Brush head wear prediction

Abstract

The present disclosure provides concepts for predicting wear of a brush head of an oral care device. The brush head comprises a brush body and cleaning elements mounted on the brush body for contact with an oral surface of a user. An image of the brush head including the cleaning elements is obtained. The image is then compared to reference image data describing an expected appearance of the cleaning elements of an unused brush head. A wear score indicating a degree of wear of the brush head is generated based on a result of the comparison of the image and the reference image data. In this way, an accurate prediction of an extent to which a brush head is worn may be obtained, based on which appropriate action can be recommended and / or actioned.

Description

[0001] BRUSH HEAD WEAR PREDICTION

[0002] FIELD OF INVENTION

[0003] The present invention relates to predicting brush head wear, and in particular, to systems and methods for predicting wear of a brush head of an oral care device.

[0004] BACKGROUND

[0005] As a brush head of an oral care device (e.g., toothbrush, mouthpiece) ages, or as the brush head is repeatedly used, an effectiveness of the brush head tends to reduce. That is, as the condition of the brush head deteriorates, the effectiveness of the overall oral care device also deteriorates. Indeed, cleaning elements of the brush head begin to harden and fray, rendering them ineffective for teeth cleaning.

[0006] Therefore, ensuring that the brush head is replaced in a timely manner is essential to ensure efficacy of the oral care device.

[0007] It is generally recommended to change the brush head every 90 days. Therefore, many mechanisms prompt the replacement of the brush head after 90 days, such as smart devices that automatically track said activity. However, it has been realized that there is much variability in the time taken for a brush head to deteriorate to the point it needs replacing. For example, if care is taken to apply appropriate pressure and / or the brush head is properly treated and cleaned at the end of a brushing session, then a brush head may be suitably effective for longer than 90 days. In contrast, if excessive pressure is used and the brush head is not looked after, the brush head may be rendered ineffective in a shorter length of time. Thus, the 90-day benchmark may not be appropriate in all cases, either increasing cost and waste, or leading some users to experience poor brushing performance for an extended period.

[0008] Accordingly, there exists a need for an improved means for detecting wear of a brush head to overcome one or more of these problems.

[0009] SUMMARY OF INVENTION

[0010] The invention is defined by the claims.

[0011] According to an aspect of the present disclosure, a method for predicting wear of a brush head of an oral care device is provided. The brush head comprises a brush body and cleaning elements mounted on the brush body for contact with an oral surface of a user.

[0012] The method comprises: obtaining an image of the brush head including the cleaning elements; comparing the image to reference image data describing an expected appearance of the cleaning elements of an unused brush head; and generating a wear score indicating a degree of wear of the brush head based on a result of the comparison of the image and the reference image data.This method allows for objective and automated assessment of brush head wear, enabling timely replacement recommendations to maintain oral hygiene effectiveness. More particularly, by comparing an image of the actual brush head with data describing an appearance of an unused / new brush head, a meaningful assessment of wear of the brush head may be made. For example, if the image of the brush head deviates significantly from the reference image data, this may indicate that the brush head is excessively worn. In contrast, if the image of the brush head substantially matches what is expected according to the reference image data, this may indicate that the brush head is not worn.

[0013] Thus, appropriate action may be recommended and / or taken according to the wear score. If the wear score indicates a high / heavy degree of wear, then a user may be prompted to replace the brush head. If the wear score indicates a low / light degree of wear, then the user may not be prompted to replace the brush head. In other examples, an expected remaining lifetime of the brush head may be estimated based on the wear score, enabling a user to anticipate when a brush head may need replacing and to plan accordingly.

[0014] In some embodiments, the reference image data may describe an expected area occupied by the cleaning elements in an image of an unused brush. In this case, comparing the image to reference image data may comprise: identifying an area of the image occupied by the cleaning elements; and comparing the area occupied by the cleaning elements to the reference image data.

[0015] That is, cleaning elements are expected to occupy a certain area of the brush head. This occupation may change with use as the cleaning elements get frayed, splayed, lost, and otherwise damaged. Accordingly, this embodiment proposes to leverage this information to objectively determine an extent to which the cleaning elements deviate from their expected positions, thereby providing an objective measure of wear of the brush head. In other words, this feature enables detection of cleaning element splaying or loss, which are key indicators of brush wear. In turn, this provides for a more accurate wear assessment.

[0016] Additionally or alternatively, the reference image data may describe an expected angle of the cleaning elements of an unused brush relative to the brush body. In this case, comparing the image to reference image data may comprise identifying an angle of the cleaning elements; and comparing the angle of the cleaning elements to the reference image data.

[0017] Analyzing the angle of cleaning elements provides insight into cleaning element deformation, allowing for more accurate wear assessment. For an unused brush head, cleaning elements may be generally expected to be tangential to the brush body. Thus, the degree of deviation from this angle may indicate an extent to which the brush head has been used, and so may be used to inform a wear score indicating wear of the brush head.

[0018] The reference image data may include a template image of an unused brush head including cleaning elements. In some embodiments, the method may further comprise aligning the image and the template image.Using a template image allows for precise comparison between the current brush head state and an ideal unused state of the same brush, improving wear detection accuracy. By aligning the template image and the image, then a computationally inexpensive comparison of the images may be made.

[0019] More specifically, the aligning may comprise identifying a location of boundary points of the brush head in the image; identifying an orientation of a major axis of the brush head in the image based on the location of the boundary points; identifying an orientation of a minor axis of the brush head in the image based on the location of the boundary points and the orientation of the major axis;

[0020] identifying a location of reference points of the brush head based on the location of the boundary points, the orientation of the major axis, and the orientation of the minor axis; and modifying the image of the brush head based on the identified reference points in the image and reference points in the reference image.

