Customs & Border Management

Visual Recognition Made Simple

“A picture paints a thousand words”

but only if you know how to read it . . 

Visual Recognition does for huge numbers of images what text analytics does for large collections of written text: it allows pictures to be processed automatically to find material of interest. This can provide the basis for open source intelligence or provide a means to process collected images to automatically find specified targets, such as military infrastructure.

The number of images from public sources, soldiers with (body) cameras, coalition partners and other sources is exploding. Clearly achieving timely, accurate classification of the images by “throwing people at the problem” does not scale and can be error prone.

Cognitive computing – in the form of unsupervised (machine) learning – will transform our ability to classify images.

Let’s consider recognising a military aircraft in an image using the Watson Visual Recognition (web) service. The service uses semantic classifiers built with machine-learning technology to recognize visual entities such as settings, objects, and events based on content such as color, texture, shape, and edges. Watson Visual Recognition allows us to build a classifier specific to our problem (“spot a military aircraft”) by learning from images we provide.

VizRec 1

Figure 1 – Watson Visual Recognition Service (in IBM BlueMix)

To train the new classifier, we provide a set of positive (correct) and negative (incorrect) images as training sets, as shown in Figure 2. Careful examination of the negative images shows a combination of civil aircraft and birds.

VizReq 2

Figure 2 – Training Sets: Positive & Negative

Once the classifier is trained, we can ask it to “recognize” images for us. Sample actual results are shown in Figure 3, but if the classifier misbehaves or the confidence is not high enough it can be re-trained with more complete and/ or comprehensive image libraries.


Figure 3 – Classification Results

For a real life problem, several classifiers would be built and applied to the same image, resulting in competing “image type” results with associated confidences. System accuracy could improve over time if the training sets are augmented with correct and incorrect classifications and the classifiers periodically re-trained.

Want to see this Watson Visual Recognition in action? We will be demonstrating it at or SPADE customer conference [3] in Berlin on the 12th & 13th April. Alternatively take a look at our BlueMix cloud integration platform.

References & Credits

  1. I’m grateful to my close colleague & friend Dr Doug Dykeman (@doug_dykeman) for showing me just how easy this can be!
  2. For insights into the underlying technology “Unsupervised One-Class Learning for Automatic Outlier Removal”
    by John Smith et al
  3. If you are interested in attending our SPADE conference, please contact your local IBM account representative – or me if you don’t have one!

Agree, disagree, disinterested?  I’d much appreciate an active debate on this topic!  Contact me through leaving a comment, twitter or LinkedIn!

Add Comment
No Comments

Leave a Reply

Your email address will not be published.Required fields are marked *

More Customs & Border Management Stories

Overcoming military cloud BLOCKAGES

In my previous post – Cloud for the Military? – I described how cloud computing could help overcome the challenge of increasing mission complexity & agility in a climate of aggressive budget reductions.  I concluded that the military don’t really have a choice and it’s really a question of what kind of Cloud is going to be deployed when rather than *if*. […]

Continue reading

Keeping an Eye on the Fundamental Objectives

Deliver better outcomes or lower costs.  At the end of the day, those two criteria should be the basis for ANY technology investments.  As federal agencies look to adopt cloud computing, it is important to keep the fundamental objectives of better outcomes and lower costs at the center of the conversation. What decades of experience […]

Continue reading

Brain-inspired Computing for Defence

Breaking away from traditional sequential processing architectures, brain inspired computing mimics how the human brain is constructed, resulting in a massively parallel yet very low power consumption chip. NeuroSynaptic processors take a radical new approach to military challenges including image recognition, machine vision, multi sensor fusion and signal processing.

Continue reading