Electric Vehicle Charger Socket Recognition and Semantic Retrieval Model using OpenCLIP (ViT-B/32)

Built OpenCLIP-based recognition and text-image retrieval for five EV socket classes. This project demonstrates practical execution from architecture and implementation to measurable delivery outcomes.

Personal ProjectsYear 2026

Project Overview

Objective

Built OpenCLIP-based recognition and text-image retrieval for five EV socket classes.

Stack

OpenCLIP (ViT-B/32)

Delivery highlights

  • Built a model that can recognize different types of Electric Vehicle charger sockets and support similarity search using OpenCLIP (ViT-B/32). The model converts both images and text descriptions into numerical vectors (embeddings) that represent their visual meaning. By placing images and text in the same vector space, the system can classify five socket types (AC Type 1, AC Type 2, DC CCS Type 1, DC CCS Type 2, CHAdeMO) and also match user text queries with relevant images.
Back to Topic ProjectsBack to All Projects

Related Projects

3 items

Electric Vehicle Charger Socket Semantic Visual Search System with YOLO, CLIP, and FAISS

Personal ProjectsYear: 2026

Built two-stage semantic retrieval and socket-type refinement for EV charger images.

Semi-Supervised Video Object Segmentation for Electric Vehicle Charger Socket Tracking

Personal ProjectsYear: 2026

Extended previous Electric Vehicle Charger Socket Instance Segmentation and Electric Vehicle Charger Socket Instance Segmentation & Tracking projects by building a custom DAVIS-style dataset with YOLOv8-Seg and adapting it for XMem to enable temporally consistent pixel-level segmentation across video frames.

Electric Vehicle Charger Socket Detection API

Personal ProjectsYear: 2025

Built REST API for real-time EV socket detection and classification.