Read text from images of books using something like tesseract ocr
Use the file below as an example
You need to show me the result that your program does after processing the image.
You can try it on any online image reader to get an idea of what I mean
When giving the sample list with book titles, please also let me know the OCR library you used, the language and whether you narrowed the rectangles around the books.
Remember that this is not a simple case of just running the OCR library from a python program, that can be done by me also. This has to be intelligent ocr where it can recognize each book and the read the title. Otherwise the accuracy won't be close to 100%. Unless the accuracy is close to 100% it is unacceptable.
Once selected from your sample processing you will have to process two more samples.
This is the final requirement -
The project involves reading book titles from an image of books.
After the titles are read they should be stored in a MySQL or sqlite table and then searched using the Google Books API. Both the title that is read by OCR and the title matched with Google should be saved to the table. Once the title is matched, it should be compared to a list of existing titles. It should be marked as found or not found.
As a sample of at least 10 different images need to be read and the accuracy should be close to 100%, at least when you match it with Google or the list.
All the libraries used should be free to use
Source code will belong to me after the project is complete
I should be able to run it on any image and get good results as described above
46 freelanceria on tarjonnut keskimäärin $585 tähän työhön
I'm a senior Python & ML developer and owner & founder of Dedeoglu Dev Company. Kindly send me a message to get in touch with me, Thanks, Yusuf.