Colour system

Abstract

A colour system (1) for generating a colour harmony based directly from the skin colour of a user, the system comprising a region selector (7) which is configured to select a region of the face of the user in a digital image of the face of the user; a colour identifier (15) coupled to the region selector (7), the colour identifier (15) being configured to identify a key colour by calculating an average colour across at least a part of the region of the face of the user in the digital image and to store data indicative of the key colour in a memory, the key colour being the skin colour of the user; an opponent colour generator (16) coupled to the colour identifier (15), the opponent colour generator (16) being configured to receive the data indicative of the key colour data from the colour identifier (15) and to generate the opponent colour of the key colour using the key colour data; and a screen (4) configured to display the skin colour and the opponent colour of the skin colour to provide a colour harmony to the user based directly from the skin colour of the user that is visually correct such that the colour harmony is arresting and has an impact on the user.

Description

[0001] COLOUR SYSTEM

[0002] FIELD OF INVENTION

[0003] The present invention relates to a colour system and method for generating a colour harmony that is visually correct such that the colour harmony is arresting and has an impact on a user. The present invention more particularly relates to a colour system and method for generating a colour harmony based directly from the skin colour of a user. The present invention also relates to a system and method for generating a colour harmony using a predetermined colour and its relative luminosity and using the opponent colour of the predetermined colour and the opponent colour’s relative luminosity to generate colour palettes that are uniquely related to the predetermined colour.

[0004] BACKGROUND

[0005] Personal colour analysis is a multi-million-pound business which traditionally involves a consultation with a colour consultant. Coloured drapes are placed against the subject’s face and based on the subjective view of the colour consultant in relation to whether the subject is warm / cool or blue / yellow in skin colour, one of a small number of seasonal fixed palettes are recommended. For example, the subject is assigned a Spring, Summer, Autumn or Winter palette.

[0006] The biology and limitations of the human eye / optic system and the ever-changing ambient light make it impossible for the colour consultant to accurately gauge the natural colouring of the subject; in one light a person appears one shade (warm) and, in another light, the same person appears a different shade (cool). Recommending a single fixed palette based on a subjective view that is liable to change with the changing light is fundamentally flawed.

[0007] Computer-based colour systems have been proposed which attempt to render colour accurately and generate colour harmonies. However, these computer-based colour systems still suffer from the same problems as a conventional personal colour analysis process described above. For example, existing computer-based colour systems still recommend predetermined fixed palettes without taking into account the fact that the palette is liable to change depending on the ambient light.

[0008] A further problem with conventional computer-based colour systems is that such systems are often incapable of capturing the colour of an object accurately. For example, many computer-based colour systems are incapable of rendering the skin colour of a person accurately under differing light conditions. Aside from personal colour analysis, there are other applications that require colour harmonies that are impactful on a user. For example, impactful colour harmonies ensure that signage is noticeable, which is critically important in the case of warning signage where safety of a user may be compromised if the user does not take notice of a warning displayed or written in colour.

[0009] Another application where impactful colour harmonies are beneficial is for partially sighted users since a partially sighted user is likely to find text written on a background in an impactful colour combination easier to read than text written in a less distinctive colour.

[0010] There is a need for an improved colour system and method which alleviates the problems outlined above.

[0011] BRIEF DESCRIPTION OF THE INVENTION

[0012] The present invention provides a system as claimed in claims 1 and 2, a method as claimed in claims 15 and 16 and a computer readable storage medium as claimed in claim 25. The present invention also provides preferred embodiments as claimed in the dependent claims.

[0013] BRIEF DESCRIPTION OF THE FIGURES

[0014] In orderthatthe present disclosure may be more readily understood, preferable embodiments thereof will now be described, by way of example only, with reference to the accompanying drawings, in which:

[0015] Figure 1 is a schematic diagram of a colour system of examples of this disclosure,

[0016] Figure 2 is a schematic diagram of part of the colour system of Figure 1 ,

[0017] Figure 3 is a diagram showing feature points on a face of a user,

[0018] Figure 4 is a diagram showing a region of the face of the user show in Figure 3,

[0019] Figure 5 is a diagrammatic view of the display of a colour system of some examples showing a monochromatic colour harmony,

[0020] Figure 6 is a diagrammatic view of the display of a colour system of some examples showing a complementary colour harmony,

[0021] Figure 7 is a diagrammatic view of the display of a colour system of some examples showing a compound colour harmony,

[0022] Figure 8 is a diagrammatic view of the display of a colour system of some examples showing another compound colour harmony, and

[0023] Figure 9 is a diagrammatic view of the display of a colour system of some examples showing an analogous colour harmony. DETAILED DESCRIPTION OF THE DISCLOSURE

[0024] Colour harmony

[0025] All colours within a colour harmony must relate to remain arresting and impactful to our senses. Many different industries including, but not limited to, computer graphics, paintings, interior design, fabrics or fashion all rely on each colour within a palette when colours are set side by side to create colour harmonies that are impactful and arresting to the biology of the human optic system.

[0026] The opponent process

[0027] The opponent process is immutable and reflects the biological workings of the human optic system. Colour harmonies have a direct relationship to our three colour receptors and our luminosity receptors. Black is the complimentary (complementary = equal and opposite) of white and white is the complimentary of black, that is the black has no white in it and white has no black in it, so when side by side black and white create the strongest contrast in the human optic system. The same is true for when all other colours are shown side by side with their complementary colour. This process also works for soft muted colours; however they relate, in precisely the same way within the opponent process.

[0028] What is less obvious to the human optic system is that blue is the complimentary of yellow and red is the complimentary of cyan. In blue there is no yellow and in yellow there is no blue; in red there is no cyan and in cyan there is no red, and so on. Every one of more than 10 million subtle and vivid colours the human eye can attenuate has its opponent (complementary) colour.

[0029] Due to the limitations of the human optic system inherently we cannot trust our eyes when it comes to colour vision. Consequently, we cannot trust the choices we make when putting colours together to create what we feel will be an interesting impactful colour harmony.

[0030] Although we cannot trust our eyes, we do respond emotionally to colour harmonies whether we understand if the colour harmonies are working well together or not. The systems and methods of examples of this disclosure seek to solve this problem by providing a technical solution that is implemented using a computing device based on the immutable opponent process and the scientifically correct (RGB) colour wheel. The relationship between the opponent process and the colour wheel (RGB)

[0031] Correct colour harmonies that are based on the application of the opponent process to a scientific colour wheel (RGB) are impactful and arresting to the viewer. By contrast, wrong colour harmonies create an entirely different and often negative effect on a viewer.

[0032] The inventors noted that in a convention a colour circle that is in use globally, purple is shown incorrectly as the opposite of yellow. This conventional colour circle was created as a visual representation of the first observations of the linear electromagnetic field. Although an attractive representation, a conventional colour circle has no scientific relevance to how colours relate therefore a conventional colour circle cannot be used to discover true relationships between colours. If a conventional colour circle is used to determine complementary colours, then the result is incorrect since the result does not reflect the human optic system. As a result, the negative impact on the world of colour cannot be underestimated.

