Google's AI will digitize NYT's 5 million historic images

The New York Times is said to have stored all its pictures under its Times Square office. The publication has around five to seven million images with information about when they were published and why. Now the newspaper is working closely working with Google to digitize its image collection.

The basement area has pictures from the 19th century, many of which are exclusive to the publication. "[It's] a treasure trove of perishable documents," says the NYT's chief technology officer Nick Rockwell. "A priceless chronicle of not just The Times's history, but of nearly more than a century of global events that have shaped our modern world."

To make this possible, the company has called Google, which will use its machine vision smarts to scan the hand- and type-written notes attached to each image and categorize the information they contain.

Google said that NYT will also be able to make use of its object recognition tools. This will allow them to extract even more information from the photos, making it easier for use in the future. This move shows how AI can preserve the history and it more accessible.

Besides, two AI researchers from Google have detailed their creation of an advanced offline AI for text classification. The AI can run on smartphones with basic specifications. During the simple data set, the AI showed an accuracy of 86.7%, while in case of more complex and multifaceted dataset it was 83.1 percent accurate.

Google has also shown how an AI might be used in real life scenarios in its latest study of AI-based Lymph Node Assistant (LYNA). The research focuses on making it easier for human pathologists to diagnose metastatic breast cancer in lymph node slides.

This is a followup of the research on the use of AI for detecting and diagnosing cancer which was reported earlier in 2018. Previously, Google demonstrated how its DeepMind could help pathologists in detecting cancer.