EP3639215A1

EP3639215A1 - Detecting impurities

Info

Publication number: EP3639215A1
Application number: EP18730695.6A
Authority: EP
Inventors: Arnd Kessler; Lars Zuechner; Peter Schmiedel; Thomas Rechenbach
Original assignee: Henkel AG and Co KGaA
Current assignee: Henkel AG and Co KGaA
Priority date: 2017-06-12
Filing date: 2018-06-05
Publication date: 2020-04-22
Also published as: US11379769B2; WO2018228862A1; DE102017209862A1; US20200134806A1

Abstract

The invention relates in particular to a method which is carried out by one or more devices, having the steps of: capturing a first image of information indicative of at least one impurity on a textile; determining impurity information indicative of at least one property of the impurity on the textile, wherein the at least one property is determined at least partly on the basis of the captured first image of information, and the at least one property of the impurity of the textile is determined at least partly on the basis of a property which depends on the contour of the impurity; and outputting or triggering the output of the determined impurity information. The invention further relates to a device and a system for carrying out the method according to the invention.

Description

Patent application

Determine impurities

Field of the invention

The invention relates to an apparatus and a method for determining impurities. Background of the invention

Impurities on a textile such as garments, curtains or bedding are often difficult to identify. Impurities can not only affect the aesthetics of the textiles, but also represent a hygienic problem for the user of the textile.

Although many impurities are easy to detect by eye, it is often unclear to the user of the textile which composition or origin of the contaminant. For example, in some cases, the user is unaware that the fabric is being contaminated by a mishap. The contamination then falls to the user only at a later time, with the cause and the composition of the contamination close to the user. Impurities with different compositions can also have a very similar appearance to the eye, for example blood stains and tomato stains, especially after a certain period of time, can no longer be distinguished from the eye.

It is desirable for the user to have an indication of the properties of the

To gain contamination. In particular, impurities can be effectively removed by a cleaning process. Such cleaning processes can be greatly facilitated by knowledge of properties of the impurity or even made possible in the first place.

It is known to determine the color of an impurity in order to identify the

To be able to roughly grasp contamination. However, the color of the contaminant, such as a defined color value, alone is insufficient to clearly identify the contaminant. The knowledge of further properties about the contamination is necessary.

General description of some exemplary embodiments of the invention Against the background of the prior art presented, it is therefore an object of the invention to at least partially reduce or avoid the problems described, that is to obtain the most accurate possible knowledge of properties of the contamination on a textile. In particular, the proposed methods and devices

user-friendly to be used in the home.

This object is achieved objectively by a method having the features of claim 1.

According to a first aspect of the invention, a method is described, performed by one or more devices, comprising the method:

Detecting first image information indicative of at least one contaminant on one

textile;

Determining contaminant information indicative of at least one property of the contaminant on the fabric, wherein the at least one property is determined based at least in part on the acquired first image information, and wherein the at least one contaminant property is based at least in part on one of the outline the impurity-dependent property is determined; Issuing or causing the output of the determined contaminant information.

According to a second aspect of the invention, a device is described which is set up or comprises corresponding means for carrying out and / or controlling a method according to the first aspect. Devices of the method according to the first aspect are or comprise in particular one or more devices according to the second aspect.

An impurity is understood in particular to be an accumulation of foreign matter on a material of a textile or a discoloration of the surface of the textile, in particular in the form of a stain, dirt or imperfections. For example, on the surface are particles such as dust, traces of liquids, dyes or greasy residues. Furthermore, unfixed textile dyes may also have been incorporated in the textile material, with the unfixed textile dyes being able to detach from the material, for example in a cleaning process such as washing. An impurity can also be understood as meaning such dissolved textile constituents as textile dyestuffs.

Under a textile in particular garments, curtains or bedding are understood. Garments and bedding include, for example, shirts, T shirts, dresses, jackets, Sweaters, pants, blankets, covers and covers. The textiles can be different

Materials include, for example, natural fibers, chemical fibers or other materials such as leather. One type of material of the textile can be, for example, the yarn of the textiles. Occasionally, for example, a textile which consists of yarn as a material, ennobled. In this case, a chemical modification of the yarn takes place, for example, to make the textile more durable or the like. Such refined materials of textiles are also referred to as treated fibers.

A property of the impurity is understood in particular to be the color of the impurity, the color of the impurity in particular according to the principle of

Detachierens is determined. In this case, for example, based on the property of the color of an impurity on the cause of the contamination can be concluded, so that the probability of being able to remove the impurity by means of a suitable treatment again increased. For example, impurities can be assigned to certain colors, such as. B. red impurities (eg berries, lipstick, red wine, make-up,

Candle wax or the like), green impurities (e.g., grass, verdigris, mildew, spinach, or the like), blue impurities (eg, ballpoint pen, stamp ink, ink, or the like), yellow and brown impurities (e.g., coffee , Feces, rust, tobacco, tea, fruit, or the like), as well as gray and black impurities (eg, graphite, iodine, carbon, oil, soot, dope, shoe polish, or the like), to some non-limiting examples call.

The detection of the first image information can be done for example by means of one or more optical sensor elements, such. B. by means of a camera.

The outline of the contamination is understood to mean, in particular, the curve which delimits the contamination from its surroundings-the part of the textile not surrounding it with the contamination and the contamination. In particular, the outline designates the outer line of lines surrounding the contaminant, thereby lifting the contaminant from the fabric.

By determining the contaminant information based at least in part on a first property, e.g. For example, the color of the contaminant, and based at least in part on a second property, the outline of the contaminant, a much more accurate determination of the contamination can take place. If the outline shows, for example, that there is an elongated contamination, a z. For example, contamination caused by spinach is usually indicative because the outline is indicative of, for example, a pulling motion while causing the Pollution is. Thus, for example, contamination information indicative of grass-caused contamination may be determined, although it may be indicative of e.g. B. in grass and spinach are each about green impurities. The contaminant information may include, for example, a composition of the contaminant of the textile.

For example, by outputting or triggering the emission information, the user may be provided with information on the composition of the contamination of the fabric, which advantageously contributes to the identification of the contaminant. The user can, for example, information about the chemical

Composition or via the occurrence of individual elements or compounds. In particular, by a classification, further information can be provided with the at least one output variable, for example, whether the contaminant contains contents of specific organic or inorganic components, such as dyes or lipids, polysaccharides or proteins and, optionally, which origin has the impurity. For example, the contaminant information may be to the user

Provide information about a possible hygienic concern of the contamination.

In one embodiment of the method according to the first aspect, one or more of the following parameters i) to iv) may determine the property dependent on the contour of the contaminant:

i) form of contamination;

ii) structure of the impurity;

iii) size of the contaminant;

iv) Contour of contamination.

For example, the shape of the contamination can be indicative of the external shape of the

Pollution. In particular, the shape of the contaminant may be indicative of the external appearance of the contaminant in its entirety. For example, the shape of the contaminant may be indicative of an annular outer shape, a frayed outer shape or a striped outer shape of the contaminant, to name a few non-limiting examples.

For example, the structure of the contaminant may be indicative of the surface of the

Contamination, such as a relief-like surface. For example, the structure of the contaminant may be indicative of a substantially solid or substantially liquid contaminant. For example, the structure of the surface is an impurity caused by a lipstick substantially thick on the textile and of firm structure. In contrast, the structure of the surface of an impurity caused by z. B. Blood applied substantially thin on the textile.

For example, the size of the contaminant is indicative of the size of the contaminant relative to the size of the fabric.

For example, the contour of the contaminant is indicative of a uniformity of the contour line from the contaminant, such as the contamination. As a smooth or frayed contour line, or even if more (at least two) contour line are covered by the contamination. A contour line is understood in particular to be that line through which the contamination is limited.

In an exemplary embodiment of the method according to the first aspect, the at least one property of the contamination of the textile is determined at least in part based on a property dependent on the color of the contaminant.

In a further exemplary embodiment of the method according to the first aspect, one or more of the following parameters v) to x) may determine the property dependent on the contour of the contamination.

v) isotropy of the contaminant;

vi) three-dimensionality of pollution;

vii) color design of the impurity;

viii) color and / or color intensity homogeneity of the contaminant;

ix) transparency of pollution;

x) gloss of the impurity.

For example, the isotropy of the contaminant is indicative of impurity independence from a direction that can be recognized by causing contamination as a property of the contaminant. For example, the contaminant may be evenly colored over its entire area. In this case, the contamination is, for example, independent of one direction. If, for example, a gradient from a darker coloration of the impurity towards a lighter coloration of

Contamination, this course can be detected as a direction of pollution. The direction independence of an impurity is also to be detected, for example, as a homogeneous structure of the impurity. The opposite, for example, may be anisotropy of the contaminant.

For example, the three-dimensionality of the contamination is indicative of a thickness of the

Pollution. For example, the three-dimensionality of the contaminant is indicative of a thickness of the contaminant in the ratio of one part (eg, the center) of the contaminant to the contour line of the contaminant. As already stated, impurities arranged on a textile can differ significantly from each other in their applied thicknesses.