[0021] This detailed alignment process ensures consistent and accurate comparison between the captured image and the reference image, regardless of variations in image capture conditions.

[0022] When the oral care device further comprises a neck for connecting the brush head to a body of the oral care device, the identified reference points may comprise a tip of the brush head, boundary points of the brush head intersecting with the minor axis of the brush head, and boundary points of the brush head intersecting with the neck of the oral care device.

[0023] These standardized reference points may allow for quick and computationally inexpensive aligning of the image and the reference image.

[0024] Furthermore, the method may comprise processing the image to generate a segmented image of the brush head indicating an area of the plan view image occupied by the cleaning elements, and an area of the image occupied by the brush body.

[0025] Segmentation allows for focused analysis on the cleaning elements, improving the accuracy of wear detection. Indeed, by comparing the segmentation of the image to the reference image data, a computationally inexpensive but meaningful assessment of the brush head may be made.

[0026] In some embodiments, the method may further comprise generating a matching score by processing the image and the template image data with a comparison algorithm, the matching score indicating an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head. In this case, generating the wear score may be based on the matching score.

[0027] The matching score provides a quantitative measure of brush head wear, enabling more precise recommendations for brush head replacement.

[0028] In addition, comparing the plan view image to the reference image data may comprise providing the plan view image to a machine learning algorithm, obtaining a prediction result from the machine learning algorithm, the prediction result comprising the matching score. In this case, generating the wear score may be based on the matching score. To be clear, the machine learning algorithm may betrained to predict an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head.

[0029] Utilizing machine learning enhances the accuracy and adaptability of the wear prediction method, allowing it to improve over time with more data. Indeed, the machine learning algorithm may identify patterns that are unrecognized by typical analytical algorithms, further improving the accuracy of the wear score.

[0030] In further embodiments, the method may also comprise obtaining audio data including sound generated by the cleaning elements contacting the oral surface of the user; and comparing the audio data to reference audio data describing an expected sound generated by the cleaning elements contacting the oral surface of the user. Accordingly, the wear score may be further based on a result of the comparison of the audio data to the reference audio data.

[0031] Indeed, it is noted that a brush head may make an unusual / unexpected noise when excessively worn compared to when it is new / unused. Thus, incorporating audio data provides an additional dimension for wear assessment, potentially capturing aspects of brush performance not visible in images alone.

[0032] In additional embodiments, the method may also comprise obtaining use data describing use of the oral care device; and comparing the use data to reference use data describing expected use of the oral care device. Thus, generating the wear score may be further based on a result of the comparison of the use data to the reference use data.

[0033] This use data may include information such as brushing duration, frequency, applied pressure to the brush head, and grip pressure on the oral care device, which may vary as the brush head condition changes. The user of the oral care device may, consciously or subconsciously, change their use behavior as a brush head wears down. For example, they may brush for longer or apply additional pressure to achieve a similar clear compared to when brushing with a new / unused brush head.

[0034] Additionally, the user may grip the body of the oral care device more firmly if the brush head is worn out, compared to when gripping the oral care device when the brush head is new. Comparing usage of the brush head may therefore provide valuable insight into the state of the brush head, further improving accuracy of the wear score. Further, considering usage patterns allows for more personalized wear predictions, accounting for individual brushing habits.

[0035] In another embodiment, the method may also comprise obtaining oral health data describing a state of an oral surface of the user before using the oral care device and after using the oral care device; and comparing the oral health data to reference oral health data describing an expected deviation in the state of the oral surface of the user before and after using the oral care device.

[0036] Accordingly, generating the wear score may be further based on a result of the comparison of the oral health data to the reference oral health data.

[0037] For example, an unused brush may be able to remove more plaque compared to a worn brush given similar brushing conditions. Assessing plaque removal (as one possible option describing thestate of the oral surface) may therefore indicate a level of wear of the brush head. Incorporating oral health outcomes provides a holistic approach to wear assessment, directly linking brush condition to its effectiveness in maintaining oral hygiene. Overall, this may further improve the accuracy of the generated wear score.

[0038] According to another aspect of the present disclosure, a computer program comprising computer program code means adapted, when said computer program is run on a computer, to implement the method for predicting wear of a brush head of an oral care device as described herein is provided.

[0039] According to a further aspect of the present disclosure, a system for predicting wear of a brush head of an oral care device is provided. The brush head comprises a brush body and cleaning elements mounted on the brush body for contact with an oral surface of a user.

[0040] The system comprises: an interface configured to obtain an image of the brush head including the cleaning elements; and a processor configured to: compare the image to reference image data describing an expected appearance of the cleaning elements of an unused brush head; and generate a wear score indicating a degree of wear of the brush head based on a result of the comparison of the image and the reference image data.

[0041] These and other aspects of the invention will be apparent from and elucidated with reference to the embodiment(s) described hereinafter.

[0042] BRIEF DESCRIPTION OF FIGURES

[0043] For a better understanding of the invention, and to show more clearly how it may be carried into effect, reference will now be made, by way of example only, to the accompanying drawings, in which:

[0044] FIG. 1 illustrates a flowchart for predicting wear of a brush head, according to aspects of the present disclosure;

[0045] FIG. 2 depicts a flowchart for predicting wear of a brush head using multiple data sources, according to an embodiment;

[0046] FIG. 3 shows a flowchart for aligning an image of a brush head, in accordance with example embodiments;

[0047] FIG. 4 illustrates a sequence of image processing steps for analyzing a brush head, according to aspects of the present disclosure;

[0048] FIG. 5 depicts a schematic diagram of a system for predicting brush head wear, according to an embodiment;

[0049] FIG. 6 presents a simplified representation of the oral care device 3, alongside two implementations of the system 500 for predicting wear of the brush head of the oral care device; and FIG. 7 is a simplified block diagram of a computer within which one or more parts of an embodiment may be employed.DETAILED DESCRIPTION

[0050] The invention will be described with reference to the Figures.

