We proposed a solution to above problem which will help to serve visually impaired people for extracting the information printed on medicines and to minimize human error . The information is converted into a speech, and can be heard by the person on a hearing device A Tensorfow based approach trained on ICDAR 2015 dataset to recognise image so we used RNN and LSTM.
Please ignore if you have already signed up.
From leadingindia.ai in your inbox.
By submitting this form, you are consenting to receive marketing emails from: Bennett University. You can revoke your consent to receive emails at any time by using the SafeUnsubscribe® link, found at the bottom of every email.