GB2419760A

GB2419760A - Image capture system with alignment and character recognition means

Info

Publication number: GB2419760A
Application number: GB0424191A
Authority: GB
Inventors: Lawson John Noble; Frank James Thomson; Nico Bekooy
Original assignee: Citysync Ltd
Current assignee: Tagmaster UK Ltd
Priority date: 2004-11-01
Filing date: 2004-11-01
Publication date: 2006-05-03
Also published as: GB0424191D0

Abstract

An image capture system (1, fig. 1) comprises a light source (5, fig. 1) preferably a narrow focused laser, operable to project a designator 12 onto a surface, capture means (6, fig. 1) being aligned with the designator 12, the surface projected onto being included in images captured, and an image processor operable to identify characters on the surface. Preferably the image processor defines a rectangular boundary shape surrounding the designator within which characters are to be identified in a captured image. The shape has two or more positions of the designator 12 as reference points, which comprise corners of the rectangle. Preferably the system has a switch (8, fig. 1) having designator and capture positions, and a secondary light (7, fig. 1) source for illuminating an object which can be activated and deactivated when the switch (7, fig. 1) is in the capture position. The processor may be located remotely from the capture means (6, fig. 1). A method is also independently claimed, the steps of which may be used as a computer program.

Description

PATENTS ACT 1977 "An Image Capture System" THIS INVENTION relates to an

image capture system, and in particular relates to a device that enables a user to capture information displayed on a vehicle registration plate in a quick and simple manner.

It is often desirable to be able to record information displayed on a vehicle registration plate. For instance, the alphanumeric information displayed on a vehicle registration plate may allow a member of the traffic police or traffic warden to identify a vehicle, as well as discover other relevant information such as the identity of the owner of the vehicle, or whether the vehicle is on a list of stolen vehicles.

In recent years, it has been desirable to record registration plate details electronically, so that the details may be transmitted for storage, for comparison against a data base of registration plates of stolen vehicles, and so on. It is known to provide a device with a keypad to allow a user to input registration details manually for storage or transmission, but this approach suffers from drawbacks in that the manual inputting of registration plate details is a slow and laborious task. In addition, the device must be sufficiently large to accommodate an alphanumeric keyboard which is rugged enough for outdoor use, and clearly this places an undesirable constraint on the size of the device.

More recently, it is now known to provide personnel such as traffic police and traffic wardens with hand-held devices which are operable to capture an image (using a CCD or similar image capture device), recognise the alphanumerics on a registration plate within the image, and automatically identify the characters on the registration plate.

Conventionally, these devices are provided with a screen, representing the current field of view of the CCD. The user of the device positions the device so that the image displayed on the screen contains the registration plate of a vehicle of interest, and operates a button or other control to "capture" the image displayed on the screen.

Image processing software within the device then analyses the image to identify objects therein that are likely to comprise vehicle registration plates.

Typically, the image processing software identifies objects within the captured image, searching for rectangles of suitable dimensions that are likely to be the registration plate. Once the registration plate has been identified, characters within the registration plate are analysed and identified.

This approach suffers from several drawbacks. Firstly, it is awkward and time consuming to position the device, whilst observing the screen, to ensure that the registration of the vehicle in question is displayed on the screen.

In addition, performing the above-described image processing on the captured image requires a relatively large amount of processing power, since the entire image must be analysed in an attempt to identify the registration plate therein.

It is an object of the present invention to alleviate some of all of the above disadvantages.

Accordingly, one aspect of the present invention provides an image capture system, comprising: a light source operable to project a designator onto a surface; an image capturer aligned with the light source to capture, in use, an image including the surface onto which the designator is projected; and an image processor operable to identif' characters on the surface onto which the designator is projected..

Advantageously, the light source comprises a laser.

Preferably, the light source projects a narrow, focused beam of light.

Conveniently, a defined portion of the image has a boundary which surrounds the designator.

Advantageously, the image processor defines the portion of the image by recognising the boundary around the designator.

Alternatively, the image processor is operable to track movements of the designator with respect to the surface, the image processor defining the portion of the image within which the characters are to be identified as a shape within the image, the shape having two or more positions of the designator as reference points thereof.

Preferably, the shape is substantially a rectangle, the two or more positions of the designator comprising corners of the rectangle.

Conveniently, characters are identified only within the defined portion of the image.

Advantageously, the system further comprises a switch having a designator position and a capture position, the light source being activated when the switch is in the designator position and the image capturer being activated when the switch is in the capture position.