[0033] For example, the commonly used purple opposite yellow colour circle causes clashes in the human optic system including greying out. This produces terrible results when used, for example, within interior design, filmmaking, colour and style analysis, art and anything where colour is of importance to the user or viewer.

[0034] Technological solution

[0035] As described below, by taking the key colour in a colour harmony, (in the example below the digital image is of a human face, but it could well be product packaging or a piece of fabric or paint for interior design, etc.) and taking a selection of Red, Green and Blue (RGB) readings from a predetermined area of the digital image to record the RGB values within that area which become mixed together a new accurate colour is generated based on the average colour readings within that area. As a result, a key colour is produced from which to create sets of accurate, useful harmonies which consist of colours at the same luminosity as the key colour and other colours at the luminosity of the key colour’s opponent luminosity. As further described below, the process also identifies the relative luminosity of that area which can be used to generate low, medium and high contrast moods with the colour palettes.

[0036] The new colour reading is then converted into the LAB colour space. LAB is the most accurate colour space within which to measure the various colour photons or pigments. LAB also represents the workings of the human optic system in that it uses the three values of L, a, and b channels to specify the precise amount of each colour in the mix of any colour we create in either the additive or subtractive colour modes. Additive being produced from light, subtractive being produced with pigments. The LAB colour space allows the systems and methods of examples of this disclosure not only to view the changes in numerical values but allow the mathematical validity of calculations to be checked for precise adjustments.

[0037] Referring now to Figure 1 of the accompanying drawings, a colour system 1 of an example of this disclosure comprises a computing device 2 and an optional camera 3 which is coupled to or integrated within the computing device 2.

[0038] The computing device 2 comprises a screen 4 which, in this example, is a touchscreen. In this example, the computing device 2 is a smartphone but in other examples the computing device may be a different type of computing device. For example, the computing device 2 may be a tablet, laptop or other personal computing device. In other examples, the computing device is a server provided within a computer network or within the cloud.

[0039] Referring now to Figure 2 of the accompanying drawings, the computing device 2 comprises a processor 5 and a memory 6 that connected to one another. The memory 6 stores executable instructions which, when executed by the processor 5 perform functions of one or more functional modules within the colour system 1 .

[0040] The computing device 2 is configured to receive a digital image. In this example, the computing device 2 receives the digital image from the camera 3 once the camera 3 captures an image of an item or a person’s face. In other examples, the computing device 2 receives a digital image from a remote data source, such as another computing device or a server connected to the computing device over a computer network, such as the Internet.

[0041] In other examples, the digital image comprises a predetermined colour that is selected by a user. A user may select a predetermined colour from a series of colours and provide the selected colour to the computing device 2 in at least part of the digital image for processing by the computing device 2. The selection of the predetermined colour may be done via the screen 4 or by the user transmitting the digital image comprising the predetermined colour to the computing device 2.

[0042] The computing device 2 comprises a region selector 7 which is configured to select a region of the digital image. In some examples, the region selector 7 comprises a computer vision system which is configured, for instance using artificial neural networks, to recognise objects or shapes in the digital image. One example of a computer vision system that is suitable for use with the colour system 1 is based on the OpenCV computer vision library. In some examples, the computer vision system is configured to process the digital image and identify a three-dimensional surface shown in the digital image, and the region selector 7 is configured to select a region of the three-dimensional surface as the region of the digital image.

[0043] In some examples, the computer vision system is trained and configured to recognise a human face in the digital image. In these examples, the computer vision system may identify a three-dimensional surface of a human face. Referring to Figure 3 of the accompanying drawings, the computer system vision performs three-dimensional mapping of a face and allocates feature points 9 to features of the face 8.

[0044] Referring to Figure 4 of the accompanying drawings, the computer vision system is configured to recognise a plurality of feature points that define edges of a region of a cheek of the face. In this example, four feature points 10-13 are selected as corners of a region 14 of the cheek of the face 8. In other examples, the computer vision system is configured to recognise a plurality of feature points that define the edges of a different region of a face, such as a person’s eye. In further examples, the computer vision system is configured to recognise a different object and to select a region 14 that is appropriate for the object. The region 14 is the region of the digital image which is selected for processing as described in more detail below.

[0045] Referring again to Figure 2 of the accompanying drawings, the computing device 2 comprises a colour identifier 15 coupled to the region selector, in this example via the processor 5. The colour identifier 15 is configured to identify a key colour by calculating an average colour across at least a part of the region 14 of the digital image.

[0046] The colour identifier 15 is configured to sample a predetermined number of pixels from the selected region 14 of the digital image. The colour identifier 15 extracts or measures red (R), green (G) and blue (B) colour values in the RGB colour space for each pixel of the sampled pixels. In some examples, each colour value is an integer in the range 0 to 255.

[0047] In some examples, the colour identifier 15 is configured to measure 32-bit true colour giving 4,294,967,296 (approximately 4 billion) colour variations. In other examples, the colour identifier 15 is configured to measure colour at a deeper colour depth, for instance 64-bit or higher.

[0048] The colour identifier 15 is configured to identify a key colour by calculating an average value for each of the red (R), green (G) and blue (B) values across the sampled pixels. In this example, the colour identifier 15 calculates the average red (R), green (G) and blue (B) values separately by summing up the corresponding values from all the sampled pixels and dividing their sums by the total number of sampled pixels in the region 14. For example, if the region 14 contains 1000 sampled pixels, the summed-up red (R) values within the 1000 sampled pixels will be divided by 1000. The colour identifier 15 carries out this calculation for each of the red (R), green (G) and blue (B) values. The formula to calculate the average colour values across the sampled pixels is as follows:

[0049] Average R = (Sum of R values of sampled pixels) / (Number of sampled pixels), Average G = (Sum of G values of sampled pixels) I (Number of sampled pixels), and Average B = (Sum of B values of sampled pixels) I (Number of sampled pixels).

[0050] In some examples, the colour identifier 15 converts the average colour values to the following two- digit hexadecimal format:

[0051] Hex Code = "#" + (Average R in hexadecimal) + (Average G in hexadecimal) + (Average

[0052] B in hexadecimal)

[0053] As described above, the colour identifier 15 converts the average red (R), green (G) and blue (B) values into hexadecimal representation. The resulting values, typically between 0 and 1 , are then multiplied by 255 to bring the values back into the 0 to 255 range, but this time with fractional values. These fractional values are then rounded to the nearest whole number integer in the range 0-255. Finally, each of these whole number integers is converted into its corresponding two-digit hexadecimal representation.

[0054] Hexadecimal is a base-16 numbering system which uses the symbols 0-9 for values 0-9 and the letters A-F (or a-f) for values 10-15. If the number is less than 16 (10 in hexadecimal), it is padded with a leading zero to ensure it consists of two digits. For example, if the red (R) value is 180 out of a possible maximum value of 255, this fraction 180 / 255 = 1.41 , which is rounded to 1.

