Projects on MOZA

Computer Vision Labs: OCR, Object Detection, Segmentation and Generative AI

Wed, 14 Oct 2026 00:00:00 +0000

Overview

Computer Vision Labs is a collection of three practical experiments in computer vision and generative AI. The project combines image preprocessing, pretrained vision models, and diffusion-based generation to solve different tasks with separate workflows.

The labs cover:

OCR with image preprocessing
Object detection, segmentation, and relative depth estimation
AI-powered interior redesign

1. OCR and Image Preprocessing

The first lab uses OpenCV and Tesseract OCR to extract text from a noisy image. The workflow improves the input before OCR rather than sending the raw image directly to Tesseract.

CampusVoice

Fri, 01 May 2026 00:00:00 +0000

Overview

CampusVoice is a secure, anonymized feedback collection platform built for universities. It allows students to submit honest evaluations of courses and instructors without any login, while providing professors and administrators with actionable insights through a protected dashboard.

Built as a Cloud Computing mini-project for the Master’s program in AI & Emerging Technologies at FPN Nador.

Key Features

Anonymous Student Submissions — No login required, anonymity-first design
Role-Based Access Control — Separate interfaces for students, professors, and administrators
Real-time Dashboard — Filter, analyze, and export feedback data as CSV
Anti-Spam — One feedback per professor per day per IP, rate limiting (5 attempts / 60s)
Cloud-Native — Deployed on Microsoft Azure (PaaS architecture)

Architecture

A 3-tier design:

Ciora

Fri, 01 May 2026 00:00:00 +0000

Overview

Ciora is a Bash-based recon automation tool built for bug bounty hunters and pentesters. It downloads the HackerOne program scope (public or private with session cookie), extracts web assets & wildcards, and optionally performs subdomain enumeration using multiple tools.

Features

Supports public & private HackerOne programs (cookie auth for private)
Automatically extracts:
- Web assets
- Wildcards
- Cleaned wildcard domains
Subdomain enumeration with:
- Amass
- Sublist3r
- Assetfinder
- Subfinder
- ShuffleDNS
Merges results into one file (all_subdomains.txt)
Pretty banner + clean output

Installation

Clone the repo and install dependencies:

Autonomous Vehicle Perception

Sun, 01 Mar 2026 00:00:00 +0000

Overview

A computer-vision project developed as part of my Master’s studies.

The project explores perception for autonomous-vehicle scenarios, including situations such as driver distraction and passenger posture.

Technology Stack

Python
Computer Vision
Machine Learning

E-commerce Customer Segmentation — Big Data & Machine Learning

Thu, 15 Jan 2026 00:00:00 +0000

Overview

This project applies Big Data processing and machine learning to e-commerce transaction data. It builds customer-level features with RFM analysis, compares clustering approaches, and demonstrates how incoming transactions can be associated with previously computed customer segments.

The implementation uses Apache Spark and PySpark for distributed processing, Spark MLlib for K-Means clustering, and Kafka with Spark Structured Streaming for transaction enrichment.

Workflow

The project follows an end-to-end customer segmentation workflow: