Panel icon identification method, apparatus, device, and medium

Abstract

The application belongs to the technical field of electrical appliances, and particularly relates to a panel icon identification method and device, equipment and a medium. The method comprises the following steps: acquiring a panel image of a clothes processing device, and determining icon information and text information corresponding to the panel image, wherein the icon information comprises icon meaning, first position information and first confidence, the text information comprises text content, second position information and second confidence, and the confidence is the accuracy of the icon meaning / text content; based on the first position information and the second position information, a plurality of icons and a plurality of texts in the panel image are paired to obtain a plurality of target function pairs, and each target function pair comprises one icon and one group of texts; according to the first confidence and the second confidence, the identification result of each target function pair is determined, and the identification result comprises one of the icon meaning or the text content.

Description

Technical Field

[0001] This application belongs to the field of smart electrical appliance technology, specifically relating to a panel icon recognition method, device, equipment, and medium. Background Technology

[0002] With the development of the garment processing industry, more and more garment processing equipment has begun to appear in people's field of vision, and some have even become essential household appliances, such as washing machines, dryers, and garment care machines.

[0003] Before being put on the market, garment processing equipment needs to undergo IoT testing and simulated user enterprise standard testing to ensure quality. Existing technology generally uses visual control automated testing systems to automatically test the IoT functions of garment processing equipment, especially key indicators such as binding success rate, by recognizing panel icons through images.

[0004] However, due to the diverse designs of panels by different manufacturers, the number and shapes of icons on the panels vary, resulting in poor image recognition performance and insufficient generalization ability, which affects the testing effect of the visual control automated testing system. Summary of the Invention

[0005] This application provides a panel icon recognition method, apparatus, device, and medium to solve the problem that the diverse panel designs, numerous and varied icons, and different shapes of clothing processing equipment in the prior art lead to poor image recognition results.

[0006] Firstly, this application provides a panel icon recognition method, including:

[0007] Acquire a panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes icon meaning, first position information and first confidence level. The text information includes text content, second position information and second confidence level. The confidence level is the accuracy of icon meaning / text content.

[0008] Based on the first location information and the second location information, multiple icons and multiple texts in the panel image are paired to obtain multiple target function pairs, each target function pair including an icon and a set of texts;

[0009] Based on the first confidence level and the second confidence level, the recognition result for each target function pair is determined, and the recognition result includes one of the following: unrecognizable, icon meaning, or text content.

[0010] In one possible design, pairing icons and text in the panel image based on the first location information and the second location information includes:

[0011] Based on the first location information and the second location information, the center point of the icon and the center point of the text are obtained respectively;

[0012] For each icon, calculate the positional distance between the center point of the icon and the center point of each text.

[0013] Based on the location distance, icon center point, and text center point, the icons and text in the panel image are paired.

[0014] In one possible design, pairing icons and text in the panel image based on the positional distance, icon center point, and text center point includes:

[0015] For each icon, obtain the text whose positional distance is less than a preset threshold, and divide the icon and each text whose positional distance is less than the preset threshold into a candidate function pair;

[0016] Based on the center point of the icon and the center point of the text, the positional relationship between the icon and the text in each candidate function pair is obtained, and the icons and text in the panel image are paired based on the positional relationship.

[0017] In one possible design, pairing icons and text in the panel image based on the positional relationship includes:

[0018] Pair the icons and text of candidate function pairs that are located in the same vertical / horizontal direction to obtain the target function pair.

[0019] In one possible design, if no text with a positional distance less than a preset threshold is found for each icon, the method further includes:

[0020] Output a prompt message, which indicates that the icon has not been matched with any text.

[0021] In one possible design, determining the identification result for each target function pair based on the first confidence level and the second confidence level includes:

[0022] For each target function pair, determine whether both the first confidence level and the second confidence level are less than the preset confidence level;

[0023] If so, then the identification result of the target function pair is determined to be unidentifiable;

[0024] If not, determine whether there exists a confidence level less than the preset confidence level between the first confidence level and the second confidence level;

[0025] If it exists, a first target confidence level is determined from the first confidence level and the second confidence level, and the recognition result of the target function pair is determined to be the icon meaning / text content corresponding to the first target confidence level, wherein the first target confidence level is not less than the preset confidence level;

[0026] If it does not exist, the recognition result of the target function pair is determined based on the meaning of the icon, the text content, the first confidence level and the second confidence level.

[0027] In one possible design, determining the recognition result of the target function pair based on the icon meaning, text content, first confidence level, and second confidence level includes:

[0028] Determine whether the icon meaning and text content of the target function pair are the same;

[0029] If they are the same, then the recognition result of the target function pair is determined to be the icon meaning / text content;

[0030] If they are not the same, then determine whether the first confidence level and the second confidence level are equal;

[0031] If they are equal, then the recognition result of the target function pair is determined to be text content;

[0032] If they are not equal, a second target confidence level is determined from the first confidence level and the second confidence level, and the recognition result of the target function pair is determined to be the icon meaning / text content corresponding to the second target confidence level. The second target confidence level is the higher of the first confidence level and the second confidence level.

[0033] Secondly, this application provides a panel icon recognition device, comprising:

[0034] The first acquisition module is used to acquire a panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes icon meaning, first position information and first confidence level, and the text information includes text content, second position information and second confidence level. The confidence level is the accuracy of icon meaning / text content.

[0035] The first processing module is used to pair multiple icons and multiple texts in the panel image based on the first location information and the second location information to obtain multiple target function pairs, each target function pair including an icon and a set of texts;

[0036] The second processing module is used to determine the recognition result of each target function pair based on the first confidence level and the second confidence level. The recognition result includes one of the following: unrecognizable, icon meaning, or text content.

[0037] Thirdly, this application provides a panel icon recognition device, including: a processor, and a memory communicatively connected to the processor;

[0038] The memory stores computer-executed instructions;

[0039] The processor executes computer execution instructions stored in the memory to implement the panel icon recognition method as described in the first aspect.

[0040] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a computer, are used to implement the panel icon recognition method as described in the first aspect.

[0041] The panel icon recognition method, apparatus, device, and medium provided in this application acquire a panel image of a garment processing device and determine the icon information and text information corresponding to the panel image. The icon information includes icon meaning, first location information, and a first confidence level; the text information includes text content, second location information, and a second confidence level, where the confidence level is the accuracy of the icon meaning / text content. Based on the first and second location information, multiple icons and multiple texts in the panel image are paired to obtain multiple target function pairs, each target function pair including one icon and one set of text. According to the first and second confidence levels, the recognition result for each target function pair is determined, where the recognition result includes either "unrecognizable," "icon meaning," or "text content."

[0042] In the above method, icons and text on the panel image of the garment processing equipment are acquired to determine their graphic meaning and positional relationship. The meaning recognition of icons and the content recognition of text each have their own corresponding confidence levels. The higher the confidence level, the more reliable the meaning of the icon or the content of the text, and the more accurate the recognition result. The positional relationship between icons and text determines icons and text belonging to the same function pair. Then, based on the confidence level of the icon meaning and the text content, the function pair is determined to achieve the binding recognition effect of icons and text. Attached Figure Description

[0043] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0044] Figure 1A This is a schematic diagram of an application scenario provided by an embodiment of this application;

[0045] Figure 1B A schematic diagram of a panel image provided in an embodiment of this application;

[0046] Figure 2 A flowchart of a panel icon recognition method provided in this application embodiment;

[0047] Figure 3 A flowchart of a panel icon recognition method provided in this application embodiment Figure 2 ;

[0048] Figure 4 A flowchart of a panel icon recognition method provided in this application embodiment Figure 3 ;

[0049] Figure 5 This is a schematic diagram of the structure of a panel icon recognition device provided in an embodiment of the present invention;

[0050] Figure 6 This is a hardware schematic diagram of a panel icon recognition device provided in an embodiment of the present invention.

