Learning techniques for medical imaging. The activity can be carried out on different research topics:

  1. Segmentation and classification of skin lesions from dermoscopic and/or confocal images

  2. Inferior alveolar nerve canal detection from dental Cone Beam Computed Tomography (CBCT)

  3. Glomeruli identification in Virtual Slide images

Literature: Skin Cancer
  1. Paper
  2. ISIC Dataset
  3. Challenge 2020
Nerve Canal Detection
  1. Paper 1
  2. Paper 2
Nephrology
  1. Paper 1
  2. Dataset
  3. Paper 2

Missioni MobileApp

Target:Bachelor Degree
Requirements (suggested):Python, Django
Goals:

Missioni (missioni.ing.unimore.it) is a Django-based web application for the semi-automatic travel reimbursement forms filling. This thesis aims at developing a mobile version of such a service, possibily integrating existing systems for the acquisition of data directly from receipt photos.

Literature: Missioni WebApp
  1. Source Code
  2. Website
Django
  1. Tutorial

Web Scraping of Exam Sessions

Target:Bachelor
Requirements (suggested):Python
Goals:

This thesis aims to develop a python script for the web scraping of exam dates (using for example selenium web driver) and their publication on a dedicated google calendar.

Literature: Selenium
  1. Tutorial
Google Calendar API
  1. Tutorial

Django Inference WebApp

Target:Bachelor/Master Degree
Requirements (suggested):Python, Django, Git and GitHub, PyTorch
Goals:

Development of a Django-based web application to perform inference on existing and previously trained Deep Learning models. The final goal is to define/implement a mechanism to connect the application (i.e. the individual models/architectures available) to GitHub repositories, so that each update on a specific repository will be automatically reflected and available within the web application.

Literature: Django
  1. Tutorial
Git/GitHub
  1. Tutorial
PyTorch
  1. Tutorial

Please contact me by email for any additional info.

Contact

Federico Bolelli, PhD

University of Modena & Reggio Emilia
Engineering Department "Enzo Ferrari"


Via P. Vivarelli 10
41125 Modena (MO), Italy
Building 27, Ground Floor, "Lab. Zero"

Tel. +39 059 205 8787
federico.bolelli _AT_ unimore.it