For example, the color design of the contaminant may be indicative of a contaminant composition. For example, it can be detected on the basis of the color design of the contaminant, whether or not the contaminant is composed of one or more substances.

Color homogeneity, such as an is, however, for example, a color gradient from a darker coloration of the impurity towards a lighter coloration of

Pollution. The color intensity homogeneity is representative of, for example, saturation of the contaminant, and / or a different intensity of the color of the contaminant in different parts of the contaminant, such as, e.g. For example, a difference in the intensity of the color of the contaminant between the center of the contaminant and the contour line of the contaminant.

For example, the transparency of the contaminant is indicative of a colorless contaminant.

For example, the gloss of the contaminant is due to the surface of a fabric being so smooth that pits are smaller than the wavelength of visible light. For example, the gloss of the contaminant is indicative of a greasy contaminant. Gloss is also referred to as greasy, such as the gloss of greasy stains. For example, it can also be detected whether a dullness of the impurity is present, in contrast to a gloss of the impurity.

In an exemplary embodiment, the method according to the first aspect further comprises:

Determining at least one cleaning strategy parameter of the fabric based at least in part on the determined contaminant information. In a further exemplary embodiment, the method according to the first aspect further comprises:

Performing or prompting the implementation of a treatment of the textile according to the at least one determined cleaning strategy parameter via at least one treatment device, in particular a cleaning device.

In particular, the purification strategy parameter is a recommendation for a specific treatment adapted to the contaminant. For example, a particularly gentle treatment of the textile can be in the foreground, so that the at least one

Cleaning strategy parameters ensures the highest possible longevity of the textile.

Likewise, a particularly intensive treatment of the textile may be desired, wherein the at least one cleaning strategy parameter is optimized with regard to the effect of the treatment of the specific structure, for example the effectiveness of a cleaning process. Also, a recommendation about a particularly energy-saving treatment can be represented by the at least one purification strategy parameter. Further, the combination of contaminant and fabric may be taken into account in determining the cleaning strategy parameter so that, for example, the contaminant may be removed from the fabric as efficiently as possible.

By determining the at least one cleaning strategy parameter based on the contaminant information, for example, the material wear in the treatment of the textile can be adjusted according to the material wear, in order to curb further increased material wear or, for example, to replace the pills

Restore the appearance of the textile. The user can thus be given a recommendation about an optimum cleaning process with regard to the impurity present.

For contamination, a conclusion can be drawn about the cleaning strategy parameter via the contamination information. In this case, the cleaning strategy parameter can be determined indirectly from a further output variable, for example, an initial variable representative of the composition of the impurity is first determined, and the purification strategy parameter is determined from this initial variable representative of the composition of the impurity. The cleaning strategy parameter can also be determined directly from the contamination information, for example by means of a classification via deposited contamination information. This evaluation can be carried out for example by means of a neural network, which is described in more detail below. In particular, if a user of the textile can not identify the contaminant with the eye and it is therefore unclear how to remove the contaminant again, the method according to the first aspect or the device according to the second aspect can provide a recommendation for an optimal purification strategy as cleaning strategy parameters for the treatment of the textile. For example, it may be unclear to the user whether an impurity contains lipids or certain dyes that can not be reliably removed by commonly used cleaning strategies. Additionally or alternatively, properties of the textile can also be taken into account. The cleaning strategy parameters, which are dependent on the composition of the impurity and determined as part of the method, can be taken with the identification of corresponding ingredients of the impurity and / or a property of the textile recommendation via a cleaning strategy adapted to the individual composition. As a result, the removal of the contaminant can be greatly simplified and made much more reliable.

It is likewise conceivable that contaminants from the material of the textile, such as unfixed textile dyes, are detected via the contaminant information. This happens in particular during the execution of a treatment, so that the user is given a conclusion on the effectiveness of the treatment of the textile.

For example, the user can recognize whether an excessive amount of textile dyes dissolves from the material of the textile, whereby the user receives an inspiration, the

To change cleaning strategy and, if necessary, to make it more gentle with regard to the textile dye. Likewise, a decolorization of a textile can be intended and a conclusion about the degree of decolorization can be drawn on the at least one initial size by a cleaning strategy.

An exemplary embodiment provides that the particular purification strategy parameter represents one or more of the following parameters a) to g):

a) type of detergent;

b) amount of detergent;

c) purification temperature;

d) type of cleaning device;

e) one or more settings of the cleaning device;

f) recommendation of pretreatment of the contaminant;

g) Recommendation to carry out a special treatment. In particular, the cleaning strategy parameter is indicative of a detergent type, a detergent amount, a cleaning temperature, a cleaning device type, one or more settings of the cleaning device, recommendation of a pre-treatment of the impurity, recommendation of performing a special treatment, or a combination thereof.

Detergents are used for example in the household for the cleaning of different objects. For example, for washing machines, a cleaning agent, for example a detergent, is used for cleaning textiles. However, a cleaning agent should also be understood as meaning also cleaning auxiliaries or cleaning auxiliaries, for example a bleaching additive, a fabric softener or laundry starch. A cleaning agent can also be a liquid, a dispersed system, for example a gel or foam, or a solid, in particular a tab, powder or granules.

A cleaning agent may, for example, one or more components from the group of components comprising surfactants, alkalis, builders, grayness inhibitors, optical brighteners, enzymes, bleach, soil release polymers, fillers, plasticizers, perfumes, dyes, conditioners, acids, starch, isomalt , Sugar, cellulose, cellulose derivatives,

Carboxymethylcellulose, polyetherimide, silicone derivatives and / or polymethylimines.

A cleaning agent may further comprise one or more other ingredients. These ingredients include, but are not limited to, the group consisting of

Bleach activators, complexing agents, builders, electrolytes, nonaqueous solvents, pH adjusters, perfume carriers, fluorescers, hydrotropes, silicone oils, bentonites, antiredeposition agents, anti-shrinkage agents, wrinkle inhibitors, dye transfer inhibitors, antimicrobial agents, germicides, fungicides, antioxidants, preservatives, corrosion inhibitors, antistatic agents, bitterness agents , Ironing aids, repellents or impregnating agents, swelling or slipping agents and / or UV absorbers.

The purification strategy parameter may represent the type of detergent and thus be indicative of the composition of the detergent. For example, if some level of colorant is included in the contaminant composition, the use of certain bleach additives may be recommended to the user. For example, if certain levels of lipids are present in the composition of the contaminant, the

Use of specific surfactants and / or lipases may be included in the recommended cleaning strategy. The purification strategy parameter may represent the amount of detergent and, in particular, may indicate an absolute amount of the detergent. Likewise, a relative amount of the cleaning agent can be indicated by means of the cleaning strategy parameter, for example based on the mass of the textiles to be cleaned or a liquor ratio or amount of detergent based on a volume of water to be used for cleaning. By means of the intensity information dependent on the composition of the impurity, a type of cleaning agent and / or a quantity of cleaning agent can thus be determined which ensures optimum removal of the impurity.

With a cleaning strategy parameter representative of the cleaning temperature, an optimum contaminant removal temperature for the particular contaminant composition can be given, especially in combination with a detergent type. On the one hand, the cleaning temperature may be high enough to ensure complete removal of the contaminant and, on the other hand, with regard to the

Energy consumption and a conservation of the textile are kept low.

As a result, with the cleaning strategy parameter, the removal of the contaminant can be greatly facilitated to the user. In particular, in the case of impurities which can not be identified with the eye, the process makes it possible to optimize the cleaning, but also the energy consumption and the protection of the material of the textile

Cleaning strategy recommended. For example, the recommendation of the

Detergent type and the settings of the cleaning device, whether the intensity information indicates a certain content of lipids in the contaminant and therefore corresponding fat-dissolving components should be included in the cleaning agent or whether certain dyes are present in the contaminant, which on a specific cleaning agent and

Settings of the cleaning device can be specifically attacked.

In an exemplary embodiment according to the first aspect, the method further comprises:

Performing or causing the treatment to be performed based at least in part on the cleaning strategy parameter by means of a cleaning device.

A cleaning device is understood in particular to mean a washing machine, in particular an automatic household washing machine. This can be a

Cleaning strategy parameters indicate a particular type of such cleaning device. It is also conceivable that the cleaning strategy parameters are at least partially manual pretend cleaning strategies, such as a hand wash. Also, the

Cleaning strategy parameters include settings of a cleaning device,

for example, a program of an automatic household washing machine or a sequence of such programs.

By recommendation of carrying out a special treatment, it is understood, inter alia, that it is recommended to have the contamination removed by cleaning or laundry using non-household methods (for example, with suitable detangling agents) in a tissue-friendly manner.