[0051] It should be understood that the Figures are merely schematic and are not drawn to scale. It should also be understood that the same reference numerals are used throughout the Figures to indicate the same or similar parts.

[0052] It should also be understood that the detailed description and specific examples, while indicating exemplary embodiments of the apparatus, systems and methods, are intended for purposes of illustration only and are not intended to limit the scope of the invention. These and other features, aspects, and advantages of the apparatus, systems and methods of the present invention will become better understood from the following description, appended claims, and accompanying drawings. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to provide an advantage.

[0053] The present disclosure provides concepts for predicting wear of a brush head of an oral care device, such that appropriate action can be recommended and / or enacted. To this end, disclosed means compare an image of the brush head with template image data describing an expected appearance of a new / unused brush head. From this comparison, a meaningful and accurate determination of whether the brush head is worn may be performed. This contrasts with traditional approaches in which the brush head is simply replaced after a certain length of time, which may either be too often leading to waste and added cost, or not often enough leading to inadequate cleaning and / or damage to oral surfaces.

[0054] By way of explanation, oral care devices such as toothbrushes and brushing mouthpieces are primary oral healthcare products, and so the quality of the oral care device that one uses is important to maintain oral hygiene. Cleaning elements (e.g., bristles) of such devices undergo the most deterioration of any element of said devices due to contact with oral surfaces. It is therefore important to know whether the brush in its current state is good enough to provide satisfactory cleaning. It is therefore desirable to prompt the user to replace the brush head whenever needed.

[0055] Generally it is acknowledged that the oral care device or brush head should be replaced when the cleaning elements of the brush head are worn or frayed. Excessive wear of the brush head tends to have occurred after three months (i.e., approximately 90 days) of use. After this point, the average brush head is hardened and frayed, and can no longer effectively clean teeth since the cleaning elements need to flex slightly when brushing.

[0056] Whilst three months is the recommended amount of time to replace the brush head, rate of deterioration of the brush head may vary based on a variety of factors, such as frequency and length of use, a pressure applied to the brush head, and storage conditions of the brush head. Thus, it is acknowledged that it is often wise to make a judgement as to whether the brush is worn based on a visible state of the brush head, and / or an odor of the brush head.

[0057] Accordingly, disclosed embodiments propose to estimate the wear of a brush head (and more specifically wear of cleaning elements of a brush head) using image processing methods. Byassessing the wear in the form of a wear score, a remaining effective lifetime of the brush head may be generated and / or it may be suggested whether the brush head needs replacing.

[0058] In other words, embodiments provide a wear score which may inform feedback to the user on the usefulness of the brush head in its current state towards the objective of maintaining oral hygiene. In many cases, users keep using a brush head when it is no longer suitable for effective cleaning (e.g., it may damage the surface or the teeth or be inadequate for removal of plaque). In other cases, users may replace the brush head too quickly. A guidance is thus required so that the user knows when to replace their brush head.

[0059] Thus, it is proposed to intelligently determine wear of the brush head, and to dynamically generate recommended actions. To do so, the appearance of the brush head may be compared to an appearance of an unused (i.e., new) brush head. Specifically, an image of the brush head may processed using image processing algorithms, to compare the brush head to reference image data and thus determine the wear of the brush head as compared to the new one. For example, an angle of the cleaning elements (from the plane of the body of the brush head), and / or an area of the brush head occupied by the cleaning elements may be considered. If such parameters differ from expected values beyond a threshold, it may be determined that replacement is required.

[0060] Nevertheless, other factors may also be considered, such as:

[0061] (i) A sound generated by the cleaning elements of the brush head contacting an oral surface (e.g., a tooth, a gum) may be compared to a sound generated by cleaning elements of an unused brush head contacting an oral surface. Specifically, audio data including said sound may be processed using audio processing techniques to determine if the brush head is making a noise that deviates from regularly generated noise. This sound analysis may be performed by hardware on the toothbrush itself, given the toothbrush has a microphone. Alternatively, the sound analysis may be performed by any device capable of audio recording and processing (e.g., a smart phone) in the vicinity of the toothbrush;

[0062] (ii) The use of the oral care device by the user by be compared to an expected use of the oral care device. In particular, if the user changes their brushing behavior compared to when the brush head was new, this may indicate wear of the brush head. For example, if the user is exerting increased pressure in order to achieve a satisfactory clean, then this may indicate that the brush head requires replacement. That is, pressure values (describing a pressure exerted by the cleaning elements on an oral surface of the user) measured after the brush head is worn may differ from standard / expected pressure values from when the brush head is new; and

[0063] (iii) The resulting state of the oral surface of the user after a brushing session may be compared to an expected state of the oral surface after a brushing session. Indeed, if cleaning performance does not meet expectations, this may be attributed to a worn out brush head. For example, if plaque reduction is less than expected than during a normal brushing routine, this may be attributed to thecleaning elements being unable to remove said plaque - therefore requiring replacement. The state of the oral surface can be determined via an intraoral camera based scanner, for example.

[0064] Put another way, the present disclosure relates to methods and systems for predicting wear of brush heads in oral care devices. Maintaining proper oral hygiene is essential for overall health, and the condition of the cleaning elements on a brush head plays a crucial role in effective cleaning. As brush heads wear overtime, their cleaning efficacy diminishes, potentially compromising oral health. Therefore, accurately assessing brush head wear and determining when replacement is necessary can significantly impact oral care routines.

[0065] Traditional approaches to brush head replacement often rely on fixed time intervals or subjective visual assessments, which may not account for individual usage patterns or variations in wear rates. The disclosed methods and systems aim to provide a more precise and personalized approach to predicting brush head wear.