Preferably, the system further comprises a secondary light source for illuminating an object.

Conveniently, the secondary light source is activated when the switch is in the capture position.

Advantageously, the image processor is located remotely from the image capturer.

Another aspect of the present invention provides a method of capturing and processing an image, the method comprising the steps of: projecting a designator onto a surface; capturing an image including the designator; using the designator to define a portion of the image; and identifying characters within the defined portion.

Preferably, the step of defining the portion of the image comprises the step of defining a portion of the image surrounding the designator.

Conveniently, the step of defining the portion of the image comprises the step of recognising a boundary around the designator.

Advantageously, the method further comprises the step of tracking movements of the designator with respect to the surface, and wherein the step of defining the portion of the image comprises defining the portion of the image as a shape within the image, the shape having two or more positions of the designator as reference points thereof.

Preferably, characters are identified only within the defined portion of the image.

Conveniently, the step of identifying characters within the defined portion is carried out remotely from the step of capturing the image.

A further aspect of the present invention provides an image processing method comprising the steps of: receiving an image comprising a field of view aligned with a designator light beam; using the designator to define a portion of the image; and identifying characters only within the defined portion.

Advantageously, the designator light beam is deactivated upon activating an image capture device to capture the image.

Another aspect of the present invention provides a computer program comprising computer program code means adapted to perform all of the steps of the above when the program is run on a computer.

A further aspect of the present invention provides a computer program according to the above, embodied on a computer readable medium.

In order that the present invention may be more readily understood, embodiments will now be described, by way of example, with reference to the accompanying drawings in which: Figure 1 shows a device embodying the present invention; and Figure 2 shows an image that might be captured by the device of Figure 1.

With reference firstly to Figure 1, a device 1 embodying the present invention is shown. The device 1 comprises a substantially oblong body 2, with a handle 3 depending therefrom. The handle 3 is dimensioned to be received comfortably in the hand of a user, and the arrangement of the body 2 and handle 3 allows the device 1 to be handled in a similar manner to a conventional pistol.

On a pointing end 4 thereof, the body is provided with a light source 5.

The pointing end 4 of the body 2 preferably comprises a portion of the body 2 which, when the device 1 is handled in the manner of a conventional pistol, is intuitively pointed forward by a user.

In advantageous embodiments of the invention, the light source 5 comprises a laser or an alternative source of a narrow, focused beam of light.

Preferably, the light source projects light within the visible spectrum.

The pointing end 4 of the body is further provided with an image capture device 6, which preferably comprises a CCD camera. The light source 5 and the image capture device 6 are arranged so that, when the device 1 is pointed at a surface, the beam of light projected by the light source 5 falls onto the surface and creates a spot or other shaped designator within the field of view of the image capture device 6. This is to say that the designator beam is co-aligned with the view of the image capture device 6.

In preferred embodiments of the invention, the device 1 further comprises a secondary light source 7, and advantageously the secondary light source 7 comprises a bank of LEDs. The secondary light source is selected so that light emitted thereby illuminates and is reflected strongly by a conventional vehicle registration plate. The light emitted by the secondary light source may fall at least partially within the infrared portion of the spectrum.

The handle 3 of the device 1 is provided with a trigger 8, which is arranged so that, when a user of the device 1 grips the handle 3, the user's forefinger rest on the trigger 8 and may easily depress the trigger 8.

The trigger 8 may preferably be placed in three positions. In the first of these positions, a rest position, the device 1 is turned off. In a second position, a designator position, the light source 5 is activated, but the secondary light source 7 and the image capture device 6 are switched off. In a third position, a capture position, the light source 5, the secondary light source 7 and the image capture device 6 are all activated.

The body 2 of the device 1 is provided, on an upper surface thereof that may be seen by the user during use of the device 1, with a display 9. The display 9 may be located at the rear of the device as shown in Figure 1 by reference numeral 9' as an alternative to the location on the upper surface.

The device 1 is preferably provided with a processor and associated circuitry, and may further comprise a transmitter or transceiver to communicate information between the device 1 and other systems.

Use of the device I will now be described. A user of the device 1 wishing to record the details displayed on a vehicle registration plate firstly moves the trigger 8 from the rest position thereof to the designator position, activating the light source 5 only. As described above, the light source 5 projects a focused beam of light, creating a visible designation spot where a surface is illuminated by the light source 5. The user manoeuvres or aims the device 1 so that the light source 5 projects the designation spot of light on to the vehicle registration plate itself.

