AT-AI15 · Deep learning
Handwritten Digit and Text Recognition
Reads handwritten digits or words drawn on screen or from a photo.
- Suits
- Sem 5–6
- Branches
- CSE, ISE, AIML
- Type
- Software
How it works
A convolutional neural network is trained on a large set of handwritten samples. You draw a digit on the on-screen pad or upload a photo. The image is cleaned, resized to the size the network expects and passed through the model, which returns the character it thinks it is with a confidence value. A report shows the accuracy on test data.
What it does
- Draw-and-predict pad
- CNN model
- Accuracy report
Built with
Python, deep learning
What you get
- Working software with full source code
- Steps to install and run it on your laptop
- Rough report and explanation of the working
- Live demo on video call before the final payment
Good to know
- Features are as listed here. Anything extra is quoted separately.
- Runs on a normal laptop unless we tell you otherwise.
- Full reports and PPTs are not included.
Similar projects
- AT-AI06Stock Trend Prediction Using LSTMLearns from past prices to forecast the short-term trend of a stock.
- AT-AI13Plant Leaf Disease DetectionUpload a leaf photo and the model names the disease.
- AT-AI14Facial Emotion RecognitionDetects emotions such as happy, sad and angry from a face on webcam.
- AT-AI16Brain Tumour Detection from MRIClassifies MRI scans as tumour or normal and highlights the region.