[0055] Again, for example, if the average red (R), green (G) and blue (B) values are 255, 128, and 64, respectively, the conversion to hexadecimal would result in a Hex Code of #FF8040 representing the key (average) colour across the region 14. In this representation, "FF" represents 255, "80" represents 128, and "40" represents 64.

[0056] The colour identifier 15 formats the three hexadecimal values (representing the average red (R), green (G) and blue (B) values) into a hex code in the format "#RRGGBB," where RR, GG, and BB are the two-digit hexadecimal values for red, green, and blue, respectively.

[0057] In the case of additive mode expression, when a digital device, such as a computer or smartphone, receives the hexadecimal code for a colour, it translates this code into instructions for displaying the colour on a screen. Each colour (channel) value determines the intensity of that colour component; the red channel value determines the intensity of the red light; the green channel value determines the intensity of the green light; and the blue channel value determines the intensity of the blue light. When a person views the screen, the combination of the three colour intensities (red, green, and blue) creates the perception of a specific colour. For instance, the code #FF0000 will cause the screen to emit only red light, resulting in the colour red as perceived by the eye.

[0058] In the case of additive mode expression, when the red, green, and blue primary colour values are combined in pairs, the combination produces secondary compound colours. For example, red and blue primaries from light produce magenta which is brighter than either the red or blue lights respectively. The secondary colours produced are cyan, magenta, and yellow and these, along with black and white, represent the primary colours of pigments and the subtractive mode. The hexadecimal code produced from plotting a colour in the RGB colour space as described above also defines the code / quantities of pigments within the cyan, magenta, yellow and black printing space to produce precise colours for all printed or coloured materials.

[0059] In some examples, the colour identifier 15 is configured to convert the key colour from the RGB colour space to the LAB (or CIELAB or L*a*b*) colour space and identify the luminance (L) of the key colour. In these examples, the system 1 stores a luminance value indicative of the luminance (L) in the memory 6.

[0060] In other examples, the colour identifier 15 is configured to convert the key colour from the RGB colour space to a different colour space and identify the luminance (L) of the key colour. For example, in some examples, the colour identifier 15 is configured to convert the key colour from the RGB colour space to the HSL (also known as HSV or HSB) colour space instead of the LAB colour space. The HSL colour space is, for instance, used when there is a need to change the luminosity of the colour without creating a colour shift in its hue or its saturation.

[0061] In some examples, the colour system is configured to assist a user in selecting or using colour according to hue and luminosity, and to assist a user in selecting or creating dynamic ranges of colours that suit different looks / moods. High key / dynamic looks involve the use of colours that are strongly opposing and colours that vary radically in luminosity; such looks omit an arresting energy. Low key looks lack this degree of dynamism and involve the use of colours that are similar in hue and luminosity creating a relaxed and sophisticated palette.

[0062] In some examples, the colour identifier 15 converts the key colour from the RGB colour space to the LAB colour space by performing the following processes:

[0063] 1 . RGB to XYZ: The RGB values represented in two-digit hexadecimal as described above are transformed into the CIE 1931 XYZ colour space. Each channel of the RGB colour is mapped to its corresponding X, Y, and Z values in the XYZ space.

[0064] 2. XYZ to LAB: From the XYZ colour space, the colour identifier 15 converts the values to the LAB colour space. In the LAB colour space: L (Lightness): L represents the perceived lightness / luminance of the colour. The lightness / luminance L is directly derived from the Y value in the XYZ space.

[0065] A (Green to Red): A represents the position on the green to red axis in the LAB colour space. A is calculated based on the X and Y values from the XYZ space.

[0066] B (Blue to Yellow): B represents the position on the blue to yellow axis in the LAB colour space. B is calculated based on the Y and Z values from the XYZ space.

[0067] 3. LAB Values: The colour identifier 15 assigns values to L, A, and B based on the RGB colour. These LAB values represent the colour in the LAB colour space. For example, #FF0000 in the RGB colour space is transformed to LAB values of L = 53.24, A = 80.09, and B = 67.20.

[0068] In the case where the region 14 of the digital image is a region of a person’s face, the above process may be followed to measure the key colour of the region and, directly from the key colour, the luminosity (L) value of the person’s skin colour. In this example, the luminosity (L) value is in a range of 0-100. For instance, a luminosity value of 76 could represent the skin colour of a person.

[0069] In some examples, the colour identifier 15 is configured to plot the key colour of a user’s skin colour on a scientific colour wheel resulting in seven classifications of skin colour groups. All users of the colour system 1 fall within these seven classifications of skin colour groups.

[0070] In some examples, the colour system 1 displays a series of faces representing a broad range of skin colours to a user and enables the user to select the face having the skin colour closest to the skin colour of the user. In these examples, the skin colour of each of the displayed faces is preferably plotted in both greyscale and colour to make it easier to discern the differentiation in colour across the face. When the user selects a face that resembles their skin colour, the colour system 1 anticipates that the resulting image will share the greyscale and colour values associated with the chosen face and adjust those elements of the user’s image which are either under or over exposed to correspond with those of the chosen image. This helps to optimise the colour system 1 by improving the accuracy of the colour system 1 in rendering the correct skin colour of the user.

[0071] In some examples, the colour system 1 displays a colour corrector / grey card to assist a user in seeing colours in their true hue in different lighting conditions.

[0072] Referring again to Figure 2 of the accompanying drawings, the computing device 2 comprises an opponent colour generator 16 coupled to the colour identifier 15, in this example via the processor 5. The opponent colour generator 16 is configured to receive key colour data from the colour identifier 15, the key colour data being indicative of the key colour identified by the colour identifier 15. The opponent colour generator 16 generates the opponent colour of the key colour. The opponent colour of the key colour is generated based on the opponent process colour theory that is familiar to those skilled in the art of imaging. As described above, the opponent process is immutable and the results are always the same when the opponent process is applied using the computing device 2 in the systems and methods of examples of this disclosure.

[0073] The opponent colour generator 16 generates the opponent colour by subtracting a predetermined shift value from each of the red (R), green (G) and blue (B) values of the key colour represented in the RGB colour space. In this example, the red (R), green (G) and blue (B) values are each in the range 0-255 and the predetermined shift value is 255.

[0074] Once the opponent colour generator 16 has generated the opponent colour, the computing device 2 is configured to display colour harmonies generated directly using the key colour as a row of colours in a first palette and colour harmonies generated directly using the opponent colour as a row of colours in a second palette. Colour harmonies in low, medium and high contrast can now be created by choosing any key colour from any of the colours produced from the two rows of colours which directly relate back to the key colour.