The cleaning strategy parameter may, for example, be a treatment of the textile

represent. As a treatment, for example, a pretreatment of the contamination of the textile and / or the textile may include. For example, this may be a pre-cleaning, a

Application of pretreatment or a particular arrangement of the textile include. For example, the cleaning strategy parameter indicates a pre-wash or pre-wash, in particular soaking of the fabric in a particular solution or

Pre-cleaning program of a cleaning device. Various pretreatment agents may be provided for manual or automatic application, for example, the application of a spotting agent or a bleaching agent is indicated. Furthermore, an arrangement of the textile can be given in particular in that the textile should be turned "on the left" before the actual treatment or arranged in another device, for example in a laundry bag the user will receive an indication of closure of a zipper for subsequent treatment.

As a treatment of the textile, for example, it may also be provided that the textile is dyed or subjected to a gentle treatment. In an advantageous embodiment of the method according to the first aspect, the treatment comprises a cleaning treatment, in particular a washing treatment carried out on a cleaning apparatus,

for example, a washing machine.

In particular, the method further comprises performing the treatment by means of a cleaning device.

Here, for example, the contamination information before, and another

Contamination information during and / or after performing the treatment of the textile be determined. With a determination prior to cleaning, for example, a recommendation about the cleaning strategy to be used can be given to the user before a cleaning treatment to be carried out.

For example, in determining contaminant information during cleaning, cleaning may be performed dynamically, i. a cleaning device may adapt to the just determined (sometimes altered) contaminant information during cleaning, in particular by continuously determining the output quantity. For example, during the washing program, a washing machine adjusts, for example, the temperature or the amount of detergent corresponding to the particular impurity information. In this case, in particular, the contamination information of detached from the textile

Textile ingredients such as textile dyes are obtained.

By determining the contamination information after cleaning, for example, the result or the effectiveness of a treatment can be recorded and checked.

The contaminant information and / or the cleaning strategy parameter can be output to the user on a display or a corresponding output can be triggered. The user can then perform the treatment of the textile. Alternatively or additionally, in one embodiment of the method, the contamination information and / or the cleaning strategy parameters can be output to a cleaning device. For example, the contaminant information and / or the cleaning strategy parameter may be applied to the

Be discharged cleaning device, so that the cleaning device, for example, the corresponding treatment by default and takes over the user

Just need to start cleaning device. It is also conceivable that the

Cleaning device with the issue of impurity information and / or the

Cleaning strategy parameter which performs treatment automatically. For example, the cleaning device may have a detergent dosing device to automatically provide the detergent type and detergent amount according to the recommended treatment of the textile. As a result, the usability of the method is improved.

According to an exemplary embodiment according to the first aspect, the method further comprises:

Determining property information of the textile, wherein the property information of the textile is indicative of at least one property of the textile, wherein the at least one cleaning strategy parameter is determined based at least in part on the determined property information.

A further embodiment according to the first aspect provides that the at least one

Property of textile indicative of material structure, material type, material distribution,

Material wear of the textile, color of the fabric of the textile, shape of the fabric of the textile, or a combination thereof.

For example, determining the feature information may be performed based at least in part on the acquired first image information in the event that at least a portion of the captured first image information is indicative of at least a portion of the textile. As a rule, the detected first image information also represents at least part of the textile in addition to the contamination and thus can be used directly for determining the property information of the textile. Alternatively or additionally, a third image information can be detected, wherein the determination of the property information can be performed at least partially based on this third image information. The third image information is indicative of, for example, at least part of the textile. The acquisition of the third image information can be done for example by means of one or more optical sensor elements, such. B. by means of a camera.

In one embodiment of the method according to the first aspect, for example, for detecting at least a part of the textile, the material structure, the type of material, the

Material distribution, the material wear of the textile, the color of the fabric of the textile, the shape of the fabric of the textile, or a combination thereof are detected.

The material structure of at least one part of the textile is understood in particular to be the type and / or shape of a woven fabric, a knit fabric or nonwoven fabric or batt. For example, the intensity information may be characteristic of the type of fiber entanglement, such as that produced by weaving, knitting, or knitting, or characteristic of a nonwoven fabric. An entanglement pattern or a

Fadenverkreuzungsmuster and a thread binding can be represented here by the intensity information. Thread density, fiber strength, fiber length, fiber fineness and / or

Fiber orientation can be detected in particular in the intensity information. The

Material structure of at least part of the textile has a direct impact on the

Requirements for the treatment of the textile, for example, a Vliessstoff other

Requirements for a cleaning treatment pose as a knitted or woven structure. The type of material is understood in particular to mean the composition of at least part of the material of the textile. For example, the intensity information is indicative of natural fibers, chemical fibers, natural materials such as wool or leather in the textile, coating of the fibers, textile finishing. The type of material also has a significant influence on an optimal treatment of the textile, ironing strength or soil release polymers, for example a

Cleaning treatment or ironing.

With the material distribution of the textile can be detected, for example, whether the textile has a mixed fabric of different fiber types or fiber materials and / or whether parts of the fabric are made of a different material. Here, the ratio of the different materials to each other, for example, a density ratio, mass ratio or area ratio can be detected. Further represented by the intensity information may be the type and number of joints, for example, seams, welds or splices.

With the property information of the textile representative of the wear of the material, in particular it can be stated whether there are pills, cracks, holes, wear or other structural damage to the textile. In particular, for pills, which arise by dissolving fibers from the textile composite and occur in the form of knots on the textile surface, the type, shape, size or height, number and / or distribution of

Material wear are detected.

In a further embodiment of the method according to the first aspect, the

Property information of the textile, for example, be representative of the presence and / or type of closure means, of coating material and / or of applications in, on and / or on the at least one part of the textile.

Zippers on the fabric are understood in particular zippers, hook-and-loop fasteners, buttons or similar arrangements, which are in particular adapted to produce a connection of parts of the textile over a positive connection and which can be made detachable.

The at least one part of the textile can have one or more coating materials, in particular the fibers are coated or a coating is applied to the structure of the material of the textile, for example on the fabric. The coating can, for example be a functional layer such as a protective layer, sealing layer, finishing layer of the textile or change the look or feel of the textile. In particular, the protective layer or the sealing view can be arranged as an additional layer on the finishing layer of the textile.

Textiles, in particular garments, may further comprise applications such as imprints, sequins, lace, patches or the like, which may also be represented by the intensity information. Likewise, functional textiles may have functional elements as applications or electronic elements may be arranged in the textile or on the surface of the textile.

If at least a part of the property information of the textile represents such closure means, coatings and / or applications on the textile, consideration can also be given to the protection of the corresponding elements during treatment. On the one hand, a wear of such closure means, coatings and / or applications can be reduced in a treatment and on the other hand, for example, a detachment of coatings or

Applications are avoided.

In an exemplary embodiment of the method according to the first aspect, the at least one cleaning strategy parameter is determined by means of a neural network, in particular an artificial neural network, wherein in a first step at least partially based on the determined contaminant information or at least partially based on the determined contaminant information and the classification of the contaminant takes place in accordance with certain property information of the textile, and in a second step of the

Cleaning strategy parameters based at least in part on the classification of

Pollution is derived.

The neural network can be, for example, an artificial system (for example a device according to the second aspect or a system according to the third aspect) that learns, for example, from training cases as examples and can generalize them after completion of the learning phase. That is, the examples are not simply learned by heart, but patterns and laws are identified in the learning data. For this purpose, different approaches can be followed. For example, supervised learning, partially supervised learning, unsupervised learning, empowered learning, and / or active learning can be used. Monitored learning can be done, for example, by means of an artificial neural network (such as a recurrent neural network) or by means of a support vector machine. An unsupervised learning, for example, by means of an artificial neural network

(For example, a car encoder) take place. As a learning data then serve, for example in particular the repeatedly obtained and / or determined intensity information or the specific output variables.

Alternatively or additionally, it is conceivable that the detected first image information or the detected first image information and a detected second image information or the specific

Impurity information associated with other information, such as the number and / or age of persons of a household to create a personal pollution profile or, for example, with the season for the creation of a seasonal pollution profile.

It is also possible that the repeated receipt and / or detection of the first

Image information or the first image information and a second image information or impurity information for machine learning is used. That's how it works

For example, contaminant profiles may be determined based at least in part on machine learning.

Through these measures, the reliability of determining the

Contamination information and in particular the treatment of the textile, in particular for the removal of the contamination from the textile, increased.

Each of the training cases, for example, by an input vector, image information, z. Example, the first image information or the first image information and a second image information, and an output vector of the artificial neural network be given. The starting vector is given, for example, by substance concentrations determined by means of a chemical analysis within this contamination of a textile belonging to the training case and / or a part of the textile.