[0066] By utilizing image processing techniques, alongside optional use of audio analysis, usage data, and / or oral health metrics, the disclosed methods can generate a comprehensive assessment of brush head condition. This assessment can be used to provide timely recommendations for brush head replacement, ensuring that users maintain optimal cleaning performance throughout their oral care routines.

[0067] By leveraging computational power and advanced algorithms, the computer program can analyze various inputs and compare them against reference data to determine the extent of brush head wear. This automated approach offers a more objective and consistent method for assessing brush head condition compared to traditional manual inspections. The integration of such a computer program into oral care devices or associated applications can provide users with real-time feedback on their brush head condition, promoting better oral hygiene practices and more timely replacement of worn brush heads.

[0068] FIG. 1 illustrates a flowchart for predicting wear of a brush head of an oral care device. The brush head comprises a brush body upon which cleaning elements are mounted. The cleaning elements are configured for contact with an oral surface of the user, in order to provide cleaning of the oral surface. For example, the cleaning elements may be bristles.

[0069] In step 100, an image of the brush head is obtained. The image of the brush head includes the cleaning elements of the brush head. This step may involve capturing a digital photograph or scan of the brush head, including the cleaning elements mounted on the brush body.

[0070] The process of obtaining and processing an image or images of the brush head is a crucial step in assessing the wear of the cleaning elements. An image acquisition system may be employed to capture images of the brush head, including the cleaning elements. This system may utilize readily available cameras in smartphones, for example. To obtain an image of the brush head including the cleaning elements, the brush head may be positioned in a predetermined orientation relative to the imaging device (e.g., the image may be taken from above the plane of the brush body, thereby providing a plan image of the brush head). Nevertheless, embodiments are not restricted hereto, and assessment maybe performed using an image of the brush head form a variety of orientations, given that at least some of the cleaning elements are visible in the image of the brush head.

[0071] Once an image is captured, it may be subject to preprocessing to enhance its quality and prepare it for further analysis. Image preprocessing techniques may include noise reduction, contrast enhancement: color correction, and image resizing.

[0072] After preprocessing, the image may be processed to generate a segmented image of the brush head. This segmentation process aims to distinguish between the area occupied by the cleaning elements and the area occupied by the brush body. Any known segmentation techniques may be utilized, including thresholding, edge detection, region growing, and machine learning-based segmentation.

[0073] The resulting segmented image provides a clear delineation between the area occupied by the cleaning elements and the area occupied by the brush body. This segmentation may improve the effectiveness of subsequent analysis steps, such as measuring the area covered by the cleaning elements or assessing their orientation.

[0074] By obtaining and processing images of the brush head in this manner, the system can generate accurate and consistent data for comparing the current state of the cleaning elements to reference data, ultimately enabling the assessment of brush head wear.

[0075] In step 200, the image is compared to reference image data describing an expected appearance of the cleaning elements of an unused (i.e., new) brush head. That is, the image is assessed based on what the brush head is expected to look like when it is new. The reference image data may simply be an image of the brush head in an unused / new state, a template image representing the brush head in an unused state in an abstracted manner, or a textual / numeric list describing one or more visibly measurable characteristics of the brush head.

[0076] The comparison process may also take into account the overall shape and structure of the brush head, including how it connects to the neck of the oral care device. This can help identify any deformations or structural changes in the brush head itself that may impact its cleaning effectiveness. This analysis step may include a selection of various sub steps 210-250. One or more of the sub steps may be employed depending on a desired tradeoff between complexity and accuracy.

[0077] In sub step 210, the image may be aligned with a template image to ensure accurate comparisons. That is, the image may be oriented with a pre-generated template image presenting one or more characteristics of the expected appearance of a new brush head. This alignment process may involve adjusting the orientation and scale of the acquired image to match a standardized template, ensuring consistent comparison across different brush heads. A detailed example of an alignment process is described below in reference to FIG. 3 and illustrated in reference to FIG. 4.

[0078] In sub step 220, an area occupied by the cleaning elements in the acquired image is identified and compared to the expected area described in the reference image data. This analysis may involve image segmentation techniques to isolate the cleaning elements from the brush body and background. The segmented area can then be quantitatively compared to the reference data to detect anysignificant deviations in the overall coverage of the cleaning elements. This analysis can reveal whether the cleaning elements have been deformed out of shape and / or lost from the brush head.

[0079] For example, a measurement may be made of the cleaning elements outside of an expected occupied area, which may indicate an extent of ware. In another example, an intersection over union algorithm may be utilized to compare the extent that an occupied area of the cleaning elements in the image matches an occupied area of cleaning elements in a template image.

[0080] In sub step 230, an angle of the cleaning elements in the acquired image are identified, and compared to expected angles of cleaning elements as described by the reference image data. That is, the reference image data may describe an expected angle of the cleaning elements relative to the brush body for an unused brush. The comparison process involves identifying the actual angle of the cleaning elements in the acquired image and comparing it to this reference data. This analysis can reveal whether the cleaning elements have become splayed or bent over time, indicating wear.

[0081] In other words, the degree of deviation from this angle may indicate an extent to which the brush head has been used and so may be used to inform a wear score indicating wear of the brush head. The correlation between the degree of deviation from the expected angle and the extent of wear may be derived from a sample set of used brush heads, thereby identifying a pattern between difference in angle and ware of the brush head (which may not be a linear relationship).

[0082] Of course, the expected angle(s) of the cleaning elements and resulting comparison / calculation may change based on the type of brush head. That is, whilst some brush heads have cleaning elements that are all substantially perpendicular to the brush body, this is not always the case. Some brush heads have cleaning elements that are expected to be provided at an angle to the brush body (e.g., to provide better cleaning action). Therefore, it may be appropriate to compare the actual angle of the cleaning elements to expected angle(s) that depend on the brush head type.