[0075] The colour system 1 is therefore able to measure accurately the skin colour and how light / dark a user is. The colour system 1 is also able to produce an opponent colour or colours that compliment and contrast with a user’s natural colouring. In some examples, the colour system 1 is configured to read and render the skin colour and eye colour of the user instantly and accurately, and the equal and opposite colours giving paramount importance to contrast when using colour (contrast in hue and luminosity).

[0076] In some examples, the computing device 2 comprises a palette generator 17 which is configured to generate a colour harmonies directly using the key colour to create a row of colours in a given palette and a second row of colours generated directly using the opponent colour of the key colour within the same palette, wherein the system is configured to display the colour harmonies generated by the palette generator. In some examples, the colour system 1 is configured to display the colour harmonies generated by the palette generator 17. In some examples, the palette generator 17 is configured to generate a palette of colours directly using the key colour and the opponent colour in one of a monochromatic harmony, complimentary harmony, opposite adjacent harmony, adjacent harmony, or compound harmony.

[0077] Given that the scientific colour wheel presents a scientific means of viewing / understanding the relationship between different colours it is also possible to plot within it, numerous colour harmonies or colour schemes that feature multiple colours which are impactful or agreeable to the human optic system. In some examples, the colours in the harmonies / schemes produced by the palette generator 17 all relate directly to the user and one another scientifically and create different psychological states and moods. In some examples, the palette generator 17 is configured to generate a series of colour harmonies based on the hue and luminosity of the skin colour of a user and its opponent. In instances where the variance in luminosity between the skin and opponent colour of the user is not sufficiently strong to create the desired levels of contrast in a recommended harmony, the luminosity of some of the colours featured in the harmony is, via an automated process, increased or decreased by 20-30%. If, in the process of increasing the luminosity of a given colour, in a given harmony, to increase the level of contrast between the featured colours, the hue of the colour is diminished to an unacceptable level, the saturation of the colour also increases by a set percentage. The palette generator 17 is intentionally configured in this way for scientific reasons relating to the human optic system. In some examples, the palette generator is configured to vary its output according to the seven classifications of skin type.

[0078] Example colour harmonies adopted by the colour system 1 of some examples are shown in Figures 5-9 of the accompanying drawings, where the lines and points in each depiction represent intersections and points on a scientific colour wheel. Each of these colour harmonies creates different moods and levels of dynamism that are impactful on a user. Some harmonies containing colours that contrast radically in both colour and luminosity create the most arresting looks (e.g. complementary), while others that contain colours which contrast minimally in colour and luminosity (e.g. monochromatic) create mid to low key looks. It is commonly accepted that different colours and colour harmonies impact us and others psychologically, they say something about how we feel / present in this world and impact how people perceive us (or our homes, or wherever else we use colour as a form of self-expression).

[0079] In some examples, the colour system 1 is configured to display key colours and opponent colours in low, medium and high contrast harmonies for different moods. In some examples, the colour system 1 is configured to detect how naturally light and dark a user is. This provides a starting point from which the colour system 1 produces a palette of colours that is genuinely unique to the user and subsequent palettes of colour containing colours associated with the user’s unique colours. The user’s skin colour is the fulcrum on which colour palettes produced by the colour system are based and / or derived directly. Having generated a unique colour palette, the colour system 1 allows the user to select favourites from that palette and to view those favourites in differing colour harmonies (monochromatic, complementary, analogous, etc.). Each colour harmony depicts the user’s chosen favourite colour alongside a myriad of other colours that remain scientifically linked to the user by virtue of their relationship with the chosen favourite colour. In some examples, the harmony produced is generated from the favourite colour which in turn featured in the user’s unique palette.

[0080] In some examples, the colour system 1 enables a user to choose any colour from either a column of colours created from the key or skin colour and its relative luminosity or from within a column of colours created from the opponent colour of the key or skin colour and its relative luminosity as the foundation from which to create a new colour palette which contains a column of colours created from the key or skin colour and its relative luminosity and a column of colours created from the opponent colour of the key or skin colour.

[0081] Adjusting to key colour luminosity and saturation

[0082] In some examples, the colour system 1 is configured to apply the luminosity value of the key colour (e.g. the average skin colour luminosity) to the luminosity values of the primaries and secondaries. The colour system 1 adjusts the luminosity levels of the red, green, blue, cyan, magenta and yellow individually to that of the luminosity value of the key colour (e.g. the skin luminosity).

[0083] In these examples, the colour system 1 applies the luminosity level of the opponent colour of the key (skin) colour to the luminosity values of a new set of primary and secondary colours. That is the luminosity levels of the red, green, blue, cyan, magenta and yellow are adjusted to that of the opponent luminosity reading.

[0084] The colour system 1 thus produces two sets of the primaries and secondaries; one row of the primary and secondaries at the key (skin) colour’s luminosity and one row at the opponent luminosity of the key (skin) colour. The colour system 1 displays one row lighter than the other darker depending on how light or dark the key (skin) colour is.

[0085] In some examples, the colour system 1 displays the colours on the screen 4 to enable a user to select a colour. For example, in the case of a dark blue; this blue was created by the colour system 1 measuring the luminosity of a person’s skin which is unique to them so any colour harmony (e.g. monochromatic) created from this blue will have a relative luminosity in direct relationship to the person’s skin colour forming part of the palette.

[0086] The colour system 1 therefore allows, for the first time, a person to achieve all forms of colour harmonies in direct relation to their key colour choice and luminosity. Therefore, creating harmonies which include their skin colour precisely as part of the colour harmony. This facilitates the use of any chosen key colour and its luminosity to be used to create different harmonies and moods.

[0087] In some examples, once the user has selected a colour, the selected colour is used as an input to the colour system 1 by inputting the selected colour in a digital image to the computing system 2, as described above. The colour system 1 can thereby use the selected colour to create varying colour harmonies, such as monochromatic, complimentary, compound and analogous, and output palettes to enable a user to choose different harmonies and moods with varying contrast levels. Consequently, the colour system 1 does not so confine a user to a limited palette of fixed colours based on their skin / eye colour. Furthermore, the colour system 1 does not suggest that the user can only wear colours that are as light as the luminosity of the skin / eyes or as dark as their complementary colours. By contrast, the colour system 1 allows a user to discover other colours linked to their key / unique colours and to see their colours at different luminosities. In this way, the colour system 1 begins to open up the world of colour for its users. On selecting a key colour and viewing it in the available colour harmonies the user can dial up or dial down their looks in terms of dynamism depending on the occasion and mood they wish to create.

[0088] The colour system 1 adds the most advanced colour separation technology to a camera and / or image processing system to detect not only a user’s skin / eye colour but how light or dark the user is. To unleash the true potential and dynamism of colour, the system considers the use of contrast and the relationship between colours when placed next to one another. In some examples, the colour system 1 begins by detecting the key colour of a user’s skin / eye to generate colours that complement the user’s natural colouring. Using your skin / eye colour as the starting point, the colour system 1 enables a user to explore complementary colours. The opponent colour generator 16 automatically generates the equal and opposite (‘opponent’) colour to a user’s skin colour to provide a range of contrast (in both colour and lightness / darkness or ‘luminosity’) for the user to consider.