Once the user has ensured that the designator beam projected by the light source 5 falls on the registration plate, the user moves the trigger 8 from the designator position thereof to the capture position, activating the secondary light source 7 and the image capture device 6 to capture the image including the item designated by the designator beam. Thus, the captured image comprises, as shown in Figure 2, all or part of a vehicle 10, including the registration plate 11 designated by the spot of light 12 projected by the light source 5 which falls upon the registration plate 11 on the image. The image shown in Figure 2 is a relatively wide field of view. If the designator beam and image capture device 6 are accurately aligned, a narrower field of view is made possible thereby excluding extraneous material from the image which then contains essentially just the item, in this case the registration plate, which the light beam 5 designates as the "target" image.

Whilst in a preferred embodiment the light source 5 is activated when the trigger 8 is in the capture position, it is also envisaged that the light source 5, projecting a spot of light 12, may be switched off when the trigger 8 moves to the capture position. Therefore, the image captured by the image capture device 6 will not include the spot of light 12 projected by the light source 5 However, as previously discussed, the light source 5 projects a designator beam which is co-aligned with the view of the image capture device 6. Therefore, should an image be captured with the light source 5 being turned off it will be appreciated that the centre of the image will fall within the bounds of the registration plate 11.

In preferred embodiments of the invention, image processing software employed by the device I determines where the registration plate 11 is within the image by searching for a rectangular boundary which surrounds the spot of light 12. This may be done by working outwards from the spot of light 12 until a region of a different colour from the surface upon which the spot of light 12 appears is found. The portion of the image within this boundary is then determined to be the registration plate, and character recognition is then applied only within this defined portion of the image.

Alternatively, should the light source 5 be turned off when the image is captured, the image processing software would work outwards from the centre of the image, since the centre of the image is known to be within the bounds of the registration plate.

It will be appreciated that this method of determining where in the image the registration plate 11 lies confers significant advantages over previous methods. For instance, there is no need for the image processing software to perform processing on any part of the image other than that which is designated by the light beam and subsequently determined to be the registration plate 11.

Secondly, there is no need for the image processing software to identify objects within the image, and attempt to determine which of the objects is the registration plate 11. The possibility of the image processing software incorrectly identifying an object as the registration plate 11 is also eliminated.

As can be seen from Figure 2, the rear bumper 13 of the vehicle, lamps 14 within the rear lamp clusters 15, a badge 16 displaying the make or model of the vehicle or a sticker 17 informing other road users of the nationality of the owner of the vehicle may all appear substantially rectangular in shape within the image and could possibly cause the image processing software to make an incorrect determination as to the location of the registration plate 11.

It will be clear form the above that the processing power required to read the details on the registration plate 11 contained in an image is reduced by the method and device of the present invention.

The display 9 on the body 2 of the device may display a captured image, the details displayed on the registration plate as determined by the image processing software, or a combination of the two.

In alternative embodiment of the invention, the device 1 may be able to track movements of the spot of light 12 with respect to objects in the field of view of the image capture device 6. This may be achieved by recognising objects in the image and determining how the spot of light 12 has moved between the capturing of one image and the next. Alternatively, the device 1 may be provided with one or more gyroscopic devices, accelerometers or the like (not shown) which are operable to measure the physical movement of the device 1, and hence determine how the device 1 has moved in the time between capturing an image and the capturing of a subsequent image.

In these embodiments, the portion of an image which comprises a registration plate may be defined by pointing the beam of light projected by the light source 5 at the registration plate and registering this beam of light in two or more locations to define a shape within the image that comprises the registration plate.

For instance, a user of the device may point the designator beam at the top right-hand corner of a vehicle registration plate, and press a button to register this location. The user may then point the designator beam at the bottom left-hand corner of the registration plate, and press a button to register this second location. The image processing software will then determine that the registration plate falls, in the image, within a rectangle having the top right- hand corner thereof at the first registered location and the bottom left- hand corner at the second registered location, and perform image processing only within this region.

In embodiments of the invention, images captured by the device 1 may be transmitted by the transmitter or transceiver to a remote location for processing, rather than being processed in situ. The present invention also provides a method of image processing to process such images, which will contain a spot of light as projected by the light source 5.

