Nanonets Blog

https://rossum.ai https://nanonets.com https://www.mindee.com/

I used a video's frames of myself playing RDR2 to train a neural network. I then showed it a photo my son took of some cows at the in-law's place. Here's what happened: https://photos.app.goo.gl/sDTofashQdDSUJMdA The network was trained with https://nanonets.com, if anyone is interested. Interesting stuff, given the knowledge came from synthesized horses. I did not train or segment any other entities other than Arthur and his horse. Labels were 'horse' and 'human'.

I am Prathamesh, co-founder of https://nanonets.com We were working on a project to detect objects using deep learning with raspberry pi and we have benchmarked various deep learning architectures on pi. With ~100-200 images, you can create a detector of your own with this method. In this post, we have detected vehicles in Indian traffic using pi and also added github links to code to train the model on your own dataset and then script to get inference on pi. Hope this helps!

Of course you can train deep learning models on small datasets. Where did you hear otherwise? Try yourself at https://nanonets.com/

Shameless plug for my structured LLM outputs handbook which is written in a similar spirit: https://nanonets.com/cookbooks/structured-llm-outputs/

This is a nice guide. I especially like the masked decoding diagrams on this page https://nanonets.com/cookbooks/structured-llm-outputs/basic-concepts/c… edit: Somehow that link doesn't work... It's the diagram on the "constrained method" page

Results with our benchmarking -> https://nanonets.com/research/nanonets-ocr-2/

We have evaluated against Gemini-2.5-flash. You can check the benchmarks here https://nanonets.com/research/nanonets-ocr-2/#markdown-evaluations

Picked a few articles from results of search engine terms, "app to translate using camera" and "finding blocks of text in an image using python" Google Lens mobile translate app [1] via smartphone. Article walking through how Google Lens does the translation.[2] Article about the text box boundary(s) [3] [1] : https://blog.google/products/translate/google-translates-instant-camer… [2] : https://medium.com/technovators/scene-text-detection-in-python-with-ea… [3] : https://nanonets.com/blog/deep-learning-ocr/

Maybe this is helpful: https://nanonets.com/blog/receipt-ocr/ In my Opinion Tesseract is the most sophisticated "free" OCR solution out there. The problem with Tesseract is not its recognition capabilities, but more the preprocessing steps. - thresholding - deskewing - segmentation - ... There is a C# library (non-free), that improves recognition A LOT, just by providing these abilities: https://www.vintasoft.com/vsocr-dotnet-index.html If you find a good Open Source solution, I would be interested, too...

A routine automation task is information extraction from any kind of document with a visual layout - receipts, PDFs, web pages. [1] [2] [1] : https://nanonets.com/blog/information-extraction-graph-convolutional-n… [2] : https://arxiv.org/pdf/1903.11279.pdf

Hey guys, here's the updated URL: https://nanonets.com/blog/handwritten-form-ocr-handwriting-recognition…

Not trying to just put in a baseless plug, but most of what you say can be refuted if you try out our product. Go here: https://nanonets.com/ocr-api/

The challenge is doing this offline/on-device. There are a billion receipt scanner APIs and services in the cloud that are basically "upload image, get back structured receipt data", but that's not what you want? Some links... - A 2019 machine vision competition about this exact use case: https://rrc.cvc.uab.es/?ch=13. Some of the submissions in the results table will discuss their methods in depth (usually in Python though). - Implementing this without AI/ML, just using Tesseract (open-source OCR, but poor performance compared to commercial apps or ML): https://pyimagesearch.com/2021/10/27/automatically-ocring-receipts-and… - Using Google's ML-kit (on-device Document Scanner SDK): https://teresa-wu.medium.com/googles-ml-kit-text-recognition-with-samp… but the tabular data is hard to work with. This writeup goes one step further: https://hackernoon.com/using-google-mlkit-text-recognition-to-scan-tab… - 2019 HN discussion on the same: https://news.ycombinator.com/item?id=10338199 - A cloud OCR vendor (Nanonets) discussing their ML-based pipeline: https://www.linkedin.com/pulse/how-build-ocr-receipt-scanner-from-scra… ---------- (Edit: Cloud options) Last time I looked into this (for a similar use case) I didn't get very far, and decided that using the cloudy Nanonets receipts API (https://nanonets.com/ocr-api/receipt-ocr) or the Google Cloud document classifier…