For example, each test case may be generated by placing the contamination of a fabric and / or part of a fabric associated with the training case in a predetermined state (e.g., defined impurity on defined textile), followed by a

Contamination information is generated representative of an impurity, as well as a chemical analysis to measure the concentration of the substance (eg, the contamination on the textile and / or the textile) is performed simultaneously. The determined contaminant information is transmitted, for example, as an input vector, the substance concentration as the output vector of the training case. By means of a neural network, for example, the calibration can be done. In this case, for example, an error feedback in the neural network, a so-called back propagation done. In this case, for example, the parameters used to determine the contamination information which the neural network uses are optimized. With the optimized

For example, the neural network is adapted from input vectors (first image information for at least one contaminant on a textile, or first image information for at least one contaminant on a textile and second image information indicative of at least the contamination on the textile from the opposite side of the textile as the first image information), which differ from the originally learned input vectors of the training cases, meaningful to determine output vectors (output, in particular for the determination of contamination information). Accordingly, for example, the parameters are adaptive so that calibration can be done using the already known (e.g., stored in a database) parameters.

In an exemplary embodiment it is provided that e.g. by means of a

Image processing unit is detected in a detected first image information and / or second image information contamination of a textile and / or at least a part of a structure of a textile, in particular a stain or stain and a textile type, and from those parts of the detected information that the contamination are associated with the textile and / or the at least one part of the textile, a plurality of input vectors is formed. In this case, for example, an input vector of the neural network can be formed from each of the pixels associated with this contamination of the textile and / or the pixel assigned to the at least one part of the textile (for example a pixel which is included in the intensity information). Here are the

Components of such an input vector given by the intensity values of each pixel represented by the respective image information. Further, chemical analysis may be carried out, for example, with regard to the contamination of the textile and / or the at least part of the textile. The associated result can, for example, form the output vector. Subsequently, for example, the neural network may combine each of the input vectors with the output vector. In this way, a multiplicity of training cases can be generated from the contamination of the textile and / or the at least one part of the textile (for example a training case in particular for each detected pixel of the intensity information).

In an exemplary embodiment, at least one pixel within the acquired first image information and / or second image information is used as a fixed reference pixel for a spectral exposure correction of the image, image data of pixels of the image Image, which are different from the at least one reference pixel, are normalized using image data of the at least one reference pixel.

An exemplary embodiment provides that the neural network has a spectral

Exposure correction of the detected first and / or second image information performs. For example, a current exposure condition of the contaminant of the textile and / or the at least a portion of the fabric may be detected (e.g., measured) and offset by normalizing the pixels of the first and / or second image information at nearly the same time. Due to the spectral exposure compensation is in addition to the

Exposure intensity of individual pixels of the spectral image and the spectral

The composition of the information (e.g., image data) of these pixels is normalized.

The exposure conditions are usually determined by incident light and the angle of incidence of the light on the contamination of the textile and / or the at least part of the structure of the textile.

In the spectral exposure correction it can be provided, for example, that within the image area covered by the intensity information with the contamination of the textile and / or the at least one part of the textile, a body is detected whose surface has, for example, predetermined, in particular optical properties. For example, one of the properties may be a certain color or gray-shade and / or brightness.

For example, this body is formed flat. For example, this body is fixedly connected to a treatment device, in particular a cleaning device (e.g., a washing machine), and / or is a direct part of its surface (e.g., a paint finish). In the event that the image information that made up that of the intensity information

Spectral image is reconstructed, is detected by an optical element, for example, the body may always be arranged in a same position relative to the optical element, so that the body is always included in the same image area of the captured image information.

In an example embodiment, at least one predetermined pixel (also referred to as reference pixel) of the acquired image information may be used for the spectral exposure correction. The reference pixel of the acquired image information is, for example, on the body with predetermined surface properties. Based on the reference pixel, for example, the remaining captured pixels of the image information can be normalized. To avoid unnecessary computation, for example, only those pixels normalized, which include the contamination of the textile and / or the at least part of the structure of the textile.

In an exemplary embodiment, the spectral exposure correction may be performed by the neural network. For example, it can be provided that a layer of the neural network performs the spectral exposure correction. The spectral

Exposure compensation can also be carried out, for example, at regular intervals, in particular automatically. Time-varying exposure conditions can be normalized in a timely manner ('real-time'). In the case that an optical element is used for detecting the image information which is not fixedly arranged, as is the case for example with an electronic device (eg a smartphone, tablet or the like), the exposure conditions can be determined by a movement of the optical sensor change the captured image information. Accordingly, it can be compensated by a performed at regular time intervals spectral exposure correction these different exposure conditions.

In an exemplary embodiment of the method according to the first aspect, the image information is detected by one or more sensors, in particular by one or more optical sensor elements.

The one or more optical sensor elements may be formed, for example, as one of the following means:

(i) camera, in particular a 3D camera or hyperspectral camera;

(ii) LED sensor element (eg photodiode);

(iii) NIR (near infrared) sensor element.

In this case, an optical sensor element or an optical sensor is understood as meaning sensors which can determine an intensity of incident radiation, in particular electromagnetic radiation in the visible range and alternatively or additionally beyond. In particular, the optical sensor element is adapted to provide an energy resolution and / or spatial resolution of the intensity information. The optical sensor element may comprise an image sensor, in particular a digital image sensor. To determine the intensity of the radiation, in particular at least one semiconductor element, diodes, CCD elements, for example a Bayer sensor, or CMOS elements, for example a sensor of the Foveon X3 type, can be used. The optical sensor element may be optical filters and

in particular a spectrometer. Also conceivable is the use of monochrome sensors without color resolution. Similarly, sensors can be used which are limited to certain wavelength ranges. By way of example, the optical sensor can be based on at least one photodiode and / or at least one LED sensor element. Individual elements or arrays of elements, such as photodiodes or photosensitive devices such as LEDs, may be used. It may be advantageous to optimize the size of the individual sensor elements, for example the individual photodiodes, in terms of dynamics, resolution and / or sensitivity.

In one embodiment, the optical sensor element provides a three-dimensional spatial resolution. With a three-dimensional spatial resolution, the accuracy of determining the contamination information may be further increased based at least in part on the acquired first image information or the acquired first image information and the acquired second image information and / or detected information from at least a part of the textile. It is conceivable to use several images from different perspectives on the same optical sensor element or the same sensor arrangement. Likewise, optical elements designed specifically for a three-dimensional resolution, such as attachment lenses or lenses, or a 3D camera can be used.

Additional optical elements, for example add-on lenses or lenses, can also be arranged on conventional, essentially two-dimensional optical sensors, for example digital cameras or cameras integrated in mobile devices. This also existing devices for a three-dimensional resolution can be retrofitted (retrofitting). With the three-dimensional resolution, for example, textile structure,

For example, the shape and arrangement of the fabric, stitches or nonwoven fabric, and / or the shape and location of a contaminant (e.g., within) the fabric may be further determined and thus more comprehensive and accurate intensity information obtained.

In a particularly simple embodiment, the at least one optical sensor element comprises at least one camera-like element and provides an image information. Accordingly, digital cameras or cameras integrated into electronic (e.g., mobile) devices may be used for the method, or as at least one device for performing the method. In this case, essays for a three-dimensional spatial resolution can be used on the camera-like element.

In one embodiment, the one or more sensors are designed as hyperspectral camera. Such cameras scan an area over a plurality of channels Wavelengths, e.g. B. from 400 to 1000 nanometers and capture based on image information. Furthermore, hyperspectral cameras can additionally scan the infrared range with wavelengths of 1000 to 2500 nanometers. Thus, hyperspectral cameras not only scan the visible range of light but also an area far beyond. As a result, such cameras provide a spectral image by which certain impurities can be detected. From this information can then be a possible

Derive treatment of the contamination of the textile.

For example, the one or more sensors include at least one CMOS element having a maximum sensitivity in the near infrared (NIR) range. This will be in

Also referred to below as the NIR sensor element. In this case, illumination with radiation in the NIR range is advantageous. Below the NIR range is a wavelength range of

Electromagnetic spectrum of at least 750 nm, in particular to a maximum of 2000 nm, in particular of at least 800 nm to a maximum of 1400 nm understood. Hereby, an image information is detected.

The one or more optical sensor elements may, for example, as image information, capture a photograph, a spectral image, a fluorescence spectral image, a differential spectral, a change of response, to name a few non-limiting examples.

In an exemplary embodiment of the method according to the first aspect, the method further comprises:

Detecting second image information indicative of at least the contamination on the textile, wherein the second image information relative to the first image information detects the opposite side of the contaminant, wherein

the at least one property is determined based at least in part on the acquired first and second image information,

Accordingly, for example, the front and the back of the contaminant on the textile are detected by means of the image information. At least partially based on this, for example, the contaminant information is determined.

In an exemplary embodiment of the method according to the first aspect, the determination of the contamination information comprises a comparison of the detected first

Image information or the acquired first and second image information with comparison values. For example, sometimes differences in contamination between the front and back of the fabric may be detected. For example, a contamination of red wine spreads evenly through the textile and is accordingly homogeneous to recognize both on the front and on the back of the textile. This may be determined in determining contaminant information based at least in part on the acquired first and second image information. On the other hand, an impurity, for. B. caused by lipstick on the front of the textile on which the impurity was applied to the textile, represent much more significant than on the back, since the

Contamination diffused not so strong through the fabric. Detecting occasional differences between the side of the textile to which the contaminant has been applied in causing it and the opposite side of the contaminant can be done, for example, with the neural network.