[0089] In some examples, colour palettes generated by the palette generator 17, at the tap of a finger, can be adjusted to match the lightness / darkness of a user’s skin colour, acting as a measure from which to dial-up or dial-down the use of colour depending on the requirements of the user. The colour system 1 is so advanced that the colour system 1 has the capability to instantly read any skin colour. In some examples where the computing device is a smartphone, the colour system 1 guides a user through a process of capturing the perfect image with the smartphone camera.

[0090] The colour system 1 enables a user to generate endless colour palettes based on the user’s skin / eye colour. In some examples, the colour system 1 comprises a camera 3 to enable a user to capture colours and see those colours in a range of colour harmonies. The colour system 1 of some examples therefore enables a user to select colours easily, for instance to use colour to lift or lower the mood depending on an occasion or mood.

[0091] All the colours in the electromagnetic spectrum feature in a linear form with the visible colours passing from blue at one end of the spectrum to red at the other end of the spectrum. The scientific colour wheel plots these same colours in a circular two-dimensional representation and shows precisely where those colours sit in relation to one another when presented in this format. For example, blue is opposite yellow, red is opposite cyan and green is opposite magenta. The scientific colour wheel is a two-dimensional depiction of the three dimensions of colour (hue / light and dark). This is very important to the colour system 1 because the scientific colour wheel enables the colour system 1 to produce colour palettes that vary in hue, remembering that colours when placed next to one another are more distinctly seen by the human optical system when they are strongly contrasting and opposing.

[0092] It helps if one thinks of these colours / hues as sitting within the circumference of the wheel like numbers on a clock face, and that there are a series of moveable scales, that runs vertically through the centre of the wheel at incremental points on each of the circle’s 360 degrees. Upon these vertical axes the luminosity (lightness / darkness) of the colours in the circle is measured on a scale of 0 to 100 with 0 representing no colour (black) and 100 representing a colour at full luminosity and full saturation. Taking red as an example 0 represents black, 50% represents maroon, and 100% represents pure red at full saturation. This variance in luminosity in colours is very important to the colour system 1 as it represents the technique by which colours contrast strongly with one another. In other words, different hues can create contrast as can variance of luminosity in a single colour. Colours are referred to as being saturated when the luminosity of the colour (or level of light in the colour) is low and desaturated when the luminosity is high.

[0093] When one thinks how many colours there are within the visible light spectrum, and that those colours are visible in thousands of different levels of saturation and luminosity, one begins to appreciate the enormity of the range of colour available to the human eye. Unlike conventional colour systems, the colour system 1 of examples of this disclosure is capable of generating colour harmonies based on a full spectrum of over 16 million colours.

[0094] In between total darkness and white light lie all the colours within the visible light spectrum. It is understanding the interplay between light and colour (which dictates how saturated or desaturated a colour is - e.g. maroon is pure red at 50% luminosity) and between colours when placed next to one another, that provides a scientific basis for understanding and appreciating the power of light and colour.

[0095] In industry, the importance of a user liking and relating to the colours they utilise cannot be underestimated. This is often overlooked in the traditional / current approach to colour analysis / consultancy. In a conventional approach, the palettes imposed are so constricted that if confined to a season and the subject does not like the recommended colours, no lasting changes are made to the person’s use of / relationship with colour.

[0096] Unlike conventional approaches, the colour system 1 of some examples does not so confine a user to a limited palette of fixed colours based on their skin / eye colour or suggest that the user can only wear colours that are as light as the luminosity of the skin / eyes or as dark as their complementary colours. By allowing the user to discover other colours linked to their key / unique colours and to see their colours at different luminosities, the colour system 1 begins to open up the world of colour for its users.

[0097] In some examples, any colour can be captured using a camera and the colour system 1 will generate the hex code and demonstrate the given colour in multiple colour harmonies. This functionality will be of invaluable use to both personal users and any professional whose work involves the use of colour. By way of example, an interior designer may see a colour and capture that colour; the app will read the hue and luminosity of the colour in question, and then use the scientific values associated with that colour to produce accurate colour palettes containing other colours that are scientifically linked with the values of the key / target colour.

[0098] In some examples, the computing device 2 is configured to communication with a remote server 18 or other remote computing device, for instance via the Internet. In these examples, one or more of the functions of the colour system 1 may be implemented in or performed by the remote server 18.

[0099] In some examples, to obtain an initial image which is as accurate as possible in circumstances where images may be taken in various biased lighting conditions that are either too warm or cool, the colour system 1 comprises a light correction module which is configured to balance the ambient light prevailing at the time an image was taken. The colour system 1 is therefore able to render an accurate skin colour. In these examples, the light correction module may be implemented in the remote server 18.

[0100] In some examples, the computing device 2 comprises an item matcher 19 configured to match an item to the chosen key colour or using a selection of chosen colours within the harmony derived from the key colour. In some examples, the item matcher 19 is configured to match a colour in a colour palette generated by the palette generator 17 to a colour of the item. In some examples, the item matcher 19 comprises an image search module that searches through images on a remote server or in the cloud to identify images showing an item having a colour that matches at least one of the key colour and the opponent colour.

[0101] In some examples, the item matcher 19 operates in conjunction with a search engine to find images of items (e.g. furniture or fashion items) having a colour that matches a chosen key colour or using a selection of chosen colours within a harmony to find other items which match the colours within the harmony. In some examples, the item matcher 19 is configured to match a plurality of items to a plurality of colours in a colour harmony generated by the colour system 1 . This can be utilised by the user to create a story board or for finding correctly coloured items to buy online.

[0102] A user can therefore use the colour system 1 to capture a colour (e.g. via a camera) of a skin colour or any object and identify other items with similar or complimentary colours based on the largest available colour space to generate colour palettes generated by the colour system. This versatility in colour generation is beneficial in many different industries, such as in the Arts, Personal Styling, Computer Graphics, Film, Interior Design, and beyond.

[0103] The visually impactful colour harmonies that are generated by the colour system 1 are also beneficial in the signage industry to ensure that signage is noticeable. In some examples, the key colour and opponent colour are output from the colour system 1 to a signage module which is configured to manufacture a sign displaying text and / or symbols in the key colour and the opponent colour or in at least one colour from a colour palette generated by the colour system 1 . The use of these colours on signage makes the signage more noticeable to users and can therefore help warn users of danger.

[0104] In other examples, the colour system 1 outputs the key colour and the opponent colour to a document production module which is configured to generate text in the key colour and the opponent colour. The document production module can therefore output a document (which may be a printed hard copy document) with text that is impactful and easy for a partially sighted user to read.

[0105] While the components of the colour system 1 have been described above, those skilled in the art will appreciate that the colour system 1 may be used to perform a method for generating colour harmonies that are visually impactful on a user. In other examples, a computer-implemented method is provided for generating a colour harmony based directly from the key colour (e.g. skin colour of a user).

