CONSUMERTEC LOGO           Home | Contact Us

Conduct Virtual Experiments
in World's Consumer Relevant Terms

Consumertec Laundry Lab Suite (CLLS) - Second Component

Unique collection of algorithms used by detergency labs around the world to conduct in-silico experimentation on predicted consumer responses about cleanliness, whiteness and colour-care perceptions

No one human being perceive the same as other. In vision, lightness and colour perception are different for different people under exactly the same context. At different visual context all perceptions can change. Are cleanliness, whiteness and colour-care perception relative? - Why numerical models to represent consumer visual perceptions?

They can overpass the conventional basic colorimetric calculations provided by spectrometric devices, opening the room for more advanced and relevant procedures based on modern understandings of fluorescent spectroscopy and vision science

Final output includes plausible variable consumer perceptions elicited in relevant market scenarios around the world, which in turn can be compared with a set of perceptual features that characterise each market in the areas of cleanliness and whiteness.

Frequently asked questions (FAQs)



CLLS Algorithms Milestones:




a. Start from any spectral data

Capable to work with spectral data coming from any equipment that works without and with UV cutting filters, collected under any source of illumination, including pulse xenon lamps or led lamps.






b. Predict new radiance of fluorescent fabrics

Algorithms calculate new spectral total, reflected and luminescent radiance factor, under relevant natural or artificial source of illuminations with different UV relative content, based on new validated algorithms based on non-contact spectrofluorimetry.

Final radiance is an estimation of the absolute energy capable to reach consumer eye's cornea at some specific visual scenario.






c. Set modern colorimetric attributes and uniform colour spaces

They use categorical visual observers, taken into account: consumer ages, field size, lens optical density, macula optical density, photopigments optical density, and photopigments lambda maximum shift.

Apply modern colour appearance models including CIECAM02 (updated version) and the new SWW model to quantify colour attributes and graph three-dimensional uniform colour spaces.

Include garment's context and surroundings in numerical calculations of visual colour attributes. Simultaneous lightness and colour contrast effects.








d. Predict consumer responses using a set of innovative cleanliness, whiteness and colour-care models

Apply novel models of cleanliness perception according to different consumer sensitivities to perceive colour differences under changing contexts. More sensitivities to chroma, hue, lightness and balanced.

Work with new models of whiteness perception according to different cultural white reference points, and other with garments as context during laundry or at closet. Preferences to whites with more lightness than bluish, more blue-violetish, more blue-greenish or more bluish than lightness.

Apply modern numerical models to represent blackness or any other colour perception based on new understanding of categorical colour percepts under the influence of white surrounds that change during laundry.






e. Generate maps of useful consumer perceptual responses

Asses whether there is a practical difference between means. Conduct statistical pairwise comparison against a benchmark. It uses two one-sided t-tests from both sides of the difference interval of means with a variable threshold.

As maps they show areas when substantial differences appears between products/technologies and show the pathway to future explorations under precise coordinates.






f. Match market variability with stimuli distribution

CLLS has the potential to characterise the perception variability in consumer realities by collecting and setting the frequency of occurrence of biological determined stimuli at specific market environments, in which perceptions are elicited. By this way maps of consumer perceptual responses are linked to specific laundry markets.

The conventional correlation statistical modelling parameter is replaced with a precise match of variability using modelling techniques that work on wholly empirical terms.





Frequently Asked Questions (FAQs)


Are consumer perception context-relative?
... yes, cleanliness, whiteness and colour-care perception are relative terms

Visual and olfactive cleanliness, visual whiteness as well as colour-care visual perception depends on consumer realities. There is no absolute cleanliness, whiteness, freshness/cleanliness nor colour-care, all depends on consumers, environments and history.

Cleanliness perception depends on visual detection of remanent stained areas at places perceived as stained before laundry. That visual detection is conducted automatically doing a comparison between the prior stained area and its surrounding. Full remotion means that no remanent stained area is detected or the slight presence of remanent stained is nearly not perceived and accepted as clean. The level of consumer sensitivity to detect sometimes small differences depends,among others on previous laundry experiences, consumer age, garment life and significance, expected laundry performance, and importantly on the visual scenario present during visual evaluation of laundry results.

Whiteness perception, a complex relative perceptual attribute, is linked on the one hand to consumer ability to perceive surface's more basics attributes like lightness, red-green opponency and yellow-blue opponency, all under some specific visual scenario, and on the other, to consumer preference of what is considered as more white, which has roots on habits and culture. The evolution of whiteness models are linked to the evolution of the level of understanding of basic and relative perceptual attributes of colours like brightness, lightness, colourfulness, chroma, saturation and hue as well as phenomenon like chromatic adaptation and colour constancy, on the consumer side; and of light reflection and fluorescence, on the surface side. Currently the reference whites (like a recently purchased white garment) are surfaces that fluoresce usually with shading dyes, and these are relative to different world regions.

Colour-care perception has conventionally been treated as a colour change process after some washing and drying cycle. In that terms, it has been considered a relative minor problem in the laundry industry because consumers has no reference of the original colour garment. Nowadays the situation is different. Much of current coloured garments are in fact a combination of white areas with adjacent coloured areas so much of colour-care perception is a visual perception of some coloured area adjacent or surrounded by a white area, therefore is a case of colour contrast effects in which whiteness perception of the adjacent fabric affect the colour perception of the coloured area. This simple fact, easy to notice at lab, has tremendous implications for numerical calculations that needs the use of recent models to calculate colorimetric attributes taking into account adjacent surfaces.

Consumers cleanliness, whiteness, and colour-care perception are relative terms, so new numerical models have to include most of the variables of those perceptions, including: consumer age, sensitivities, visual scenarios, preferences and references.

All of these have a very important role for innovation, which is, to experiment virtually (in-silico) with large complexities, in order to find those technologies that really match the need to products capable to do the job expected by actual consumers around the world.


Why numerical models?
... because they can accurately represent variable perception realities

The ultimate way of consumer understanding is to represent it with a numeric function, capable to be optimised as our understanding improve. It is cyclic, better models to better understanding to better models. This is mandatory for our consumer industry due to the high level of competition and the complex consumer environment; we have to clearly understand how consumers perceive brand central benefits, like whiteness and cleaning, which in turn are key purchase intent drivers.

Marketing teams need to model consumer purchase behaviour in order to virtual simulate the influence of variables on business success or failure. Accurate perception models are the critical intermediate stage, and relevant in-vitro models act as a fulcrum in that effort.

R&D teams needs to experiment in virtual terms so as to be fast, with less costs, and to include a real matrix of relevant market elements. In the laundry market any other way is very expensive, time consuming and practically impossible to follow. Can you image a physical experimentation under five or more source of illuminations? with three or more different group of consumers with different visual conditions due to age? with four or more different group of consumers with different sensitivities and preferences concerning lightness, red-green opponency and yellow-blue opponency? with more than ten different stains and more than ten different white substrates? Probably not, but now all of this and more is possible with virtual R&D techniques. That is the purpose of CONSUMERTEC LAUNDRY LAB SUITE - CLLS.

Why numerical modelling? The well known answer is: "I am never content until I have constructed a mathematical model of what I am studying. If I succeed in making one, I understand; otherwise I do not" William Thomson (Lord Kelvin) 1824 - 1907.



Home | Contact Us

2017. CONSUMERTEC