Accordingly, an exemplary embodiment provides that the determination of the

Contamination information comprises a comparison of the detected first image information or the detected first and the acquired second image information with comparison values.

For example, the comparison can be made with comparison values. Corresponding comparison values can be stored in a database. The acquired first image information or the acquired first and the acquired second image information may be subjected to a classification, for example, wherein the contamination information is obtained or influenced by a result of the classification. For example, a classification may be based on a comparison of the acquired first image information or the acquired first and the detected second

Image information is based on a database of already known image information associated, for example, with a specific contaminant. A corresponding classification can be done, for example, additionally or alternatively with the neural network. In particular, a neural network as described in this specification can be used here.

The comparison values or a database provided for this purpose can in particular

Contain contamination information of typical, occurring in the fields of application of textiles impurities. These can be represented, for example, by the training cases. These can then be used by the neural network to determine a

Contamination information can be used. For example, in the household sector, contamination information may be from typical contaminants such as various

Food remnants, traces of drinks, grass or colors are used. The Contaminant information of the database may be associated with certain other information, for example at least one contaminant removal information.

For example, should the particular contaminant information not be unique

For example, an input of information of a user may be detected, wherein the input of the user is indicative of a specification of the contaminant.

For example, one or more such input of the user can be detected, if that makes sense. This can be done in the context of an interaction with the user, if z. B. after a first input of information of the user no clear result of contamination can be determined. For example, the user may be asked where in his opinion the contamination came from. For example, the location and / or location (eg, whether the

Indoor or outdoor pollution, eg. B. in the garden) has its origin. For example, by the user a decisive hint by entering the

Information to be able to determine the contamination information can.

In an exemplary embodiment of the method according to the first aspect, the method further comprises the following method steps:

Detecting at least one voice command indicative of at least one parameter based on which the contaminant information is determined.

The voice command may be input, for example, by a user, e.g. Via a voice communication interface (e.g., an electronic device including a microphone or the like). The entered voice command can, for example, locally by the

Speech communication interface or processed by a server. to

Processing by a server, the voice command can be transmitted, for example, after input via a communication link of the electronic device to a server. By means of speech recognition software (e.g., Apple Siri or Amazon Echo), the

entered voice command, for example, processed. This may require the installation of additional software. For example, a voice command processed in this way may be converted into control information that may be used by the device, e.g. B. an electronic device and / or another electronic device (eg., A cleaning device), for example, evaluate, process, forward, or otherwise use. For example, appropriate control information may be taken into account in determining the contaminant information. In one exemplary embodiment of the invention in all aspects, status information is obtained (eg, determined). The status information can be output, for example, or its output can be initiated.

For example, in a system, for example, each cleaning device may have status information via a wireless communication interface (eg, WLAN, WAN, Zigbee, Bluetooth, to name but a few examples). For example, the status information may be based on a query to a centrally installed home appliance

Controller (eg a desktop computer, a central control unit, a server, a home automation system), and / or a (eg mobile) smart device (eg a smartphone, a tablet, a smartwatch, to give a few examples). The status information can be output, for. B. a user can be displayed on a display device of the smart device.

For example, the status information may be indicative of a cleanup and / or care action. Alternatively, or additionally, the status information may be indicative of progress, abort, completion, startup, or another status of a cleanup operation. Alternatively or additionally, the status information can be indicative of properties of the contaminant and / or the structure of the textile.

According to the second aspect of the invention, an alternative device is also described, comprising at least one processor and at least one memory

Computer program code, wherein the at least one memory and the computer program code are configured to execute and / or control at least one method according to the first aspect with the at least one processor. For example, a processor is understood to mean a controller, a microprocessor, a microcontroller such as a microcontroller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), or a field programmable gate array (FPGA).

For example, an exemplary apparatus further includes means for storing information such as program memory and / or main memory. For example, an exemplary inventive device further includes means for receiving and / or transmitting information over a network, such as a network interface. For example, exemplary devices of the invention are interconnected and / or connectable via one or more networks. An example device according to the second aspect is or includes a computing device that is software and / or hardware configured to perform the respective steps of an example method according to the second aspect. Examples of a data processing system are a computer, a desktop computer, a server, a thin client and / or a portable computer (mobile device), such as a laptop computer, a tablet computer, a wearable, a personal digital assistant or a smartphone ,

Individual method steps of the method according to the first aspect (for example, obtaining or determining an intensity information, determining the at least one

Output size) can in this case with a sensor device, which also has at least one sensor element, are performed. Likewise, individual method steps (for example, obtaining or determining intensity information, determining the at least one output variable) which, for example, do not necessarily coincide with the

Sensor device must be performed, be made by a further device, which is in particular via a communication system with the device, which has at least one sensor element, in communication.

Further devices may be provided, for example a server and / or for example a part or a component of a so-called computer cloud, which

Data processing resources dynamic for different users in one

Communication system provides. Under a computer cloud becomes in particular a

Data processing infrastructure as defined by the National Institute for Standards and Technology (NIST) for the English term "cloud computing". An example of a computer cloud is a Microsoft Windows Azure Platform.

According to the second aspect of the invention, there is also described a computer program comprising program instructions that cause a processor to execute and / or control a method according to the first aspect when the computer program is run on the processor. An exemplary program according to the invention may be stored in or on a computer-readable storage medium containing one or more programs.

According to the second aspect of the invention, there is also described a computer-readable storage medium containing a computer program according to the second aspect. One Computer-readable storage medium may be formed, for example, as a magnetic, electrical, electromagnetic, optical and / or other type of storage medium. Such a computer-readable storage medium is preferably representational (ie "touchable"), for example it is designed as a data carrier device Such a data carrier device is for example portable or permanently installed in a device

Data carrier devices are volatile or non-volatile random access memory (RAM) such as memory. NOR flash memory or with sequential access such as NAND flash memory and / or read only access (ROM) memory or read / write access. Computer readable, for example, should be understood that the storage medium from a computer or a

Data processing system (off) read and / or can be described, for example, by a processor.

According to a third aspect of the invention, there is also described a system comprising a plurality of devices, in particular a mobile device and a cleaning device, which together perform a method according to the first aspect.

An exemplary system according to the third aspect includes an example

Cleaning device and additionally another device, such as a mobile device or a server for performing an exemplary method according to the first aspect.

The exemplary embodiments of the present invention described above in this description are also to be understood as being disclosed in all combinations with one another.

In particular, exemplary embodiments are to be understood in terms of the different aspects disclosed.

In particular, by the preceding or following description of method steps according to preferred embodiments of a method and corresponding means for

Implementation of the method steps to be disclosed by preferred embodiments of a device. Likewise, by the disclosure of means of a device for carrying out a method step, the corresponding method step should also be disclosed.

Further advantageous exemplary embodiments of the invention can be found in the following detailed description of some exemplary embodiments of the present invention, in particular in conjunction with the figures. However, the figures should only serve the purpose of clarification, but not to determine the scope of the invention. The figures are not to scale and are intended merely to illustrate the general concept of the present invention Reflect the invention by way of example. In particular, features included in the figures should by no means be considered as a necessary part of the present invention.

The exemplary embodiments described above in this description are to be understood as disclosed in all combinations with each other. In particular, exemplary embodiments are to be understood in terms of the different aspects disclosed.

In particular, the preceding or following description of method steps according to preferred embodiments of a method also discloses corresponding means for carrying out the method steps by preferred embodiments of a device. Likewise, by the disclosure of means of a device for carrying out a method step, the corresponding method step should also be disclosed.

Further advantageous exemplary embodiments can be taken from the following detailed description of some exemplary embodiments, in particular in conjunction with the figures. However, the figures should only serve the purpose of clarification, but not to determine the scope. The figures are not to scale and are merely intended to exemplify the general concept. In particular, features included in the figures are by no means considered necessary components.

Brief description of the figures

In the drawing shows

Fig. 1a-c is a flowchart of an embodiment according to a method of the first aspect;

Fig. 2a first schematic representation of an impurity;

Fig. 2b second schematic representation of an impurity;

Fig. 3 is a schematic representation of an embodiment of a device according to the second aspect;

Fig. 4 is a block diagram of an embodiment of a device according to the

second aspect; and Fig. 5 different embodiments of a storage medium after the second

Aspect.

Detailed Description of Some Exemplary Embodiments of the Invention

FIGS. 1a to 1c each show a flow chart of an embodiment according to a method according to the first aspect. The respective flowcharts 100a, 100b and 100c may be executed and / or controlled, for example, by a device according to the second aspect of the invention, or by a system according to the third aspect of the invention. The device according to the second aspect of the invention, or one of the several devices of the system according to the third aspect of the invention, in particular at least one mobile device and a cleaning device, can each one, several or all of the in the

Execute and / or control flowcharts 100a, 100b and 100c.

