š AI Vision Assistant ā Object Detection with Voice Feedback Excited to share my latest project ...š AI Vision Assistant ā Object Detection with Voice Feedback Excited to share my latest project ...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
š AI Vision Assistant ā Object Detection with Voice Feedback
Excited to share my latest project AI Vision Assistant, an intelligent application that detects objects in real-time and provides voice feedback for better accessibility and interaction.
This project uses Deep Learning and Computer Vision to identify objects from images or webcam input and announces the detected objects using speech output. The goal is to demonstrate how AI can make technology more interactive and assistive.
š¹ Key Features:
⢠Real-time Object Detection using a pretrained deep learning model
⢠Webcam and Image support
⢠Voice feedback to announce detected objects
⢠Interactive Gradio-based web interface
⢠Built using Python, Transformers, and Computer Vision
This project helped me strengthen my understanding of AI, deep learning models, and real-time application development.
š» GitHub Repository:
[https://lnkd.in/gC3J8dzi]
I would love to hear your feedback and suggestions!
#ArtificialIntelligence#ComputerVision#DeepLearning#Python#MachineLearning#AIProjects#ObjectDetection#HuggingFace#GitHub
An AI-powered phone receptionist built for real estate agencies that answers inbound calls, qualifies leads in real time, and books showings directly to Google Calendar ā all within the call itself, with no manual follow-up required.
The problem: Real estate agencies routinely lose leads to missed calls ā after-hours inquiries, calls during showings, or overflow during busy periods. A slow callback often means the lead has already moved on to a competitor.
What it does:
Answers every call instantly, 24/7
Naturally qualifies the caller (buy/sell intent, area of interest, showing vs. agent call)
Collects contact details and preferred timing conversationally
Checks real-time calendar availability before booking
Prevents double-bookings and duplicate entries automatically
Confirms the appointment out loud before ending the call
Built with: Retell AI (conversational voice layer), n8n (workflow automation and business logic), Google Calendar API (scheduling)
Available for: Custom builds for real estate agencies, brokerages, or property management companies looking to stop losing leads to missed calls
Another productive day ā this time showcasing my Hand Gesture Mouse Control project. A Python-based computer vision project that lets you control your computer mouse using hand gestures in real time.
š Index finger ā Move the cursor
š Pinch index + middle finger ā Click
Built...
AI Lead Qualification & Appointment Automation System
AI Lead Conversion Platform ā Telegram, CRM & Automated Scheduling
Designed and developed an AI-powered lead conversion system that handles incoming Telegram conversations from first contact to qualification, CRM synchronization, and appointment booking.
The AI works with conversation history, lead profile data, unanswered questions, current funnel stage, available actions, and verified CRM data to determine the next appropriate step and generate structured responses.
The system automatically creates and updates leads in the CRM, manages qualification stages, books meetings, generates Yandex Telemost links, sends reminders, handles rescheduling, and escalates exceptional cases to a human manager.
The architecture includes dialogue state management, message deduplication and batching, PostgreSQL persistence, concurrency protection, validation before actions are executed, and safeguards against sending unverified or prohibited information.
This is not just an AI chatbot ā it is an automated sales workflow that connects Telegram, AI, CRM, scheduling, and human escalation into one controlled process.
AI makes decisions within controlled business rules instead of operating as an unrestricted chatbot.
The concurrency safeguards and validation-before-actions detail is a strong distinction hereābooking systems usually fail at the edges, not in the happy path. Iād expose a compact lead state to the operator (stage, next action, last unanswered question) so a human can resume...