Vanilla Js Object Detector

What is Vanilla Js Object Detector ?

Vanilla Js Object Detector is a lightweight JavaScript library designed for object detection in web applications. It allows developers to easily integrate object detection capabilities into their projects using the power of TensorFlow.js and the Coco-SSD model. The library is built with vanilla JavaScript, making it dependency-free and easy to use in any web environment.

Features

• Dependency-Free: Built with pure JavaScript, no external libraries required. • Real-Time Detection: Detect objects in images or video streams instantly. • Multiple Object Support: Identify and classify multiple objects within a single image. • User-Friendly API: Simple and intuitive interface for integration. • Cross-Browser Compatibility: Works seamlessly across modern browsers. • Customizable: Easily tweak detection settings to suit your needs.

How to use Vanilla Js Object Detector ?

1. Install via npm: Add the library to your project using npm with the command npm install vanilla-js-object-detector.
2. Include the Script: Add the library to your HTML file using a script tag:

   <script src="node_modules/vanilla-js-object-detector/dist/vanilla-js-object-detector.js"></script>
   

3. Initialize the Detector: Create an instance of the detector:

   const detector = new ObjectDetector();
   

4. Load the Model: Load the Coco-SSD model:

   detector.loadModel().then(() => {
     console.log('Model loaded');
   });
   

5. Detect Objects: Pass an image or video element to the detector:

   const img = document.getElementById('image');
   detector.detect(img).then(results => {
     console.log(' Detected objects:', results);
   });
   

Frequently Asked Questions

What browsers are supported?
Vanilla Js Object Detector is designed to work with modern browsers, including Chrome, Firefox, Safari, and Edge.

Can I customize the detection model?
Yes, the library allows you to tweak settings such as confidence thresholds and model paths to suit your specific requirements.

How do I improve detection accuracy?
Ensure high-quality input images and consider fine-tuning the model or adjusting the confidence threshold for better results.