[0106] In the described embodiments, the system may be implemented as any form of a computing and / or electronic device. Such a device may comprise one or more processors which may be microprocessors, controllers, or any other suitable type of processors for processing computerexecutable instructions to control the operation of the device. In some examples, for example where a system-on-a-chip architecture is used, the processors may include one or more fixed function blocks (also referred to as accelerators) which implement a part of the method in hardware (rather than software or firmware). Platform software comprising an operating system, or any other suitable platform software may be provided at the computing-based device to enable application software to be executed on the device.

[0107] Various functions described herein can be implemented in hardware, software, or any combination thereof. If implemented in software, the functions can be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media may include, for example, computer-readable storage media. Computer-readable storage media may include volatile or non-volatile, removable or non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. A computer-readable storage media can be any available storage media that may be accessed by a computer. By way of example, and not limitation, such computer- readable storage media may comprise RAM, ROM, EEPROM, flash memory or other memory devices, CD-ROM or other optical disc storage, magnetic disc storage or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. Disc and disk, as used herein, include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc (BD). Further, a propagated signal is not included within the scope of computer- readable storage media. Computer-readable media also includes communication media including any medium that facilitates transfer of a computer program from one place to another. A connection, for instance, can be a communication medium. For example, software transmitted from a website, server, or other remote source using a coaxial cable, fibre optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave is included in the definition of communication medium. Combinations of the above should also be included within the scope of computer-readable media.

[0108] Alternatively, or in addition, the functionality described herein can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, hardware logic components that can be used may include Field-programmable Gate Arrays (FPGAs), Programspecific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a- chip systems (SOCs), or Complex Programmable Logic Devices (CPLDs).

[0109] The functionality of the components or modules described herein may be implemented as a set of logic instructions stored in a machine- or computer- readable storage medium such as random access memory (RAM), read only memory (ROM), programmable ROM (PROM), firmware, flash memory, etc., in configurable logic such as, for example, programmable logic arrays (PLAs), field programmable gate arrays (FPGAs), complex programmable logic devices (CPLDs), in fixed- functionality logic hardware using circuit technology such as, for example, application specific integrated circuit (ASIC), complementary metal oxide semiconductor (CMOS) or transistor-transistor logic (TTL) technology, or any combination thereof. For example, computer program code to carry out operations may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++, Python or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages.

[0110] Although illustrated as a single system, it is to be understood that the computing device may be a distributed system. Thus, for instance, several devices may be in communication by way of a network connection and may collectively perform tasks described as being performed by the computing device. Although illustrated as a local device, it will be appreciated that the computing device may be located remotely and accessed via a network or other communication link (for example, using a communication interface).

[0111] The term ‘computer’ is used herein to refer to any device with processing capability such that it can execute instructions. Those skilled in the art will realise that such processing capabilities are incorporated into many different devices and therefore the term ‘computer’ includes PCs, servers, mobile telephones, personal digital assistants, and many other devices.

[0112] Those skilled in the art will realise that storage devices utilised to store program instructions can be distributed across a network. For example, a remote computer may store an example of the process described as software. A local or terminal computer may access the remote computer and download a part or all of the software to run the program. Alternatively, the local computer may download pieces of the software as needed or execute some software instructions at the local terminal and some at the remote computer (or computer network). Those skilled in the art will also realise that by utilising conventional techniques known to those skilled in the art that all, or a portion of the software instructions may be carried out by a dedicated circuit, such as a DSP, programmable logic array, or the like.

[0113] It will be understood that the benefits and advantages described above may relate to one embodiment or may relate to several embodiments. The embodiments are not limited to those that solve any or all of the stated problems or those that have any or all of the stated benefits and advantages.

[0114] Any reference to ‘an’ item refers to one or more of those items. The term ‘comprising’ is used herein to mean including the method steps or elements identified, but that such steps or elements do not comprise an exclusive list and a method or apparatus may contain additional steps or elements.

[0115] As used herein, the terms ‘component’ and ‘system’ are intended to encompass computer-readable data storage that is configured with computer-executable instructions that cause certain functionality to be performed when executed by a processor. The computer-executable instructions may include a routine, a function, or the like. It is also to be understood that a component or system may be localised on a single device or distributed across several devices.

[0116] Further, as used herein, the term ‘exemplary’ is intended to mean ‘serving as an illustration or example of something’. Further, to the extent that the term ‘includes’ is used in either the detailed description or the claims, such term is intended to be inclusive in a manner similar to the term ‘comprising’ as ‘comprising’ is interpreted when employed as a transitional word in a claim.

[0117] The figures illustrate exemplary methods. While the methods are shown and described as being a series of acts that are performed in a particular sequence, it is to be understood and appreciated that the methods are not limited by the order of the sequence. For example, some acts can occur in a different order than what is described herein. In addition, an act can occur concurrently with another act. Further, in some instances, not all acts may be required to implement a method described herein.

[0118] It will be understood that the above description of a preferred embodiment is given by way of example only and that various modifications may be made by those skilled in the art. What has been described above includes examples of one or more embodiments. It is, of course, not possible to describe every conceivable modification and alteration of the above devices or methods for purposes of describing the aforementioned aspects, but one of ordinary skill in the art can recognise that many further modifications and permutations of various aspects are possible. Accordingly, the described aspects are intended to embrace all such alterations, modifications, and variations that fall within the scope of the appended claims.

[0119] It is furthermore contemplated that any part of any aspect or embodiment discussed in this specification can be implemented or combined with any part of any other aspect or embodiment discussed in this specification.

[0120] When used in this specification and claims, the terms "comprises" and "comprising" and variations thereof mean that the specified features, steps or integers are included. The terms are not to be interpreted to exclude the presence of other features, steps or components.

[0121] The invention may also broadly consist in the parts, elements, steps, examples and / or features referred to or indicated in the specification individually or collectively in any and all combinations of two or more said parts, elements, steps, examples and / or features. In particular, one or more features in any of the embodiments described herein may be combined with one or more features from any other embodiment(s) described herein.

[0122] Protection may be sought for any features disclosed in any one or more published documents referenced herein in combination with the present disclosure. Although certain example embodiments of the invention have been described, the scope of the appended claims is not intended to be limited solely to these embodiments. The claims are to be construed literally, purposively, and / or to encompass equivalents.

[0123] REPRESENTATIVE FEATURES

[0124] Representative features are set out in the following clauses, which stand alone or may be combined, in any combination, with one or more features disclosed in the text and / or drawings of the specification.