[0083] To be clear, a template image of an unused brush head may be included in the reference image data. This template serves as a baseline for comparison, representing the ideal arrangement and condition of the cleaning elements. The comparison process may involve overlaying the aligned acquired image with this template to identify areas of deviation.

[0084] In step 240, the image and template image are processed with a comparison algorithm. This algorithm may employ various image processing techniques to quantify differences between the acquired image and the reference data. Thus, the comparison algorithm may generate a matching score indicating an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head.

[0085] To this end, advanced image processing techniques may be employed to enhance the accuracy of these comparisons. For example, edge detection algorithms can be used to more precisely define the boundaries of the brush head and individual cleaning elements. Texture analysis may be applied to assess changes in the surface characteristics of the cleaning elements, which can indicate wear or fraying.In step 250, the image may be provided to a machine learning algorithm. This algorithm may be trained on a dataset of brush head images at various stages of wear, allowing for automated assessment of brush head condition. In other words, the image is provided to a machine learning algorithm trained to predict an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head. A prediction result may then be obtained from the machine learning algorithm, with the prediction result comprising the matching score. This matching score may be used alone, or in combination with the matching score generated by a comparison algorithm (e.g., an average or a weighted sum may be taken) to provide a matching score.

[0086] By combining these various comparison techniques, a comprehensive assessment of the brush head's condition can be generated.

[0087] In step 300, a wear score is generated based on the preceding comparison operations. This wear score indicates the degree or an extent of wear of the brush head determined through the analysis of the captured image. This wear score may then be used to recommend whether and / or when a brush head should be replaced.

[0088] For instance, the wear score generation process may consider multiple factors, such as: 1. The matching score from the comparison algorithm and / or machine learning algorithm; 2. The area occupied by the cleaning elements in the acquired image compared to the reference data describing an expected area occupied by the cleaning elements of a new / unused brush head; and / or

[0089] 3. The angle of the cleaning elements relative to the brush body compared to the reference data describing an expected angle of the cleaning elements of a new / unused brush head.

[0090] Each of these factors may be assigned a weight in the wear score calculation. For example:

[0091] Wear Score = (0.4 Matching Score) + (0.3 Area Score) + (0.3 Angle Score).

[0092] In this example, the matching score has the highest weight, reflecting its importance in determining overall wear. Of course, this is just one example, and various weights and factors may be adjusted based on empirical data and testing to optimize the accuracy of the wear score.

[0093] The resulting wear score indicates the degree of wear of the brush head based on the comparison of the acquired image and the reference image data. This score may be represented on a scale, for instance from 0 to 100, where 0 indicates a completely worn brush head and 100 represents a new, unused brush head (or vice versa).

[0094] By generating a wear score in this manner, the system provides a quantitative assessment of brush head condition, enabling users to make informed decisions about when to replace their brush heads for optimal oral care.

[0095] Furthermore, the wear prediction process may incorporate additional data sources to enhance the accuracy of brush head wear assessment. This is shown in FIG. 2, depicting a flowchart forpredicting wear of a brush head with a multi-factor approach to wear prediction, incorporating different types of data including audio, usage patterns, oral health metrics, and visual information from the brush head.

[0096] The flowchart shows multiple parallel processes that contribute to generating a wear score.

[0097] In step 102, audio data is obtained, including sound generated by the cleaning elements contacting the oral surface of the user. This audio data may include sounds generated during brushing, which may change as the brush head wears.

[0098] Therefore, in step 202, this audio data may be compared to reference audio data describing an expected sound generated by the cleaning elements contacting the oral surface of the user. The comparison may reveal changes in the sound profde that indicate wear of the cleaning elements. For this comparison, various audio analysis techniques may be used.

[0099] In step 104, use data describing use of the oral care device is obtained. This use data may include information such as brushing duration, frequency, and applied pressure, which may vary as the brush head condition changes.

[0100] In step 204, this use data is compared to reference use data describing expected use of the oral care device. Deviations from expected usage patterns may indicate changes in brush head performance due to wear.

[0101] In step 106, oral health data describing a state of an oral surface of the user before using the oral care device and after using the oral care device are collected. For example, the oral health data may include an extent of plaque coverage on the oral surfaces before and after cleaning.

[0102] For instance, the oral health data may be assessed by determining the amount of plaque present on oral surfaces before and after a brushing session. To this end, an intraoral scanner device may be used to obtain images of the oral surface, and these images may be analyzed to determine a degree of plaque removal. That is, information from an intraoral scanner can be evaluated (e.g., using a processing device such as a mobile device, or the cloud) to generate oral health data.

[0103] In step 206, this oral health data is compared to reference oral health data describing an expected deviation in the state of the oral surface of the user before and after using the oral care device. Differences in cleaning effectiveness may suggest wear of the brush head.

[0104] Additionally, in step 100 an image of the brush head is obtained and in step 200 this image is compared to reference image data, similar to the process described in FIG. 1.

[0105] The results from all (or a selection of) comparison steps converge to a final step where a wear score is generated. This wear score is based on the outcomes of the various comparisons performed in the parallel processes, providing a comprehensive assessment of brush head condition.

[0106] In one embodiment, a wear score is first generated based on the comparison of the image of the brush head and the reference image data. Then, the wear score is updated based on the comparisonof the other data sources. In other cases, the image, audio data, use data, and oral health data are used simultaneously to generate the wear score.

[0107] In other words, the wear score generation process may incorporate the results of these additional comparisons in addition to the comparison of the image of the brush head with the reference image data. The wear score may be further based on a result of the comparison of the audio data to the reference audio data. Similarly, the wear score may be further based on a result of the comparison of the use data to the reference use data. Additionally, the wear score may be further based on a result of the comparison of the oral health data to the reference oral health data.

