Which AI techniques are there that combine multiple models to make sense of data at different stages?

Question

I have been working to design a system that uses multiple machine learning models to make sense of data that is dynamically webscraped. Each AI would handle a specific task, for example:

An AI model would identify text in an image, then attempt to create plain text of what it might be. Once the text is extracted, it would be passed in a stored variable to an AI that can read the text to determine if it is a US city/state.

I tried to look into if others have done this, but didn't find much on it relating to what I was looking for. Does anyone know if there are potential issues with this? Logically, it looks good to me, but I figured I'd ask.

If anyone can put me in the right direction for reading material or further information, I would appreciate it.

Answer 1

You have explained a pipeline of AI algorithms for text in images: 1) Text detection, 2) OCR, 3) named entity recognition (NER). There are reams of paper on these topics.

Extracting City and Country Name from Text

• Introducing flashgeotext: extract city and country names from text
• locationtagger -A Python Package for detecting location
• A Comparison Between Spacy NER & Stanford NER Using All US City Names
• CoreNLP NER
• Detecting Locations with NER
• Papers with code for NER
• Named Entity Recognition: A Practitioner’s Guide to NLP
• Named Entity Recognition with NLTK and SpaCy

Papers on Text from Images

• A High-Robust Automatic Reading Algorithm of Pointer Meters Based on Text Detection
• Towards Spatio-Temporal Video Scene Text Detection via Temporal Clustering
• An end-to-end text spotter with text relation networks
• Recognizing Text with a CNN
• A Framework to Detect Digital Text Using Android Based Smartphone
• Detected text‐based image retrieval approach for textual images
• A CNN-Based Approach to Detecting Text from Images of Whiteboards and Handwritten Notes

Websites on Text from Images

• Deep Learning Based OCR for Text in the Wild
• Automatically Detect and Recognize Text in Natural Images
• Tesseract OCR: Text localization and detection
• OpenCV Text Detection (EAST text detector)
• Detect text in images
• Learning to Read: Computer Vision Methods for Extracting Text from Images