[0125] 1 . A colour system for generating a colour harmony based directly from the skin colour of a user, the system comprising: a region selector which is configured to select a region of the face of the user in a digital image of the face of the user; a colour identifier coupled to the region selector, the colour identifier being configured to identify a key colour by calculating an average colour across at least a part of the region of the face of the user in the digital image and to store data indicative of the key colour in a memory, the key colour being the skin colour of the user; an opponent colour generator coupled to the colour identifier, the opponent colour generator being configured to receive the data indicative of the key colour data from the colour identifier and to generate the opponent colour of the skin colour using the key colour data; and a screen configured to display the skin colour and the opponent colour of the skin colour to provide a colour harmony to the user based directly from the skin colour of the user that is visually correct such that the colour harmony is arresting and has an impact on the user.

[0126] 2. A colour system for generating a colour harmony that is visually correct such that the colour harmony is arresting and has an impact on a user, the system comprising: a region selector which is configured to select a region of a digital image; a colour identifier coupled to the region selector, the colour identifier being configured to identify a key colour by calculating an average colour across at least a part of the region of the digital image; an opponent colour generator coupled to the colour identifier, the opponent colour generator being configured to receive key colour data from the colour identifier, the key colour data being indicative of the key colour, and to generate the opponent colour of the key colour; and a screen configured to display the key colour and the opponent colour of the key colour to provide a colour harmony to the user based directly from the key colour that is visually correct such that the colour harmony is arresting and has an impact on the user. 3. The system of clause 2, wherein the digital image comprises a portion having a colour selected by a user.

[0127] 4. The system of clause 1 or clause 2, wherein the region selector comprises: a computer vision system which is configured to process the digital image and identify a three-dimensional surface shown in the digital image, and wherein the region selector is configured to select a region of the three-dimensional surface as the region of the digital image.

[0128] 5. The system of clause 4, wherein the computer vision system is configured to: recognise a human face in the digital image, identify a three-dimensional surface of the human face, and select a region of the three-dimensional surface comprising the surface of at least part of a cheek of the human face as the region of the digital image.

[0129] 6. The system of any one of the preceding clauses, wherein the colour identifier is configured to: sample a predetermined number of pixels from the selected region of the digital image, measure red (R), green (G) and blue (B) colour values in the RGB colour space for each pixel of the sampled pixels, each colour value being an integer in the range 0 to 255, and identify the key colour by calculating an average value for each of the red (R), green (G) and blue (B) values across the sampled pixels.

[0130] 7. The system of clause 6, wherein the colour identifier is configured to calculate the average value for each of the red (R), green (G) and blue (B) values across the sampled pixels using the following equations:

[0131] Average R = (Sum of R values of sampled pixels) I (Number of sampled pixels), Average G = (Sum of G values of sampled pixels) I (Number of sampled pixels), and Average B = (Sum of B values of sampled pixels) I (Number of sampled pixels).

[0132] 8. The system of clause 6 or clause 7, wherein the colour identifier is configured to: convert the key colour from the RGB colour space to the LAB colour space, and identify the luminance (L) of the key colour and store a luminance value indicative of the luminance (L) in the memory.

[0133] 9. The system of any one of the preceding clauses, wherein the opponent colour generator is configured to: generate the opponent colour by subtracting a predetermined shift value from each of the red (R), green (G) and blue (B) values of the key colour represented in the RGB colour space.

[0134] 10. The system of clause 9, wherein the predetermined shift value is 255.

[0135] 11 . The system of any one of the preceding clauses, wherein the system further comprises: a palette generator which is configured to generate colour harmonies directly using the key colour to create a row of colours in a given palette and a second row of colours generated directly using the opponent colour of the key colour within the same palette, wherein the system is configured to display the colour harmonies generated by the palette generator.

[0136] 12. The system of clause 11 , wherein the palette generator is configured to generate a palette of colours directly from the key colour and the opponent colour in either a monochromatic harmony, complimentary harmony, opposite adjacent harmony, adjacent harmony or compound harmony.

[0137] 13. The system of any one of the preceding clauses, wherein the system further comprises: an item matcher configured to match an item to the chosen key colour or using a selection of chosen colours within the harmony derived from the key colour.

[0138] 14. The system of clause 12 as dependent on clause 11 , wherein the item matcher is configured to match a colour in the colour palette to a colour of the item.

[0139] 15. A computer-implemented method for generating a colour harmony based directly from the skin colour of a user, the method comprising: selecting a region of the face of the user in a digital image of the face of the user; identify a key colour by calculating an average colour across at least a part of the region of the face of the user in a digital image and storing data indicative of the key colour in a memory, the key colour being the skin colour of the user; generating the opponent colour of the skin colour using the key colour data; and displaying the skin colour and the opponent colour of the skin colour on a screen to provide a colour harmony to the user based directly from the skin colour of the user that is visually correct such that the colour harmony is arresting and has an impact on the user.

[0140] 16. A computer-implemented method for generating a colour harmony that is visually correct such that the colour harmony is arresting and has an impact on a user, the method comprising: receiving, at a computing system, a digital image; selecting, by the computing system, a region of the digital image; identifying, by the computing system, a key colour by calculating an average colour across at least part of the region of the digital image; generating, by the computing system, the opponent colour of the key colour; and displaying the key colour and the opponent colour of the key colour to provide a colour harmony to the user based directly from the key colour that is visually correct such that the colour harmony is arresting and has an impact on the user.

[0141] 17. The method of clause 16, wherein the method comprises: receiving a selected colour in response to an input from a user; and providing to the computing device the digital image comprising the selected colour.

[0142] 18. The system of clause 15 or clause 16, wherein selecting a region of the digital image comprises selecting a region of a cheek of a human face shown in the digital image.

[0143] 19. The method of any one of clauses 15 to 18, wherein the method comprises: processing the digital image to identify a three-dimensional surface shown in the digital image; and selecting a region of the three-dimensional surface as the region of the digital image.

[0144] 20. The method of clause 19, wherein the method comprises: recognising a human face in the digital image, identifying a three-dimensional surface of the human face, and selecting a region of the three-dimensional surface comprising the surface of at least part of a cheek of the human face as the region of the digital image.

[0145] 21 . The method of clause 19, wherein the method comprises: sampling a predetermined number of pixels from the selected region of the digital image; measuring red (R), green (G) and blue (B) colour values in the RGB colour space for each pixel of the sampled pixels, each colour value being an integer in the range 0 to 255; and identifying the key colour by calculating an average value for each of the red (R), green (G) and blue (B) values across the sampled pixels.

[0146] 22. The method of clause 21 , wherein the method comprises: converting the key colour from the RGB colour space to the LAB colour space, and identifying the luminance (L) of the key colour and store a luminance value indicative of the luminance (L) in the memory.