[0108] By incorporating these multiple data sources, the wear prediction process may provide a more comprehensive assessment of brush head condition. The combination of visual, auditory, usage, and oral health data may allow for a more accurate determination of when a brush head requires replacement, potentially improving overall oral care effectiveness.

[0109] Moving on, and as outlined above, aligning the acquired image may be important for improving accuracy of the comparison with the reference image data, and thus for accuracy of the wear score. FIG. 3 presents a flow diagram of a method for aligning the image. FIG. 4 illustrates a variety of these steps on an example brush head, for comparison with a template image 410 of the brush head in an unused state.

[0110] As seen in 410, an expected area occupied by the cleaning elements is depicted by the various black elements 412 within the shape of the brush head.

[0111] In step 211, the location of boundary points of the brush head in the acquired image is determined. To this end, initially the image may be segmented to identify boundary points of the brush head. The result of this is shown in 420, which shows an estimated outline 422 of a used brush head.

[0112] In step 212, the orientation of the major axis of the brush head is determined based on these boundary points. To this end, principle component analysis of the boundary points may be performed to estimate the orientation of the major axis of the brush head. Alternatively, and as shown in 430, a Hough transform may be used to fit lines 434 to the boundary corresponding to the brush handle, and find the vanishing points of intersection the two lines 434. Then ,the major axis 432 may be located as the angular bisector of the lines 434. The orientation of the major axis 432 may be corrected such that for all points or samples points on the detected major axis, the perpendicular line passing through the point intersects the boundary at equal distances on either side.

[0113] In step 213, the orientation of the minor axis of the brush head is identified using the boundary points and the established major axis. The minor axis 442 is depicted in 440. The minor axis 442 is perpendicular to the major axis by definition. It is just then a matter of shifting the minor axis 442 to the point on the brush head where the perpendicular distance of the major axis with boundary points / outline is a maximum.

[0114] In step 214, reference points on the brush head are located, which may include the tip of the brush head, points where the minor axis intersects the brush head boundary, and points where thebrush head connects to the neck of the oral care device. That is, the reference points may comprise a tip of the brush head, boundary points of the brush head intersecting with the minor axis of the brush head, and boundary points of the brush head intersecting with the neck of the oral care device. The example reference points 442 are also shown in 440.

[0115] Finally, in step 215, the acquired image is modified based on these identified reference points to align with corresponding points in the reference image. This may include matching the reference points to reference points in the reference image, and transforming, resizing and rotating the image to match the reference image.

[0116] FIG. 5 illustrates a schematic diagram showing components of a system 500 for predicting wear of a brush head of an oral care device.

[0117] The system 500 comprises an interface 510, and a processor 520. The interface 510 may be responsible for obtaining input data, such as images of the brush head, audio data from brushing sessions, use data, and oral health data. The interface 510 may also provide output to the user, such as wear score results orbrush head replacement recommendations.

[0118] The processor 520 may be responsible for executing the comparison algorithms, machine learning models, and wear score calculations based on the input data received through the interface 510, as described above in reference to FIGS. 1-3.

[0119] FIG. 6 presents a simplified representation of the oral care device 3, alongside two implementations of the system 500 for predicting wear of the brush head of the oral care device.

[0120] On the left side of the diagram, an oral care device 3 is depicted in a side view, showing an elongated body with cleaning elements mounted at its upper portion. The oral care device comprises a main body 40, a neck portion 30 that connects to the main body 40. The brush head comprises a brush head body 20, and cleaning elements 10. The brush head body 20 may be detachable from the neck 30, and so may be replaced when excessively worn.

[0121] The system for predicting wear may be implemented by various systems, which may leverage computational power and advanced algorithms to analyze various inputs and compare them against reference data to determine the extent of brush head wear. Of course, as described above, the system may be integrated into oral care devices 3. Alternatively, as shown, the system may be provided separately from the oral care device 3, and connected to the oral care device 3 via a wireless communication interface (e.g., Wi-Fi, Bluetooth, etc.)

[0122] In one example, the oral care device 3 may be connected to a cloud processing environment 50 via a Wi-Fi interface. The cloud processing environment 50 may then perform all of the actions as described above. In another example, the oral care device 3 may be connected to a mobile device 60 via a Wi-Fi interface. The mobile device 60 may then perform all of the actions as described above. Equally, various aspects of the invention may be performed by the mobile device 60, and other aspects by the cloud processing environment 50. For instance, the mobile device 60 may act as an interface configured to obtain an image of the brush head, and then may provide this information to thecloud processing environment 50 to compare the image and generate a wear score. The results may then be communicated back to the mobile device 60 and / or oral care device 3, thus establishing a digital brushing ecosystem.

[0123] FIG. 7 illustrates an example of a computer 900 within which one or more parts of an embodiment may be employed. Various operations discussed above may utilize the capabilities of the computer. For example, one or more parts of a proposed embodiment may be incorporated in any element, module, application, and / or component discussed herein. In this regard, it is to be understood that system functional blocks can run on a single computer or may be distributed over several computers and locations (e.g. connected via internet), such as a cloud-based computing infrastructure.

[0124] The computer 900 includes, but is not limited to, PCs, workstations, laptops, PDAs, palm devices, servers, storages, and the like. Generally, in terms of hardware architecture, the computer 900 may include one or more processors 910, memory 920 and one or more I / O devices 930 that are communicatively coupled via a local interface (not shown). The local interface can be, for example but not limited to, one or more buses or other wired or wireless connections, as is known in the art. The local interface may have additional elements, such as controllers, buffers (caches), drivers, repeaters, and receivers, to enable communications. Further, the local interface may include address, control, and / or data connections to enable appropriate communications among the aforementioned components.

[0125] The processor 910 is a hardware device for executing software that can be stored in the memory 920. The processor 910 can be virtually any custom made or commercially available processor, a central processing unit (CPU), a digital signal processor (DSP), or an auxiliary processor among several processors associated with the computer 900, and the processor 910 may be a semiconductor based microprocessor (in the form of a microchip) or a microprocessor.

