← davidasaolu.dev

04 / GRADUATE RESEARCH · COMPUTER VISION

Teachingmachinestosee.

B.Tech Computer Science from the Federal University of Technology, Akure — First Class Honours and the department’s best graduating student. Now going deeper into detection, segmentation and multimodal vision models.

Research experience ↓Projects ↓Certifications ↓
David Asaolu, used as a detection demoperson 0.98face 0.99tie 0.93● live inference
Toggle between the raw photo, detection boxes and segmentation masks.
4.8/ 5.0 CGPA

EDUCATION

B.Tech Computer Science

Federal University of Technology, Akure (FUTA)

First Class HonoursTop 1%★ Departmental Best Graduating Student

Research experience

UNDERGRADUATE DISSERTATION

Design and Implementation of an E-voting System for Elections in Ondo State

A secure e-voting system for the Senatorial District and Governorship elections in Ondo State, Nigeria — built to strengthen transparency and electoral integrity with image similarity–based voter recognition, encrypted data and results transmitted live.

ADVISOR
Prof. Olumide S. Adewale
INSTITUTION
FUTA, Dept. of Computer Science
SCOPE
Senatorial & Governorship elections

SYSTEM PIPELINE

  1. 01Voter recognitionImage similarity matching
  2. 02EncryptionBallots protected end to end
  3. 03Real-time databaseVotes recorded instantly
  4. 04Live resultsTransparent transmission

Research projects

CompletedB.Tech dissertation

Secure E-voting with Image-Similarity Voter Recognition

Voters verified by image similarity, ballots encrypted, results streamed live through a real-time database for Ondo State elections.

Image similarityEncryptionReal-time systems

What I’m looking at

01 · SEEDetection & segmentationCNNs and U-Net for finding and outlining objects.
02 · UNDERSTANDVision transformers & multimodalViTs and CLIP: models that connect what they see with language.
03 · RECOGNISEIdentity & similarityImage-similarity recognition, carried on from my e-voting dissertation.

Certifications

CUUniversity of Colorado Boulder · Coursera2025

Introduction to Computer Vision

Core computer vision principles, applying deep learning models to real-world vision tasks.

Verify certificate ↗
CUUniversity of Colorado Boulder · Coursera2025

Deep Learning for Computer Vision

MLPs, normalisation, autoencoders, GANs, CNNs and U-Net for visual recognition.

Verify certificate ↗
CUUniversity of Colorado Boulder · Coursera2025

Modern AI Models for Vision and Multimodal Understanding

RNNs, transformers, Vision Transformers, CLIP and diffusion models for visual understanding.

Verify certificate ↗
MWMathWorks · Coursera2025

Image Segmentation, Filtering, and Region Analysis

Segmenting images, filtering noise and measuring regions — the building blocks of classical vision pipelines.

Verify certificate ↗
MWMathWorks · Coursera2025

Introduction to Image Processing

Intensity and colour-based segmentation for object detection and contrast enhancement.

Verify certificate ↗
ORPackt Publishing · O’Reilly Media2025

Machine Learning for Beginners, Levels I & II

Processing and preparing datasets for ML algorithms with Jupyter Notebook and Pandas.

Verify certificate ↗
CUUniversity of Colorado Boulder · Coursera2025

Data Mining Pipeline

The data mining pipeline end to end — pre-processing and warehousing.

Verify certificate ↗
DCDataCamp2024

Python Developer

Data structures and algorithms, OOP, testing and web scraping with Python.

Verify certificate ↗

Want David to join your project or group?