It is envisaged that the present invention will find application outside the field of registration plate identification. For instance, it is common for cargo containers to display a plate or other label on which a code identifying the cargo or the container itself is shown. A person wishing to perform an audit of the cargo on a vessel or at a dock may capture the plates on many cargo containers quickly and simply using a device embodying the present invention, and the information read by the device may be transmitted to a remote location for storage in the database andlor comparison with a list of the expected cargo in the location in question.

In the above embodiments, the image processing required to recognise characters within an image captured by the device 1 is carried out within the device 1 itself In embodiments of the invention, however, images are simply captured by the device 1, and are subsequently transmitted to one or more remote devices or systems for processing of the image to take place. It is envisaged that only a selected portion of the image, for instance a region of the image determined to include a registration plate, may be transmitted.

Alternatively, some preliminary image processing may be carried out by the device 1, with the remainder of the image processing being performed remotely.

It will be appreciated that the present invention provides a device and method which will allow a user to read a large number of registration plates and the like quickly and easily.

In the present specification "comprises" means "includes or consists of' and "comprising" means "including or consisting of'.

The features disclosed in the foregoing description, or the following claims, or the accompanying drawings, expressed in their specific forms or in terms of a means for performing the disclosed function, or a method or process for attaining the disclosed result, as appropriate, may, separately, or in any combination of such features, be utilised for realising the invention in diverse forms thereof.

Claims

CLAIMS: 1. An image capture system, comprising: a light source operable to

project a designator onto a surface; an image capturer aligned with the light source to capture, in use, an image including the surface onto which the designator is projected; and an image processor operable to identif' characters on the surface onto which the designator is projected.
2. A system according to Claim 1, wherein the light source comprises a laser.
3. A system according to Claim 1 or 2, wherein the light source projects a narrow, focused beam of light.
4. A system according to any preceding claim, wherein a defined portion of the image has a boundary which surrounds the designator.
5. A system according to Claim 4, wherein the image processor defines the portion of the image by recognising the boundary around the designator.
6. A system according to any one of Claims 1 to 3, wherein the image processor is operable to track movements of the designator with respect to the surface, the image processor defining the portion of the image within which the characters are to be identified as a shape within the image, the shape having two or more positions of the designator as reference points thereof.
7. A system according to Claim 6, wherein the shape is substantially a rectangle, the two or more positions of the designator comprising corners of the rectangle.
8. A system according to any one of Claims 4 to 7, wherein characters are identified only within the defined portion of the image.
9. A system according to any preceding claim, further comprising a switch having a designator position and a capture position, the light source being activated when the switch is in the designator position and the image capturer being activated when the switch is in the capture position.
10. A system according to Claim 9, further comprising a secondary light source for illuminating an object.
11. A system according to Claim 10, wherein the secondary light source is activated when the switch is in the capture position.
12. A system according to any one of Claims 9 to 11, wherein the light source is deactivated when the switch is in the capture position.
13. A system according to any preceding claim, wherein the image processor is located remotely from the image capturer.
14. A method of capturing and processing an image, the method comprising the steps of: projecting a designator onto a surface; capturing an image including the designator; using the designator to define a portion of the image; and identifying characters within the defined portion.
15. A method according to Claim 14, wherein the step of defining the portion of the image comprises the step of defining a portion of the image surrounding the designator.
16. A method according to Claim 15, wherein the step of defining the portion of the image comprises the step of recognising a boundary around the designator.
17. A method according to Claim 14, further comprising the step of tracking movements of the designator with respect to the surface, and wherein the step of defining the portion of the image comprises defining the portion of the image as a shape within the image, the shape having two or more positions of the designator as reference points thereof.
18. A method according to any one of Claims 15 to 17, wherein characters are identified only within the defined portion of the image.
19. A method according to any one of Claims 14 to 18, wherein the step of identifying characters within the defined portion is carried out remotely from the step of capturing the image.
20. An image processing method comprising the steps of: receiving an image comprising a field of view aligned with a designator light beam; using the designator to define a portion of the image; and identifying characters only within the defined portion.
21. A method according to Claim 20, wherein the designator light beam is deactivated upon activating an image capture device to capture the image.
22. A computer program comprising computer program code means adapted to perform all of the steps of Claim 20 or 21 when the program is run on a computer.
23. A computer program according to Claim 22, embodied on a computer readable medium.
24. A device substantially as hereinbefore described, with reference to the accompanying drawings.
25. A method substantially as hereinbefore described, with reference to the accompanying drawings.
26. A computer program substantially as hereinbefore described, with reference to the accompanying drawings.
27. Any novel feature or combination of features disclosed herein.