TASK : Using a machine learning toolkit of your choice, create a tool which identifies objects in the image, then returns positions in pixels corresponding to bounding boxes of a user-selected class of object in the image.
Technology Used : Javascript, Tensorflow.js
- Download the Repository
- Open Index.html
- Upload Image using upload button
- Type the class of the image you want to detect. See the supported classes in classes.txt
- On clicking the predict button the model will create bounding boxes around the class typed by the user.(If the class is present in the image)
- *Download button will create a zip file of all the objects detected and will be downloaded to your computer.
- Clear button clears the canvas.
*Added after feedback from mentor.
Detecting cat from cat and dog image
Detecting person in an image
Detecting multiple objects in image
JS Library used - Filesaver, JSZIP