[0126] The memory 920 can include any one or combination of volatile memory elements (e.g., random access memory (RAM), such as dynamic random access memory (DRAM), static random access memory (SRAM), etc.) and non-volatile memory elements (e.g., ROM, erasable programmable read only memory (EPROM), electronically erasable programmable read only memory (EEPROM), programmable read only memory (PROM), tape, compact disc read only memory (CD-ROM), disk, diskette, cartridge, cassette or the like, etc.). Moreover, the memory 920 may incorporate electronic, magnetic, optical, and / or other types of storage media. Note that the memory 920 can have a distributed architecture, where various components are situated remote from one another, but can be accessed by the processor 910.

[0127] The software in the memory 920 may include one or more separate programs, each of which comprises an ordered listing of executable instructions for implementing logical functions. The software in the memory 920 includes a suitable operating system (O / S) 950, compiler 960, source code 970, and one or more applications 980 in accordance with exemplary embodiments. As illustrated, the application 980 comprises numerous functional components for implementing the features and operations of the exemplary embodiments. The application 980 of the computer 900 may represent various applications, computational units, logic, functional units, processes, operations, virtual entities, and / ormodules in accordance with exemplary embodiments, but the application 980 is not meant to be a limitation.

[0128] The operating system 950 controls the execution of other computer programs, and provides scheduling, input-output control, file and data management, memory management, and communication control and related services. It is contemplated by the inventors that the application 980 for implementing exemplary embodiments may be applicable on all commercially available operating systems.

[0129] Application 980 may be a source program, executable program (object code), script, or any other entity comprising a set of instructions to be performed. When a source program, then the program is usually translated via a compiler (such as the compiler 960), assembler, interpreter, or the like, which may or may not be included within the memory 920, so as to operate properly in connection with the O / S 950. Furthermore, the application 980 can be written as an object oriented programming language, which has classes of data and methods, or a procedure programming language, which has routines, subroutines, and / or functions, for example but not limited to, C, C++, C#, Pascal, Python, BASIC, API calls, HTML, XHTML, XML, ASP scripts, JavaScript, FORTRAN, COBOL, Perl, Java, ADA, .NET, and the like.

[0130] The I / O devices 930 may include input devices such as, for example but not limited to, a mouse, keyboard, scanner, microphone, camera, etc. Furthermore, the I / O devices 930 may also include output devices, for example but not limited to a printer, display, etc.

[0131] Finally, the I / O devices 930 may further include devices that communicate both inputs and outputs, for instance but not limited to, a NIC or modulator / demodulator (for accessing remote devices, other fdes, devices, systems, or a network), a radio frequency (RF) or other transceiver, a telephonic interface, a bridge, a router, etc. The I / O devices 630 also include components for communicating over various networks, such as the Internet or intranet.

[0132] If the computer 900 is a PC, workstation, intelligent device or the like, the software in the memory 920 may further include a basic input output system (BIOS) (omitted for simplicity). The BIOS is a set of essential software routines that initialize and test hardware at start-up, start the O / S 950, and support the transfer of data among the hardware devices. The BIOS is stored in some type of read-only-memory, such as ROM, PROM, EPROM, EEPROM or the like, so that the BIOS can be executed when the computer 900 is activated.

[0133] When the computer 900 is in operation, the processor 910 is configured to execute software stored within the memory 920, to communicate data to and from the memory 920, and to generally control operations of the computer 900 pursuant to the software. The application 980 and the O / S 950 are read, in whole or in part, by the processor 910, perhaps buffered within the processor 910, and then executed.

[0134] When the application 980 is implemented in software it should be noted that the application 980 can be stored on virtually any computer readable medium for use by or in connection withany computer related system or method. In the context of this document, a computer readable medium may be an electronic, magnetic, optical, or other physical device or means that can contain or store a computer program for use by or in connection with a computer related system or method.

[0135] The application 980 can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. In the context of this document, a "computer-readable medium" can be any means that can store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer readable medium can be, for example but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, device, or propagation medium.

[0136] The proposed method(s), device(s) and / or system(s) may be implemented in hardware or software, or a mixture of both (for example, as firmware running on a hardware device). To the extent that an embodiment is implemented partly or wholly in software, the functional steps illustrated in the process flow diagrams may be performed by suitably programmed physical computing devices, such as one or more central processing units (CPUs) or graphics processing units (GPUs). Each process - and its individual component steps as illustrated in the flow diagrams - may be performed by the same or different computing devices. According to embodiments, a computer-readable storage medium stores a computer program comprising computer program code configured to cause one or more physical computing devices to carry out a control method as described above when the program is run on the one or more physical computing devices.

[0137] Storage media may include volatile and non-volatile computer memory such as RAM, PROM, EPROM, and EEPROM, optical discs (like CD, DVD, BD), magnetic storage media (like hard discs and tapes). Various storage media may be fixed within a computing device or may be transportable, such that the one or more programs stored thereon can be loaded into a processor.

[0138] To the extent that an embodiment is implemented partly or wholly in hardware, some of the blocks shown in the block diagrams may be separate physical components, or logical subdivisions of single physical components, or may be all implemented in an integrated manner in one physical component. The functions of one block shown in the drawings may be divided between multiple components in an implementation, or the functions of multiple blocks shown in the drawings may be combined in single components in an implementation. Hardware components suitable for use in embodiments of the present invention include, but are not limited to, conventional microprocessors, application specific integrated circuits (ASICs), and field-programmable gate arrays (FPGAs). One or more blocks may be implemented as a combination of dedicated hardware to perform some functions and one or more programmed microprocessors and associated circuitry to perform other functions.

