foveola logo
[ home ]
[ info ]
[ news ]
[ contact ]
foveola faqs

This page should help to answer your questions about Foveola. It's divided into three sections:

  • General FAQ: About the Foveola technology and its potential applications.

  • Business FAQ: About who we are and doing business with us.

  • Technical FAQ: About the underlying Foveola algorithms and implementation.

You can also find some general information about Foveola in this background summary.
general faq

1.1   "What's so special about the Foveola shape recognition technology?"

Foveola can deal with shape-related visual tasks in a similar way to humans. It is therefore like having simulated human eyes interrogating digital images at enormous speed.

Teaching the system to see new shapes is simple, transparent and fast. Shapes can be represented in a single database which allows Foveola to "get" the visual analogy between an 'm' and a flying seagull, or an 'L' and a gumboot.

The actual Foveola engine is implemented as an ANSI C library, making it both fast and easily portable across hardware platforms and operating systems.
 

1.2  "I get the impression that Foveola is just another system for Optical Character Recognition. OCR is already a mature technology, so why do I need Foveola?"

Foveola isn't simply an OCR technology - it's a general-purpose shape recognition engine. It can be used to recognise all shapes, from road signs to engineering components.
 

1.3  "Is Foveola an end-user application?"

No, it's a tool which can be built into an existing application or embedded in your hardware device.
 

1.4  "What applications areas is Foveola useful for?"

We are seeing particular interest in mobile applications such as handwriting recognition, general image recognition software such as multimedia search tools, and hardware-based deployments such as interactive toys.

We expect Foveola to have valuable applications in smart, face-sensitive cameras and other security systems. Foveola is intended as a general shape recogniser, so we can even envisage providing visually-impaired people with some measure of shape recognition ability (via a different sensory modality such as hearing).
 

1.5  "Foveola is a so-called "neuromorphic" technology. How is it different from ordinary Neural Networks?"

Foveola is modelled on certain aspects of the behaviour of cells in the visual cortex of higher mammals, and its advantages over traditional Neural Networks are considerable.

Foveola doesn't include interconnected layers of neurons with "weights" which require adjustment by an opaque learning process involving many training examples.

Instead, only a single training example is required for each input shape variant that the system is required to recognise. Additionally, the system's current knowledge is unaffected by the addition of new shapes; there is no danger of "overtraining".
 

1.6  "You talk about Foveola being modelled on how humans see, but when I see the world, I don't view it through some tiny window."

Actually, to some extent you do! You can only really see full detail in an area which is about the same as that of a fingernail held at arm's length - the "foveolar window". (This means, incidentally, that you can identify the face of a friend at about 30m away; at 60m you can at least tell that it's a face and whether it's smiling or not).

In your visual field, the sharpness with which things can be seen falls off rapidly with increasing radial distance from the foveolar window.

For example, when you view a school photograph you can't spot a particular child immediately, using only your peripheral vision. You have to scan for that child by examining each face, one by one. When looking at any given child, you can't even be sure whether the neighbouring child (viewed in peripheral vision only) is the one you're looking for.

business faq

2.1  "Is Foveola a company? Who are you exactly?"

Foveola is one of a small portfolio of innovative technologies which are available for license through break-step productions, a privately-held company based in Cambridge, UK.
 

2.2  "Are you chasing venture capital?"

No, we fund our own developments by making sales.
 

2.3  "I'd like to talk. What are your contact details?"

You can contact us using our online form, or by post, phone or email:

break-step productions limited
Hawkshaw Cottage
Gordon Road
Crieff PH7 4BL, UK

Phone +44 (0)1764 652 602
Email sales@foveola.com

technical faq

3.1  "My application doesn't need alphanumeric character recognition. Can I train Foveola to recognise other shapes?"

Foveola is distributed with a collection of sample databases, which include mainly alphanumeric shapes and simple icons. However, these databases can readily be extended or replaced for your own applications: Foveola is not just an OCR tool, it is a general shape recognition system.

Foveola only needs to see a given shape once to be able to recognise future examples of that shape, together with a range of variants of that shape. "Training" Foveola is therefore just a matter of adding the shapes you wish to recognise to your own database of shapes, using the GUI-based or command-line tools supplied with all editions of the Foveola software.
 

3.2  "What underlying technologies does Foveola rely on?"

The actual Foveola engine is implemented as an ANSI C library with a simple API, to maximise both its speed and its cross-platform portability.

There is no dependence on any particular database or platform for storing shape codes when training the Foveola engine. The actual classification engine can be used as a stand-alone tool, or incorporated into your own application, and integrated with a database of your choice.
 

3.3  "What about hardware implementations?"

The Foveola engine is modelled on neurophysiology at both high and low levels, with the underlying algorithm being implemented as a sequential set of relatively simple, multi-cellular operations. This construction makes it very suitable for on-chip hardware implementations.
 

3.4  "How does Foveola cope with real photographs, rather than simple drawings?"

Foveola works on thresholded (black and white) images; real photographs are therefore thresholded before processing. This is surprisingly like the way that people see shapes, and helps Foveola to be robust to the visual imperfections (noise, shadows etc) which can affect photographic images.
 

3.5  "How does Foveola deal with segmenting a poorly-lit scene?"

Lighting variability is dealt with by looking at only a small area of the scene in detail at any time. At no point is an attempt made to segment the whole scene. A higher-level application (such as SceneReader) can perform global image analysis, and pass shapes of interest to Foveola for processing.
 

3.6  "What about 'invariances'"?

Foveola exhibits some size invariance. Rotational invariance is deliberately avoided: since the shapes X and + actually look different, it makes no sense to arrange for the system to conflate them.