Reducing Noise in Digital Images

NVidia has announced impressive progress in using AI to remove noise from “grainy” images without access to a clean version of the image to learn from.

https://news.developer.nvidia.com/ai-can-now-fix-your-grainy-photos-by-only-looking-at-grainy-photos/

By noise – they tend to refer to the grainy result of a low light digital photo, a side benefit being that they can also easily remove textual noise.  Currently, the result is “softer” than the original clean image, but I’m curious whether it will end up causing issues with watermarking or other copy protection schemes.  At what point will “good enough” be sufficient for a derivative use when we deal in low resolution imagery on the web all the time?

Many of us in collections rely on the use of watermarks to make openly sharing our collections more palatable to our donors.  Already, we have to warn them that there is no low barrier way to really prevent unattributed image reuse… This is simply going to make that conversation even more difficult.

 

How does a small robot get around an interior space?

We’ll need a robot navigation system that will allow it to get around the inside of the library and roam the stacks.

Open Autonomous Domestic Robots – An open source system for domestic cleaning robots using low-cost hardware

Build your own friend

How to build a robot that “sees” with $100 and TensorFlow

Carmen Robot Navigation Toolkit

Mobile Robot Navigation on Partially Known Maps using a Fast A Star Algorithm Version

Mobile Robot Vision Navigation & Localization Using Gist and Saliency

Indoor Robot Navigation by Landmark Tracking

Robot Navigation

Detecting Book Spines in an Image

I have images of stacks of books – can I detect the spines? Can I get the call numbers?

Combining Image and Text Features: A Hybrid Approach to Mobile Book Spine Recognition
(combine text recognition with comparing to known images of book spines)

Automatic Book Spine Extraction and Recognition for Library Inventory Management

Discussion on the OPENCV forum

Matching book-spine images for library shelf-reading process automation

Smart Library: Identifying Books on Library Shelves Using Supervised Deep Learning for Scene Text Reading

Mobile augmented reality for books on a shelf

Viewpoint-independent book spine segmentation

Identifying books in library using line segment detector and contour clustering

A review of Augmented Reality and its application in context aware library system

Describing every 10 square feet of the surface of the earth

Interesting approach to make sharing your location verbally easier. GPS has more resolution, but is almost impossible to share quickly without some sort of electronic handshake.

What Three Words

How What3words pinpoints every spot on Earth for better navigation

Note to Libraries colleagues – this company currently has a staff of 12 just to manage and encourage the use of this single set of three-word terms…

“We make money by a tool that converts three-word addresses into latitude and longitude” (spoken by Sheldrick in the CNET interview)

Lest you say – “well, that’s interesting – but I think the terms we use should be in the public domain…” may I refer you to Patent #9883333

Hoping the Drupal community really does wake up

I hope this bit of introspection from tsvenson over at drupal.org (Wake up community – WordPress.org should scare you!) gets some traction. He makes some excellent points about how the drupal.org experience is likely to scare away anybody but the most hardy self implementers. I believe that the system is worth the effort, but acknowledge that it does take a huge amount of effort to bridge the gap from considering an install and actually doing one. Drupal 7 has made some good improvements in being easier to use as a novice, but if people are scared away when they try to play with it… where are they going to go? (and yeah… my blog is … in wordpress…)

On “protection” plans

For the first time in a long time I broke down and accepted the protection plan that big box offered me when I was checking out.  You know, “just pay an extra $15 and you will be able to exchange the thing you are buying at any time for any reason…”  I’ve always viewed these things as something that earns them extra cash while “covering” you with additional warranty service that is hard to use and inadequate when you do.

Well, I have to say … it actually seems to have been worth it on these $70 headphones I bought.  I thought to myself, “I always mangle my headphones.. what the hell, why not?!”

I bought the coverage and, so far, I’ve received 3 “free” new pairs of headphones to replace the ones that failed on me.  All I’ve had to pay is a few minutes in line at the Service Counter.  They’ve been pleasant and efficient and soon after walking in, I’ve been told to go select a new pair from the headphone display.  This last time, it is clear the manufacturer has redesigned the piece that has been failing… so maybe this set will last a bit longer. [grin]

So far… a good bet.