[0139] Variations to the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed invention, from a study of the drawings, the disclosure, and theappended claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit may fulfil the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to provide an advantage. If a computer program is discussed above, it may be stored / distributed on a suitable medium, such as an optical storage medium or a solid-state medium supplied together with or as part of other hardware, but may also be distributed in other forms, such as via the Internet or other wired or wireless telecommunication systems. If the term "adapted to" is used in the claims or description, it is noted the term "adapted to" is intended to be equivalent to the term "configured to". Any reference signs in the claims should not be construed as limiting the scope.

[0140] The flow diagrams and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flow diagrams or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flow diagrams and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

Claims

CLAIMS:

1. A computer-implemented method (1, 2) for predicting wear of a brush head of an oral care device, the brush head comprising a brush body and cleaning elements mounted on the brush body for contact with an oral surface of a user, the method being executed by at least one processor operatively coupled to an imaging sensor and a memory comprising:obtaining (100), via the imaging sensor, an image of the brush head including the cleaning elements;comparing (200), by the processor, the image to reference image data stored in a memory and describing an expected appearance of the cleaning elements of an unused brush head; processing (240), by the processor, the image and the reference image data with a comparison algorithm to generate a matching score indicating an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head; and generating (300), by the processor, a wear score indicating a degree of wear of the brush head based on the matching score.

2. The method of claim 1, wherein the reference image data describes an expected area occupied by the cleaning elements in an image of an unused brush, and wherein comparing the image to reference image data comprises:identifying (220) an area of the image occupied by the cleaning elements; and comparing the area occupied by the cleaning elements to the reference image data.

3. The method of claim 1 or 2, wherein the reference image data describes an expected angle of the cleaning elements of an unused brush relative to the brush body, and wherein comparing the image to reference image data comprises:identifying (230) an angle of the cleaning elements; andcomparing the angle of the cleaning elements to the reference image data.

4. The method of any of claims 1-3, wherein the reference image data includes a template image of an unused brush head including cleaning elements.

5. The method of claim 4, further comprising aligning (210) the image and the template image.

6. The method of claim 5, wherein the aligning comprises:identifying (211) a location of boundary points of the brush head in the image; identifying (212) an orientation of a major axis of the brush head in the image based on the location of the boundary points;identifying (213) an orientation of a minor axis of the brush head in the image based on the location of the boundary points and the orientation of the major axis;identifying (214) a location of reference points of the brush head based on the location of the boundary points, the orientation of the major axis, and the orientation of the minor axis; and modifying (215) the image of the brush head based on the identified reference points in the image and reference points in the reference image.

7. The method of claim 6, wherein the oral care device further comprises a neck for connecting the brush head to a body of the oral care device, and wherein the identified reference points comprise a tip of the brush head, boundary points of the brush head intersecting with the minor axis of the brush head, and boundary points of the brush head intersecting with the neck of the oral care device.

8. The method of any of claims 4-7, further comprising:processing the image to generate a segmented image of the brush head indicating an area of the plan view image occupied by the cleaning elements, and an area of the image occupied by the brush body.

9. The method of any of claims 1-8, further comprising generating the matching score by processing (240) the image and the template image data with a comparison algorithm, the matching score indicating an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head, andwherein generating (300) the wear score is based on the matching score.

10. The method of any of claims 1-9, wherein comparing (200) the image to the reference image data comprises:providing (250) the image to a machine learning algorithm, the machine learning algorithm being trained to predict an extent to which an appearance of the cleaning elements in the image matches an expected appearance of the cleaning elements of an unused brush head;obtaining a prediction result from the machine learning algorithm, the prediction result comprising the matching score, andwherein generating (300) the wear score is based on the matching score.

11. The method of any of claims 1-10, further comprising:obtaining (102), by a microphone arranged in the oral care device or in a mobile terminal in wireless communication with the oral care device, audio data including sound generated by the cleaning elements contacting the oral surface of the user and processing, by the processor, the audio data to extract at least one audio characteristic descriptive of the sound; andcomparing (202) the extracted audio characteristic to reference audio characteristic describing an expected sound generated by the cleaning elements contacting the oral surface of the user, wherein generating (300) the wear score is further based on a result of the comparison of the extracted audio characteristic to the reference audio characteristic.

12. The method of any of claims 1-11, further comprising:obtaining (104) use data describing use of the oral care device, the use data comprising one or more operational parameters measured or recorded by sensors or timers of the oral care device and / or a mobile terminal in communication with the oral care device; andcomparing (204) the obtained use data to reference use data describing expected values of said operational parameters for an unused brush head ,wherein generating (300) the wear score is further based on a result of the comparison of the obtained use data to the reference use data.

13. The method of any of claims 1-12, further comprising:obtaining (106) oral health data indicative of a cleaning effectiveness outcome describing a state of an oral surface of the user before using the oral care device and after using the oral care device, processing, by the processor, the oral health data to compute an oral health outcome metric indicative of the change in said state due to brushing; andcomparing (206) the oral health outcome metric to reference oral health data describing an expected outcome metric before and after using the oral care device for an unused brush head, and wherein generating (300) the wear score is further based on a result of the comparison of the oral health outcome metric to the reference oral health data.

14. A computer program comprising computer program code means adapted, when said computer program is run on a computer, to implement the method of any of claims 1-13.

15. A system (500) for predicting wear of a brush head of an oral care device (3), the brush head comprising a brush body (20) and cleaning elements (10) mounted on the brush body for contact with an oral surface of a user, the system comprising:an interface (510) configured to obtain an image of the brush head including the cleaning elements;a processor (520) configured to:22compare the image to reference image data describing an expected appearance of the cleaning elements of an unused brush head; andgenerate a wear score indicating a degree of wear of the brush head based on a result of the comparison of the image and the reference image data.

Images