The device according to the second aspect of the invention, or one of the several devices of the system according to the third aspect of the invention can be designed, for example, as a smartphone or smartwatch or another mobile terminal. Also conceivable is an add-on system, for example comprising one or more sensor elements for a device and / or permanently installed systems, wherein the add-on system can be coupled to the device and / or the permanently installed system, in particular via a (eg wireless and / or

wired) communication link can be coupled. Additionally or alternatively, the device may be designed as a cleaning device (eg a washing machine). The

Cleaning device, for example, the one or more sensor elements with which, for example, the first image information can be detected include. Further, the device according to the second aspect of the invention, or one of the several devices of the system according to the third aspect of the invention, may be formed as a smart pen, the smart pen comprising means for carrying out the method according to the first aspect of the invention or to control. The smart pen can be coupled, for example, with a cleaning device, z. Via a wired or wireless communication link. By way of example, it is also possible to include a power supply from the cleaning device, by means of which the smart-stylus can be supplied with electrical energy.

Means for carrying out the method according to the first aspect of the invention may for example also be included in a cleaning device, such as a cleaning robot, wherein the

Cleaning robot in particular at least one communication interface for communication with one or more other devices comprises. The device after the second Aspect of the invention, or one of the several devices of the system according to the third aspect of the invention, for example, a z. B. centrally installed in the household control, such as a home appliance control or the like.

In step 101a, a first image information is acquired. The first image information is indicative of at least one contaminant on a textile. Capturing the first

Image information can for example be done with one or more sensor elements (eg a camera). For example, a camera 308 of a mobile terminal 306 according to FIG. 3, or a camera 332 according to FIG. 3 arranged on it detecting device 330 or a camera (eg camera 326 of the cleaning device 320) included in a cleaning device 3) detects the contamination of the fabric (eg, contaminant 302 of the fabric 304 of Fig. 3). In the event that z. For example, if the lighting for capturing the first image information is insufficient (eg, in a darker laundry room), it may be in one

3) or a display device of the device (eg display device 312 according to FIG. 3) is used to detect the contamination on the textile before or during the detection of the first Illuminate picture information.

In step 102a, determination of contaminant information is indicative of at least one property of the contaminant on the fabric. The at least one property is determined based at least in part on the acquired first image information. The at least one property of the contamination of the textile is determined at least partially based on a property dependent on the contour of the contaminant. Accordingly, the first image information acquired in step 101a is representative of the entire contaminant, not just part of the contaminant. As usual

Impurities on textile occupy a significantly smaller area on the textile than the total area of the textile, it is usually no problem to detect the contamination in its entire size as the first image information.

For example, the detected contaminant information represents the composition of the contaminant, so that, for example, information stored in a database for

Removal of the contamination from the textile, for example, can be made available to a user. To do so, in step 103a, outputting or causing outputting of the determined contaminant information, e.g. To another device (eg, a server 316 of Fig. 3). At least in part, based on the contamination information, the further device may interrogate, for example, the aforementioned information. In an optional step 104, at least one determination is made

Cleaning strategy parameters based at least in part on the contaminant information determined in step 104a. The cleaning strategy parameter includes, for example, a type, amount or the like of a cleaning agent, which optimally for removing the

Contamination on the textile is suitable. Accordingly, in optional step 105a, a performance or cause of treatment of the fabric may be performed.

For example, if the contamination on the textile can not be determined unambiguously at least in part based on the acquired first image information, further steps for detecting (further) properties of the contamination can be carried out. Further exemplary details are described in connection with FIG. 1 b and FIG. 1 c.

In the event that the contamination on the textile can not be determined unambiguously, as is checked, for example, in step 106b, a capture of a second image information may take place in step 107b. For example, the second image information is acquired from the opposite side of the contaminant on the textile against the first image information.

Accordingly, for example, the front and the back of the contaminant on the textile are detected by the first and second image information. The at least one property of the contaminant is determined, for example, based at least in part on the detected first and the acquired second image information. The detection of the second image information may reveal another property associated with the contaminant on the textile, e.g. Whether or not the contaminant has spread through the fabric. For example, low viscosity substances are more prone to spreading in the fabric so that such contaminants are visible on both the front and back of the fabric. The acquisition of the second image information can be effected, for example, with one or more sensor elements (eg a camera). For example, a camera 308 of a mobile terminal 306 according to FIG. 3, or a camera 332 according to FIG. 3 arranged on the determination device 330 or a camera (eg camera 326 of the cleaning device 320) included in a cleaning device 3) detects the contamination of the fabric (eg, contaminant 302 of the fabric 304 of Fig. 3).

In step 108b, determination of the contaminant information is indicative of at least one property of the contaminant on the fabric, wherein the at least one Property is determined at least partially based on the detected first and second image information.

In the event that the contamination of the textile could already be unambiguously determined after determining the contamination information based at least in part on the detected first image information, the method ends.

FIG. 1 c shows a flow chart 100 c with which, for example, a further indication for unambiguous determination of the contamination of the textile can be detected and determined. The flowchart 100c may be executed and / or controlled, for example, following a completed flowchart 100a and / or a completed flowchart 100b.

In the event that the contamination on the textile can not be determined unambiguously, as is checked, for example, in step 109c, in step 1 1 1 c, a determination of a

Property information of the textile done. As a rule, property information of the textile can already be carried out at least partially based on the acquired first image information, since at least part of the textile (eg its structure) is regularly covered by the first

Image information is included in addition to the contamination on the textile.

If at least part of the textile is not included in the first image information, in the optional step 1 10c, third image information can be captured indicatively for at least part of the textile. The detection of the third image information can be effected, for example, with one or more sensor elements (eg a camera). For example, a camera 308 of a mobile terminal 306 according to FIG. 3, or a camera 332 according to FIG. 3 arranged on the determination device 330 or a camera (eg camera 326 of the cleaning device 320) included in a cleaning device 3) detects the contamination of the fabric (eg, contaminant 302 of the fabric 304 of Fig. 3).

In step 1 12c, determination of the contaminant information is indicative of at least one property of the contaminant on the fabric, wherein the at least one

Property is determined at least partially based on the detected first image information, or at least partially based on the first and second image information, or at least partially based on the first and the second and the third image information. In the event that the contamination of the textile could already be unambiguously determined after determining the contamination information based at least in part on the detected first image information, the method ends.

Fig. 2a shows a first schematic representation of an impurity. FIG. 2 a shows a schematic representation of a textile 202 with an impurity 204, which can be detected, for example, as first image information. In an exemplary embodiment, the image information by means of z. B. an evaluation be analyzed, the

Evaluation unit, for example, image algorithms used to detect properties of the contamination on the textile can.

The detected first image information may be, for example, a spectral image, the spectral image being in particular from the illumination of the surface of the contaminant 204a on the textile 202a with light, in particular by reflection and emission from the surface of the light

Contamination 204a and / or the textile 202a radiation goes out. These can be as

Reflection information is detected, e.g. by a physical measurement, in particular via one or more (optical) sensor elements. A detected first image information is for example representative of the spatial resolution of the spectral image, and in particular can be recorded via a multiplicity of sensor elements, for example pixels.

The contaminant 204a is a sharp edge contaminant shown schematically by the contour line of the contaminant 204a. The contaminant 204a also has leaking areas, such as may come from blood, beer or dairy products. On the basis of determining impurity information, wherein the aforementioned non-limiting examples of impurity are analyzed

according to the contamination (clearly) be determined.

FIG. 2b shows a second schematic representation of an impurity 204b on a textile 202b. In contrast to the contaminant 204a, the contaminant 204b does not have a sharp edge as well. Also, the area of the contaminant 204b is not homogeneous and a direction can be recognized by the structure of the contaminant, namely in the direction of the stripes shown. The directionally dependent impurity shown schematically in FIG. 2b may have been created, for example, by a movement. For example, it may be a grass patch, for example, in the context of a contact of the textile with a

Grass area has emerged. As already stated, further properties which depend, for example, on the contour of the impurity and / or on the color of the impurity can be determined dependent property are taken into account in order to be able to determine the contaminant information accordingly.

FIG. 3 shows an exemplary embodiment of a device 300 according to the second aspect or a system according to the third aspect. The device 300 is set up or comprises corresponding means for carrying out and / or controlling a method according to the first aspect.

In particular, the apparatus 300 facilitates determining impurity information (eg, identifying a composition of an impurity 302 on a fabric 304 and / or providing an identification regarding properties of the fabric 304). For example, based on the contaminant information or information, at least in part, a recommendation for treating the fabric 304 to remove the contaminant 302 from the fabric 304 may be given in the form of a cleaning strategy parameter.

With an electronic device, here a smartphone 306, first a first

Image information, e.g. Representative of an image resulting from the illuminated surface of the contaminant 302 on the textile 304. For this example, an optical

Sensor element 308 used, which may include, for example, a camera. In addition, a radiation source 310 is provided which serves to illuminate the surface of the contaminant 302 and / or the textile 304. The smartphone 306 also has a display element 312. The display element 312 can also be used for example to illuminate the surface of the contaminant 302 and / or the textile 304 and, accordingly, as a radiation source.

