PicTranslate: Seamless live Image Text translator
Given an image with text on it, this app can give you a new image with text modified into a different language.
optical-character-recognition convolutional-neural-networks aws translation autoencoders computer-vision article code tutorial

picTranslate is an AI based web app to translate the text on your image from one language to other while keeping the background of the image preserved. This way you can create images and presentation slides in multiple languages.

Input/Output The only input is the source image that you want the translation of. The app will generate the required image.

Use Cases Imagine you're a professor who has just given a presentation in English and now want to present to Italian audience. You might want your presentation slides in Italian for better communication. Here, picTranslate can be used to transform those slides instantly!!

Don't forget to tag @ramsrigouthamg , @Vaibhav-nn in your comment, otherwise they may not be notified.

Authors original post
Lead Data Scientist || BITS Pilani || Ex Co-Founder & CTO of a funded AI startup
Deep Learning | Computer Vision | NLP | Transformers | Technical Blogger
Share this project
Similar projects
A 2020 review of Handwritten Character Recognition
Concept of handwritten text recognition, relevant use-cases, different neural network architectures involved in achieving the results, training your own ...
Transformer OCR
Rectification-free OCR using spatial attention from Transformers.
Building a Captcha OCR in TF2.0
A Kaggle notebook showcasing the use of an Endpoint layer for CTC loss function used for building a Captcha Reader in TensorFlow.
Easy OCR
Ready-to-use OCR with 40+ languages supported including Chinese, Japanese, Korean and Thai.
Top collections