[0147] 23. The method of clause 22, wherein the method comprises: generating the opponent colour by subtracting a predetermined shift value from each of the red (R), green (G) and blue (B) values of the key colour represented in the RGB colour space. 24. The method of any one of clauses 15 to 23, wherein the method comprises: generating at least one harmony colour using at least one of the key colour and the opponent colour. 25. A computer-readable storage medium comprising instructions which, when executed by a computing device, cause the computing device to perform the method of any one of clauses 15 to

Claims

CLAIMS1 . A colour system for generating a colour harmony based directly from the skin colour of a user, the system comprising: a region selector which is configured to select a region of the face of the user in a digital image of the face of the user; a colour identifier coupled to the region selector, the colour identifier being configured to identify a key colour by calculating an average colour across at least a part of the region of the face of the user in the digital image and to store data indicative of the key colour in a memory, the key colour being the skin colour of the user; an opponent colour generator coupled to the colour identifier, the opponent colour generator being configured to receive the data indicative of the key colour data from the colour identifier and to generate the opponent colour of the skin colour using the key colour data; and a screen configured to display the skin colour and the opponent colour of the skin colour to provide a colour harmony to the user based directly from the skin colour of the user that is visually correct such that the colour harmony is arresting and has an impact on the user.

2. A colour system for generating a colour harmony that is visually correct such that the colour harmony is arresting and has an impact on a user, the system comprising: a region selector which is configured to select a region of a digital image; a colour identifier coupled to the region selector, the colour identifier being configured to identify a key colour by calculating an average colour across at least a part of the region of the digital image; an opponent colour generator coupled to the colour identifier, the opponent colour generator being configured to receive key colour data from the colour identifier, the key colour data being indicative of the key colour, and to generate the opponent colour of the key colour; and a screen configured to display the key colour and the opponent colour of the key colour to provide a colour harmony to the user based directly from the key colour that is visually correct such that the colour harmony is arresting and has an impact on the user.

3. The system of claim 2, wherein the digital image comprises a portion having a colour selected by a user.

4. The system of claim 1 or claim 2, wherein the region selector comprises: a computer vision system which is configured to process the digital image and identify a three-dimensional surface shown in the digital image, and wherein the region selector is configuredto select a region of the three-dimensional surface as the region of the digital image.

5. The system of claim 4, wherein the computer vision system is configured to: recognise a human face in the digital image, identify a three-dimensional surface of the human face, and select a region of the three-dimensional surface comprising the surface of at least part of a cheek of the human face as the region of the digital image.

6. The system of any one of the preceding claims, wherein the colour identifier is configured to: sample a predetermined number of pixels from the selected region of the digital image, measure red (R), green (G) and blue (B) colour values in the RGB colour space for each pixel of the sampled pixels, each colour value being an integer in the range 0 to 255, and identify the key colour by calculating an average value for each of the red (R), green (G) and blue (B) values across the sampled pixels.

7. The system of claim 6, wherein the colour identifier is configured to calculate the average value for each of the red (R), green (G) and blue (B) values across the sampled pixels using the following equations:Average R = (Sum of R values of sampled pixels) I (Number of sampled pixels), Average G = (Sum of G values of sampled pixels) I (Number of sampled pixels), and Average B = (Sum of B values of sampled pixels) I (Number of sampled pixels).

8. The system of claim 6 or claim 7, wherein the colour identifier is configured to: convert the key colour from the RGB colour space to the LAB colour space, and identify the luminance (L) of the key colour and store a luminance value indicative of the luminance (L) in the memory.

9. The system of any one of the preceding claims, wherein the opponent colour generator is configured to: generate the opponent colour by subtracting a predetermined shift value from each of the red (R), green (G) and blue (B) values of the key colour represented in the RGB colour space.

10. The system of claim 9, wherein the predetermined shift value is 255.11 . The system of any one of the preceding claims, wherein the system further comprises: a palette generator which is configured to generate colour harmonies directly using the key colour to create a row of colours in a given palette and a second row of colours generated directly using the opponent colour of the key colour within the same palette, wherein the system is configured to display the colour harmonies generated by the palette generator.

12. The system of claim 11 , wherein the palette generator is configured to generate a palette of colours directly from the key colour and the opponent colour in either a monochromatic harmony, complimentary harmony, opposite adjacent harmony, adjacent harmony or compound harmony.

13. The system of any one of the preceding claims, wherein the system further comprises: an item matcher configured to match an item to the chosen key colour or using a selection of chosen colours within the harmony derived from the key colour.

14. The system of claim 12 as dependent on claim 11 , wherein the item matcher is configured to match a colour in the colour palette to a colour of the item.

15. A computer-implemented method for generating a colour harmony based directly from the skin colour of a user, the method comprising: selecting a region of the face of the user in a digital image of the face of the user; identify a key colour by calculating an average colour across at least a part of the region of the face of the user in a digital image and storing data indicative of the key colour in a memory, the key colour being the skin colour of the user; generating the opponent colour of the skin colour using the key colour data; and displaying the skin colour and the opponent colour of the skin colour on a screen to provide a colour harmony to the user based directly from the skin colour of the user that is visually correct such that the colour harmony is arresting and has an impact on the user.

16. A computer-implemented method for generating a colour harmony that is visually correct such that the colour harmony is arresting and has an impact on a user, the method comprising: receiving, at a computing system, a digital image; selecting, by the computing system, a region of the digital image; identifying, by the computing system, a key colour by calculating an average colour across at least part of the region of the digital image; generating, by the computing system, the opponent colour of the key colour; and displaying the key colour and the opponent colour of the key colour to provide a colour harmony to the user based directly from the key colour that is visually correct such that the colour harmony is arresting and has an impact on the user.

17. The method of claim 16, wherein the method comprises: receiving a selected colour in response to an input from a user; and providing to the computing device the digital image comprising the selected colour.

18. The system of claim 15 or claim 16, wherein selecting a region of the digital image comprises selecting a region of a cheek of a human face shown in the digital image.

19. The method of any one of claims 15 to 18, wherein the method comprises: processing the digital image to identify a three-dimensional surface shown in the digital image; and selecting a region of the three-dimensional surface as the region of the digital image.

20. The method of claim 19, wherein the method comprises: recognising a human face in the digital image, identifying a three-dimensional surface of the human face, and selecting a region of the three-dimensional surface comprising the surface of at least part of a cheek of the human face as the region of the digital image.21 . The method of claim 19, wherein the method comprises: sampling a predetermined number of pixels from the selected region of the digital image; measuring red (R), green (G) and blue (B) colour values in the RGB colour space for each pixel of the sampled pixels, each colour value being an integer in the range 0 to 255; and identifying the key colour by calculating an average value for each of the red (R), green (G) and blue (B) values across the sampled pixels.

22. The method of claim 21 , wherein the method comprises: converting the key colour from the RGB colour space to the LAB colour space, and identifying the luminance (L) of the key colour and store a luminance value indicative of the luminance (L) in the memory.

23. The method of claim 22, wherein the method comprises: generating the opponent colour by subtracting a predetermined shift value from each of the red (R), green (G) and blue (B) values of the key colour represented in the RGB colour space.

24. The method of any one of claims 15 to 23, wherein the method comprises: generating at least one harmony colour using at least one of the key colour and the opponent colour.

25. A computer-readable storage medium comprising instructions which, when executed by a computing device, cause the computing device to perform the method of any one of claims 15 to 24.

Images