DetectAI AI Browser Object Detection

Use a pre-trained model to localize and identify multiple objects in a single image or use a Web Camera.

The prediction generates scores for the presence of each object. Our product is a web-based application optimized for modern browsers that give users the power to localize and identify multiple objects in a single image or using a Web Camera.

Our product combines the power of TensorFlow JS and a pre-trained model for object detection from MobileNet with the ease of use of Bootstrap and Jquery, making it an essential tool for developers, businesses, and anyone looking to detect objects in images.

With our product, users can easily upload a single image or multiple images and get predictions about the contents of the image, including class names and scores. What's more, with our real-time Web Camera detections, users can quickly and easily detect objects found in their surroundings.

Our product also offers the ability to export results in a JSON file and integrate it easily with other applications. Plus, our software requires minimal implementation requirements, as it only needs a web server.

It's important to note that the detections correspond to statistical probabilities, and so accuracy is not guaranteed. The image quality and complexity also interfere with the accuracy of the prediction, and all class names are only available in English.

Our product is the perfect solution for anyone needing to quickly and easily detect objects in images. With our product, users have the power to localize and identify multiple objects in a single image or using a Web Camera, making it an essential tool for web and software developers, businesses, and more.

Limitations:

The detections correspond to statistical probabilities, hence the accuracy is not 100% guaranteed.
The image quality and complexity interfere with the accuracy of the prediction.

The UI is meant to be run using the current modern browsers. The browser should support javascript and enable javascript.

For the web camera function, the user has to give the browser consent to open and use the web camera. Your website must have enabled HTTPS access. Port 443 needs to be open in order for the browser to ask permission to load the camera
The class names are only available in English.

External sources: The following website uses TensorFlow JS, as well as a pre-trained model for object detection from MobileNet. It also uses Bootstrap and Jquery. The model is trained using the dataset COCO (http://cocodataset.org/#home).