In Video Indexer, we have the capability for recognizing display text in videos. This blog explains some of the techniques we used to extract the best quality data. To start, take a look at the sequence of frames below. Did you manage to recognize the text in the images? It is highly reasonable that you did, without even noticing.

The other two authors start their EDAs with more general explorations of the dataset and images themselves.

Now that the Galaxy S9 and S9 Plus are on sale, I thought we should take some time to get reacquainted with Samsung's ambitious virtual assistant. The sad truth is, the version of Bixby installed on the Galaxy S9 and S9 Plus isn't that much better than what shipped on last year's Samsung flagships. Bixby does a lot of things, but some of Samsung's most fascinating work has gone into Bixby Vision, a suite of seemingly useful image recognition tools. Here's the rub, though: They're just about all powered by third-party services, and there's often little reason to use Bixby over any of those standalone apps. Vision is legitimately useful in that it provides a single place to access these functions, but it's hard to get excited when Samsung's main selling point comes down to convenience. Samsung does, however, deserve credit for dramatically improving Bixby Vision's overall speed.

Dicom is the de-facto file standard in medical imaging.

This paper continues the research that considers a new cognitive model based strongly on the human brain. In particular, it considers the neural binding structure of an earlier paper. It also describes some new methods in the areas of image processing and behaviour simulation. The work is all based on earlier research by the author and the new additions are intended to fit in with the overall design. For image processing, a grid-like structure is used with 'full linking'. Each cell in the classifier grid stores a list of all other cells it gets associated with and this is used as the learned image that new input is compared to. For the behaviour metric, a new prediction equation is suggested, as part of a simulation, that uses feedback and history to dynamically determine its course of action. While the new methods are from widely different topics, both can be compared with the binary-analog type of interface that is the main focus of the paper. It is suggested that the simplest of linking between a tree and ensemble can explain neural binding and variable signal strengths.

Microsoft today announced several improvements to its pre-built AI tools for companies, with a focus on improving facial recognition, custom image classification, and understanding important entities. The updates are included in the company's suite of Cognitive Services -- APIs that help developers deliver intelligent capabilities even if they don't have a great deal of AI expertise. The three updated services -- Microsoft's Custom Vision Service, Face API, and Bing Entity Search -- are designed to make AI easier for companies that can't keep a professional data scientist on staff. That's important, given the limited number of AI experts currently available, how much they cost to hire, and how complicated the task of rolling your own AI capabilities can be. The Custom Vision Service is now in paid public beta.

There are already lots of great articles covering these topics (for example here or here). And this isn't a discussion about whether AI will enslave humankind or merely steal all our jobs. You can find plenty of speculation and some premature fearmongering elsewhere. Instead, this post is a detailed description of how to get started in Machine Learning by building a system that is (somewhat) able to recognize what it sees in an image. I'm currently on a journey to learn about Artificial Intelligence and Machine Learning.

Since 9/11, border patrol agencies around the world have focused on improving their abilities to quickly assess threats from passengers and cargo entering the country. Based on its work with several countries on border protection, Unisys developed the LineSight software, which uses advanced analytics that assesses risk in near real time. Rather than relying solely on pattern recognition based on historical data, LineSight assesses risk from the initial intent to travel and refines that assessment as current information becomes available -- beginning with a traveler's visa application, reservation, ticket purchase, seat selection, check-in and arrival, the company said. The software provides similar risk assessments for cargo shipments based on manifest forms, customs declaration or airline bills. If border agencies rely on patterns to spot border threats, "smugglers and terrorists become smarter on how to avoid those patterns," Mark Forman, global head of Unisys Public Sector, said.

These are all related, yet distinct, concepts that have been used for a very long time to describe an aspect of data mining that many would argue is the very essence of the term data mining: taking a set of data and applying statistical methods to find interesting and previously-unknown patterns within said set of data. We aren't looking to classify instances or perform instance clustering; we simply want to learn patterns of subsets which emerge within a dataset and across instances, which ones emerge frequently, which items are associated, and which items correlate with others. It's easy to see why the above terms become conflated. So, let's have a look at this essential aspect of data mining. Foregoing the Apriori algorithm for now, I will simply use the term frequent pattern mining to refer to the big tent of concepts outlined above, even if somewhat flawed (and even if I personally prefer the less often used term association mining).

A while back, I was reading an article posted on Facebook, about Clovis people found alive and well living in Florida, with a picture featuring tribesmen (see below.) The quality of the picture was poor, and the URL was very suspicious: baynews9.com.ddwg.clonezone.link, as to make it appear that it was from Baynews9.com. It turned out that the picture (and thus the whole story) was fake: these people are real people living in Peru, see here for a Youtube video about them. My question is how to detect that a story is fake? The picture might have metadata embedded in it, allowing the data scientist to find the real source, unless it is a screenshot.