The detected first image information is obtained from a communication system 314. In connection with the communication system 314 is a determination device 316, z. As a server, which is adapted to determine from the first image information from the contaminant 302 at least one dependent contamination information. The determination device 316 may also comprise an evaluation unit (eg an artificial neural network). Alternatively or additionally, a dedicated evaluation unit may be used, which for example is in communication with the communication system 314. For example, the evaluation unit can determine an output variable on the basis of an adaptive evaluation algorithm, in particular by means of the neural network, in order to be able to unambiguously determine the contamination. The determination of the output of the neural network includes, for example, a comparison of the determined contamination information with comparison values. The comparison values are stored, for example, in a database 318, which is also in communication with the communication system 314. Specifically, the comparison values of the database 318 include contaminant information from previously (eg, typical household) and detected contaminants. These can be given as training cases by an input vector, an impurity information and an output vector and stored accordingly in the database. The training cases can be used, for example, by a neural network in order to be able to determine an output variable based at least partially on the basis of specific contamination information by the neural network, the output quantity being dependent on the contamination due to the contamination information. Furthermore, the database 318 contains data associated with the comparison values in the form of, for example

Treatment parameters with respect to a recommended for the corresponding contamination and optional properties of the textile, recommended treatment, on the basis of which, for example, a cleaning strategy parameters can be determined.

The cleaning strategy parameter includes, for example, a cleaning strategy as

Treatment of the textile, wherein a cleaning agent, a cleaning agent, a cleaning temperature, a cleaning device type and settings of a

Cleaning device 320 or the like, to name a few non-limiting examples. The cleaning strategy parameter may be displayed, for example, on the display element 312 of the smartphone 306 and thus made available to the user. The user will thus receive a recommendation about an optimal impurity 302

Treatment provided.

The cleaning device 320 is also in communication with the communication system 314, whereby the contamination information and / or optionally the cleaning strategy parameters can be output to the cleaning device 320. The cleaning device 320 has, for example, a display element 322, which in particular the

Contamination information and / or optionally display the cleaning strategy parameter. Furthermore, the cleaning device 320 has a dosing device 324 for cleaning agents. The dosing device 324 may in this case a cleaning agent according to the

Provide treatment parameters relating to the type of detergent and / or the amount of detergent or check whether the cleaning agent was introduced into the dosing device 324 in accordance with the recommended treatment of the textile 304. Furthermore, the cleaning device 320 has a camera 326, by means of which z. B. the first image information is detected. The cleaning device 320 may further include a control (not shown) for controlling the cleaning device 320 by a user. For example, the cleaning device 320 may be preset according to the cleaning strategy parameter. The user then has the option of following the recommendation of the cleaning strategy and simply starting the cleaning device 320 via the operating element 326 or carrying out his own manual adjustment of the cleaning device 320 via the operating element 326. The cleaning is carried out in a cleaning tank 328, here a laundry drum.

Further, in Fig. 3, a detection device 330 is shown. The determining device 330 comprises sensor elements 332 and optionally at least one illumination means (not shown). The

Detection device has a shape such that when used in a cleaning device, neither the cleaning device nor the laundry of the detection device 330 can be damaged. Accordingly, the determining device 330, for example, a spherical shape, but on other particular shapes without apex corners and edges are conceivable. The determining device 330 is configured to be disposed in the cleaning tank 328 while performing cleaning. The determination device 330 is in this case freely movable and resistant to an action of the washing solution in the cleaning container 328. The determining device 330 can thus, for example, before or during a

Detect cleaning process first, second and / or third image information of the contaminant 302.

4 shows a block diagram of an exemplary embodiment of an apparatus 400, which in particular can execute an exemplary method according to the first aspect. The device 400 is for example a device according to the second or a system according to the third aspect.

The device 400 may be, for example, a computer, a desktop computer, a server, a thin client, or a portable computer (mobile device), such as a laptop computer, a tablet computer, a personal digital assistant (PDA), or a smartphone , For example, the device may perform the function of a server or a client.

Processor 410 of device 400 is particularly designed as a microprocessor, microcontroller, microcontroller, digital signal processor (DSP), application specific integrated circuit (ASIC) or field programmable gate array (FPGA). Processor 410 executes program instructions stored in program memory 412 and stores, for example, intermediate results or the like in working or main memory 41 1. For example, program memory 412 is a nonvolatile memory such as a flash memory, a magnetic memory, an EEPROM memory (electrically erasable programmable read only memory) and / or an optical memory. Main memory 41 1 is, for example, a volatile or nonvolatile memory, in particular a random access memory (RAM) such as a static RAM (SRAM), a dynamic RAM (DRAM), a ferroelectric RAM (FeRAM) ) and / or a magnetic RAM memory (MRAM).

Program memory 412 is preferably a local volume permanently attached to device 400. Hard disks permanently connected to the device 400 are, for example, hard disks which are built into the device 400. Alternatively, the data carrier may, for example, also be a data carrier which can be connected in separable manner with the device 400, such as a memory stick, a removable data carrier, a portable hard disk, a CD, a DVD and / or a floppy disk.

Program memory 412 includes, for example, the operating system of the device 400, which is loaded at least partially into main memory 41 1 when the device 400 is started and executed by the processor 410. In particular, when device 400 starts, at least a portion of the kernel of the operating system is loaded into main memory 41 1 and executed by processor 410. The operating system of device 400 is, for example, a Windows, UNIX, Linux, Android, Apple iOS, and / or MAC operating system.

The operating system in particular allows the use of the device 400 for

Data processing. It manages, for example, resources such as main memory 41 1 and program memory 412, communication interface 413, input and output device 414, provides, inter alia, through programming interfaces other programs basic functions and controls the execution of programs.

Processor 410 controls communication interface 413, which may be, for example, a

Network interface can be and can be designed as a network card, network module and / or modem. The communication interface 413 is in particular configured to connect the device 400 to other devices, in particular via a

(Wireless) communication system, such as a network to produce and communicate with them. For example, communication interface 413 may receive data (via the communication system) and forward to processor 410 and / or receive and transmit data (via the communication system) from processor 410. Examples of a Communication system are a local area network (LAN), a wide area network (WAN), a wireless network (for example, according to the IEEE 802.1 1 standard, the Bluetooth (LE) standard and / or the NFC standard), a wired network, a mobile network, a telephone network and / or the Internet.

Furthermore, processor 410 may control at least one input / output device 414. Input / output device 414 is, for example, a keyboard, a mouse, a display unit, a microphone, a touch-sensitive display unit, a loudspeaker, a reading device, a drive and / or a camera. For example, input / output device 414 may receive inputs from a user and pass them to processor 410 and / or receive and output information to the user of processor 410.

Finally, FIG. 5 shows different embodiments of storage media on which an embodiment of a computer program according to the invention can be stored. The storage medium may be, for example, a magnetic, electrical, optical and / or different storage medium. For example, the storage medium may be part of a processor (e.g., processor 410 of Fig. 4), such as a (non-volatile or volatile) program memory of the processor or a portion thereof (such as program memory 412 in Fig. 4). Embodiments of a storage medium include a flash memory 510, a SSD hard disk 51 1, a magnetic hard disk 512, a memory card 513, a memory stick 514 (e.g., a USB stick), a CD-ROM or DVD 515, or a floppy disk 516.

The following embodiments are also to be understood as disclosed:

Embodiment 1

Method performed by one or more devices, comprising:

Detecting first image information indicative of at least one contaminant on a textile;

Determining contaminant information indicative of at least one property of the contaminant on the fabric, wherein the at least one property is determined based at least in part on the acquired first image information, and wherein the at least one contaminant property is based at least in part on one of the outline the impurity-dependent property is determined; Issuing or causing the output of the determined contaminant information. Embodiment 2:

Method according to embodiment 1, wherein one or more of the following parameters i) to iv) determine the property dependent on the contour of the impurity:

i) form of contamination;

ii) structure of the impurity;

iii) size of the contaminant;

iv) Contour of contamination.

Embodiment 3

Method according to one of the preceding embodiments, wherein the at least one property of contamination of the textile is determined at least in part based on a color-dependent property of the contaminant.

Embodiment 4

Method according to embodiment 3, wherein one or more of the following parameters v) to x) determine the property dependent on the contour of the impurity:

v) isotropy of the contaminant;

vi) three-dimensionality of pollution;

vii) color scheme of the impurity;

viii) color and / or color intensity homogeneity of the contaminant;

ix) transparency of pollution;

x) gloss of the impurity.

Embodiment 5:

Method according to one of the preceding embodiments, the method further

full:

Determining at least one cleaning strategy parameter of the fabric based at least in part on the determined contaminant information.

