Image Computing and Perceptual Intelligence
Research and publish high-quality scientific papers throughout my Master's and PhD journey.
Current Address: Wuhan, Hubei, China
I am HOSEN ARAFAT, I grew up in Bogura, Bangladesh, a city renowned for its natural
harbor, rolling hills, and industrial
significance. I am a Software Engineering graduate with a strong passion for image
computing and perceptual intelligence, and building technology that can solve
real-world problems. My interest in technology started at an early age and grew from
simple curiosity into a clear academic and professional goal. Growing up in
Bangladesh, I experienced how limited access to technology can affect learning and
opportunity. That experience shaped my belief that computer science is not only a
technical field, but also a powerful tool for social and economic progress.
My academic journey took me to China, where I completed my Bachelor’s degree in
Software Engineering at Anhui University of Technology. During my studies, I built a
strong foundation in programming, algorithms, software development, and intelligent
systems. I worked hard to maintain excellent academic performance, earned multiple
scholarships, and developed strong discipline, adaptability, and problem-solving
skills. Studying in an international environment also helped me improve my
communication skills, leadership ability, and cross-cultural understanding, all of
which have become important parts of my personal and professional growth.
Through both academic work and independent learning, I have developed experience in
software engineering, artificial intelligence, machine learning, deep learning,
computer vision, web development, and immersive technologies. I enjoy building
practical systems that combine technical knowledge with creative thinking.
Strong communication across 6 different languages
Mother Tongue
Professional Communication
Listening: 78 | Reading: 89 | Writing: 98
Total Score: 265Speaking Ability
Speaking Ability
Speaking Ability
Wuhan Technical University
GPA: 3.81 Out of 4.00
Anhui University of Technology
GPA: 3.90 Out of 4.50
Sherwood In't (Pvt) School
GPA: 4.58 Out of 5.00
Fulbari Hamidia Dhakil Madrasa
GPA: 4.78 Out of 5.00
Brac Primary School
GPA: 5.00 Out of 5.00
for Academic Performance
Anhui University of Technology
2021 - 2022
for Academic Performance
Anhui University of Technology
2020 - 2021
for Academic Performance
Anhui University of Technology
2019 - 2020
“Encouragement Prize”
Anhui University of Technology
May - 2021
Math Run Mathematical Brain Game, a fun browser game where you play as a cool runner escaping from a chasing monster by solving quick math problems. Every correct answer pushes you forward, while wrong or late answers let the monster catch up! But here’s the twist: instead of typing answers, you handwrite digits (0–9) directly on the canvas.
View Project
Introducing space education to kids serves as a gateway to fostering curiosity and scientific interest. To make learning about planets a thrilling adventure, this project utilizes virtual reality, interactive apps, and hands-on activities to provide immersive experiences for children.
View Project
This project presents a novel game-based cognitive assessment system designed for the early detection of dementia. The system integrates deep learning techniques with an interactive gaming environment to evaluate cognitive health through both physiological data and facial analysis.
View Project
Vision-based intelligent game agent that learns to interact with a game environment using deep reinforcement learning. The system relies solely on raw visual input (screen pixels) to perceive the environment and make decisions, mimicking human-like perception and action.
View Project
Trajectory Forecast is a lightweight, modular extension built on top of Ultralytics YOLO that enables real-time multi-object tracking with future motion prediction. It combines detection, tracking, motion history modeling, and velocity-based forecasting into a unified pipeline.
View Project
Object Detection with oriented boxes using the off-the-shelf YoloV8s-OBB model from Ultralytics. It implements an object detection pipeline for oriented bounding boxes where objects are detected in an image, and bounding boxes and keypoints are processed for downstream tasks.
View Project
The Vehicle Detection project demonstrates real-time vehicle detection using a trained model. The system processes images or video streams and identifies vehicles within each frame for traffic monitoring, intelligent transportation systems, and smart city solutions.
View Project
Advanced Lane Detection is a computer vision–based project designed to detect and track road lane markings using image processing and classical computer vision techniques. The system processes road images and video streams to identify lane boundaries in real time.
View Project
A deep learning and computer vision project to monitor parking lots in real time. It detects cars using YOLOv8, highlights occupied and free parking spaces, and provides a live count of available slots for smart parking management.
View Project
A Generative Adversarial Network project where two neural networks, Generator and Discriminator, compete against one another to create realistic face images. This demonstrates the power of generative deep learning for synthetic image creation.
View Project
Machine learning–based facial deformation system that detects facial landmarks and applies controlled transformations to modify facial expressions or geometry in real time.
View Project
The Real-Time Stress Detection System is a computer vision–based application that estimates a user's stress level using live webcam input and facial landmark analysis. The system processes facial expressions in real time and classifies stress levels into three categories: Calm, Mild, and High.
View Project
Classify Image as Alien using Transfer Learning (VGG16). Deep Convolutional Neural Networks (CNNs) require large datasets and extensive training time. To overcome these limitations, this project uses VGG16, a pre-trained CNN model trained on the ImageNet dataset, and fine-tunes it for binary image classification.
View Project
Adaptive Traffic Signal Timer is an intelligent traffic management system that dynamically adjusts signal timing based on real-time vehicle detection and traffic analysis. The system leverages Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), and YOLOv8-based object detection to monitor traffic density and optimize green-light duration accordingly.
View Project
Nature Image Classification is a deep learning–based computer vision project designed to automatically classify images of natural scenes into predefined categories such as forest, mountain, sea, desert, glacier, and buildings.
View Project
Object Detection using Faster R-CNN with ResNet50-FPN, a state-of-the-art deep learning model for real-time object localization and classification. The model is fine-tuned on a custom dataset to accurately detect multiple object classes in images, combining region proposal networks (RPN) with a powerful ResNet-50 Feature Pyramid Network.
View Project
Automated Toll Tax Estimation System is a real-time AI-powered traffic monitoring solution that detects vehicles, tracks their movement, and automatically calculates toll tax revenue based on vehicle type. The system leverages deep learning and computer vision techniques to ensure accurate vehicle counting and classification without manual intervention.
View Project
Fire and smoke detection system using the YOLO (You Only Look Once) object detection model. The system is built with the Ultralytics YOLO library and is designed to detect smoke and fire in images and videos.
View ProjectCore programming languages and technical foundations.
Frameworks, architectures, and applied model development.
Perception systems, image analysis, and language tooling.
Data analysis, exploration, and visual communication.
Perception, tracking, navigation, and intelligent mobility.
Frontend, backend, APIs, and modern software systems.
Interactive simulations, XR systems, and spatial experiences.
Infrastructure, versioning, deployment, and research workflow.
Nilgiri Holidays
Operations Department
Worked as a Junior Executive at Nilgiri Holidays in the Operations Department, handling client-focused travel services including bookings, ticketing, visa processing assistance, and day-to-day communication with customers.
Supported customers with travel-related services while maintaining clear, professional, and helpful communication.
Managed bookings, ticketing, and coordination tasks with attention to accuracy, speed, and service quality.
Assisted clients with visa-related processes and helped ensure smooth handling of travel documentation needs.
Strengthened communication, responsibility, organization, teamwork, and customer-handling skills in a fast-paced work environment.
This experience helped me develop a stronger professional mindset, practical operational knowledge, and real-world service skills. It also prepared me for advanced academic goals by improving my discipline, confidence, and ability to work responsibly in client-oriented environments.
Feel free to reach out through email, social platforms, or by scanning the QR codes below for quick communication.
Wuhan, China
Scan the QR code below to connect with me directly on WhatsApp for quick communication.
Scan the QR code below to connect with me directly on WeChat for quick communication.
