hemraj007 Goto Github PK

carrental

covid-19

General awareness website for covid-19 pandemic

dict2vec

Dict2vec is a framework to learn word embeddings using lexical dictionaries.

hello-world

first repository to learn how github works. It will be used to store my ideas.

imagetotext

# ImageToText An android application for image to text conversion using optical character recognition(OCR) ### Overview ImageToText allows you to extract text from camera preview directly. It is an experimental application for Android that performs optical character recognition (OCR) on images captured using the device camera. Runs the Tesseract OCR engine using [tess-two](https://github.com/rmtheis/tess-two), a fork of Tesseract Tools for Android. ### Features * convert images to pdf * recognize text in images * basic document management * search text in generated content ### Usage The application consists of: - Capture Image - Crop - Rotate - Binarize (enhance image) - Recognize Text (English) - Search - Copy to clipboard - Generate a text file and captured images PDF ### Libraries - [android-image-cropper](https://github.com/ArthurHub/Android-Image-Cropper): for image cropping. - [tess-two](https://github.com/rmtheis/tess-two): to recognize text (tesseract) and binarize (leptonica). ### Support - Android 4.0 + ### Advantages - flexible - web or multi-media tie-up - user friendly - cost effective - inclined to adopt digitization - automates the manual traditional process by generating content as a digital version - digitize multiple pages in concurrent and time saving manner - efficient retrieval of content using indexing and searching ### Future Scope Government bodies, archivists, publishers etc. have a large number of printed documents stored physically which is inconvenient in searching, securing and maintaining as compared to digital documents. Plan is to build a prototype that will digitally migrate printed documents to editable text, without manually flipping the pages. Our system will generate a indexed digital version of the document by using cloud based OCR (Optical character recognition).

lab

API and Back-end

labexamportal

onlinetestmanagementtool

webscraperpython

Python Script to scrap doctor's information from medindia's website.