Embodiment 6:

Method according to one of the preceding embodiments, the method further

full:

Performing or prompting the implementation of a treatment of the textile according to the at least one determined cleaning strategy parameter via at least one treatment device, in particular a cleaning device. Embodiment 7:

The method of embodiment 6, wherein the particular cleaning strategy parameter represents one or more of the following parameters:

a) type of detergent;

b) amount of detergent;

c) purification temperature;

d) type of cleaning device;

e) one or more settings of the cleaning device;

f) recommendation of pretreatment of the contaminant;

g) carrying out a special treatment.

Embodiment 8:

Method according to embodiment 6 or embodiment 7, the method further comprising:

Embodiment 9:

Method according to one of the preceding embodiments, the method further

full:

Determining property information of the textile, wherein the property information of the textile is indicative of at least one property of the textile, wherein

the at least one cleaning strategy parameter is determined based at least in part on the determined property information.

Embodiment 10:

Method according to embodiment 9, wherein the at least one property of the textile is indicative of material structure, type of material, material distribution, material wear of the textile, color of the fabric of the textile, shape of the fabric of the textile, or a combination thereof.

Embodiment 1 1:

Method according to one of the preceding embodiments, wherein the at least one cleaning strategy parameter is determined by means of a neural network, in particular an artificial neural network, wherein in a first step based at least in part on the determined contaminant information or at least partially based on the determined contaminant information and the determined characteristic information the textile a classification of the impurity takes place, and in a second step, the purification strategy parameters based at least in part on the classification of the

Pollution is derived.

Embodiment 12:

Method according to one of the preceding embodiments, wherein the classification is performed by means of a cluster recognition, wherein as input information the detected first image information or the acquired first image information and the acquired second image information is used as a function of the neural network parameters of certain

Impurities that are assigned to defined clusters are used, and as

Output information is output indicative of a defined contamination

Embodiment 13:

Method according to one of the preceding embodiments, wherein the image information from one or more sensors, in particular of one or more optical

Sensor elements are detected.

Embodiment 14:

Method according to one of the preceding embodiments, wherein the one or more optical sensor elements are formed as one of the following means:

(i) camera, in particular a 3D camera or hyperspectral camera;

(ii) LED sensor element;

(iii) NIR sensor element.

Embodiment 15:

Method according to one of the preceding embodiments, the method further

full:

the at least one property is determined based at least in part on the acquired first and second image information, Embodiment 16:

A method according to the embodiment 15, wherein the determining of the

Contamination information comprises a comparison of the detected first image information or the detected first and second image information with comparison values.

Embodiment 17:

Method according to one of the preceding embodiments, the method further comprising:

Determining an impurity profile based at least in part on

Cleaning strategy parameters, in particular based on a plurality of specific cleaning strategy parameters,

wherein determining the cleaning strategy parameter is based, at least in part, on the impurity profile in the event that an impurity profile (previously, initially) has been determined.

Embodiment 18:

Method according to one of the preceding embodiments, wherein at least one of the devices for carrying out the method is a mobile device.

Embodiment 19:

Device which is set up or comprises corresponding means for carrying out and / or controlling a method according to one of the exemplary embodiments 1 to 18.

Embodiment 20:

Device according to the embodiment 19, wherein the device is an electronic device, in particular a mobile device.

Embodiment 21:

Device comprising at least one processor and at least one memory

Computer program code, wherein the at least one memory and the computer program code are adapted to execute and / or control at least one method according to one of the embodiments 1 to 18 with the at least one processor. Embodiment 22:

A computer program comprising program instructions that cause a processor to execute and / or control a method according to any one of embodiments 1 to 18 when the computer program is running on the processor.

Embodiment 23:

Computer-readable storage medium, which is a computer program according to the

Embodiment 22 includes.

Embodiment 24:

System comprising:

several devices, in particular at least one mobile device and a

Cleaning device, which together a method according to one of

Execute embodiment 1 to 23 and / or control.

The exemplary embodiments of the present invention described in this specification and the respective optional features and properties cited in this context should also be understood to be disclosed in all combinations with one another. In particular, should also the

Description of a feature encompassed by an embodiment - unless explicitly stated to the contrary - are not understood in this case that the feature for the function of the embodiment is essential or essential. The sequence of the method steps described in this specification in the individual flowcharts is not mandatory, alternative sequences of the method steps are conceivable. The method steps can be implemented in different ways, so an implementation in software (by

Program instructions), hardware, or a combination of both to implement the method steps.

Terms used in the claims, such as "comprising," "comprising," "including," "containing," and the like, do not exclude other elements or steps. The phrase "at least partially" includes both the "partial" and "full" cases, and the phrase "and / or" shall be understood to disclose both the alternative and the combination, "A and." / or B "means" (A) or (B) or (A and B) ". The use of the indefinite article does not exclude a majority. A single device can perform the functions of several units or devices mentioned in the claims. Reference signs indicated in the claims should not be regarded as limitations on the means and steps employed.

Claims

claims

Method performed by one or more devices, comprising:

Detecting first image information indicative of at least one contaminant (204a,

204b, 302) on a textile (202a, 202b, 304) (202a, 202b, 304);

Determining contaminant information indicative of at least one property of the contaminant (204a, 204b, 302) on the fabric (202a, 202b, 304), wherein the at least one property is determined based at least in part on the acquired first image information, and wherein the at least one Property of

Contamination (204a, 204b, 302) of the fabric (202a, 202b, 304) is determined based at least in part on a property dependent on the contour of the contaminant (204a, 204b, 302);

Issuing or causing the output of the determined contaminant information.

The method of claim 1, wherein one or more of the following parameters i) to iv) determine the property dependent on the contour of the contaminant (204a, 204b, 302):

Form of contamination (204a, 204b, 302);

Structure of the contaminant (204a, 204b, 302);

Size of the contaminant (204a, 204b, 302);

Contour of the contaminant (204a, 204b, 302).

Method according to one of the preceding claims, wherein the at least one

Property of the contaminant (204a, 204b, 302) of the fabric (202a, 202b, 304) is determined based at least in part on a property dependent on the color of the contaminant (204a, 204b, 302).

The method of claim 3, wherein one or more of the following parameters v) to x) determine the property dependent on the contour of the contaminant (204a, 204b, 302):

Isotropy of the contaminant (204a, 204b, 302);

Three-dimensionality of the contaminant (204a, 204b, 302);

Color design of the contaminant (204a, 204b, 302);

Color and / or color intensity homogeneity of the contaminant (204a, 204b, 302);

Transparency of the contaminant (204a, 204b, 302);

Gloss of the contaminant (204a, 204b, 302).

5. The method of claim 1, the method further comprising: determining at least one cleaning strategy parameter of the fabric (202a, 202b, 304) based at least in part on the determined contaminant information.

A method according to any one of the preceding claims, the method further comprising:

Performing or causing the treatment of the textile (202a, 202b, 304) to be carried out in accordance with the at least one determined cleaning strategy parameter via at least one treatment device, in particular a cleaning device (320).

The method of claim 6, wherein the particular purification strategy parameter represents one or more of the following parameters:

a) type of detergent;

b) amount of detergent;

c) purification temperature;

d) type of cleaning device;

e) one or more settings of the cleaning device (320);

f) recommending a pretreatment of the contaminant (204a, 204b, 302);

g) Recommendation to carry out a special treatment.

The method of claim 6 or claim 7, the method further comprising:

Performing or causing the treatment to be performed based at least in part on the cleaning strategy parameter by means of a cleaning device (320).

9. The method according to any one of the preceding claims, the method further comprising:

Determining property information of the textile (202a, 202b, 304), wherein the property information of the textile (202a, 202b, 304) is indicative of at least one property of the textile (202a, 202b, 304), wherein

10. The method of claim 9, wherein the at least one property of the textile (202a, 202b, 304) indicative of material structure, material type, material distribution, material wear the fabric (202a, 202b, 304), color of the fabric of the textile (202a, 202b, 304), shape of the fabric of the fabric (202a, 202b, 304), or a combination thereof.

1 1. The method according to any one of the preceding claims, wherein the at least one

Cleaning strategy parameter is determined by means of a neural network (316), in particular an artificial neural network, wherein in a first step based at least in part on the determined contaminant information or at least partially based on the determined contaminant information and the determined property information of the textile (202a, 202b, 304 ) a classification of

Contamination (204a, 204b, 302) takes place, and in a second step the

Cleaning strategy parameter is derived based at least in part on the classification of the contaminant (204a, 204b, 302).

12. The method according to any one of the preceding claims, wherein the image information from one or more sensors (308, 332, 326), in particular detected by one or more optical sensor elements.

13. The method according to any one of the preceding claims, the method further comprising:

Detecting second image information indicative of at least the contaminant (204a, 204b, 302) on the fabric (202a, 202b, 304), the second image information covering the opposite side of the contaminant (204a, 204b, 302) from the first image information, wherein the at least one property is determined based at least in part on the detected first and second image information,

14. The method of claim 12, wherein determining the contaminant information comprises comparing the detected first image information or the acquired first and second image information with comparison values.

15. Device which is set up or comprises corresponding means for carrying out and / or controlling a method according to one of claims 1 to 13.