[0051] The accompanying drawings illustrate specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to particular embodiments. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0053] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented, for example, in orders other than those illustrated or described herein.

[0054] In this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0055] With the development of technology and the improvement of people's living efficiency, the frequency of use of garment processing equipment is also increasing. To meet the growing demand, a large number of new garment processing equipment models are launched every year. Before being released to the market, garment processing equipment typically needs to undergo IoT testing and simulated user standard testing to ensure quality. Traditional manual testing is inefficient, time-consuming, and the differences in garment processing equipment models and panel designs increase the difficulty of testing. Therefore, a visual automated testing system for garment processing equipment has emerged, capable of automatically testing the IoT functions of garment processing equipment, especially key indicators such as binding success rate. Compared to manual operation, automated testing saves manpower, improves efficiency and accuracy, accelerates product launch, and ensures testing quality.

[0056] However, due to the diverse panel designs of garment processing equipment, and the large number and varied shapes of icons on the panel, the image recognition effect of the visual control automated testing system is poor and its generalization ability is insufficient, which affects the testing results.

[0057] Therefore, this application proposes a method for recognizing and matching text on the panel icons of a garment processing device. The method primarily involves first acquiring an image of the garment processing device's panel, then determining the positional relationship between the icons and text on the panel image, as well as the meaning of the icons and the content of the text. Each of the icon meaning recognition results and the text content recognition results corresponds to a confidence level. Subsequently, based on the relative positional relationship between the icons and text, the icons and text on the panel are grouped and paired to obtain multiple function pairs. Each function pair contains an icon and a set of text. Finally, for each function pair, the method identifies and determines the type of function pair based on the confidence levels corresponding to the icon meaning and the text content.

[0058] The application scenarios of this application will be explained below with reference to Figure 1.

[0059] Figure 1A This is a schematic diagram illustrating an application scenario provided by an embodiment of this application. For example... Figure 1A As shown, the scenario includes a clothing processing device 100, such as a washing machine or a dryer. The clothing processing device 100 is equipped with a panel 101. The execution entity in this embodiment can be the clothing processing device 100 or a server that is communicatively connected to the clothing processing device 100. This embodiment does not limit this.

[0060] First, acquire the panel image of the garment processing device 100 and determine the corresponding icon information and text information. The icon information includes the icon meaning, first position information and first confidence level. The text information includes the text content, second position information and second confidence level. The position information can be the coordinate information of the icon / text, such as diagonal coordinate information. The confidence level is the accuracy of the icon meaning / text content.

[0061] The recognition of text content and the recognition of icon meaning are existing technologies, and this application will not elaborate on them.

[0062] Based on the first and second position information, multiple icons and texts in the panel image are paired to obtain multiple target function pairs. Each target function pair includes an icon and a set of text. In this step, the icons and texts on panel 101 are grouped into functional groups, with each functional group consisting of an icon and a set of text, such as... Figure 1B As shown, "Standard Wash" and the icon above it form a function pair, "Gentle Mode" and the icon above it form a function pair, and so on for other function pairs.

[0063] Finally, based on the first and second confidence levels, the recognition result for each target function pair is determined. The recognition result includes one of the following: unrecognizable, icon meaning, or text content.

[0064] Based on the coordination between the above process steps, it is possible not only to match the icons and text on the garment processing equipment panel with functions, but also to accurately identify what kind of function each function pair is.

[0065] The technical solutions of this application and how they solve the aforementioned technical problems are described in detail below with specific embodiments. These specific embodiments may exist independently or in combination with each other. Identical or similar concepts or processes may not be repeated in some embodiments. The embodiments of this application will now be described with reference to the accompanying drawings.

[0066] Figure 2 A flowchart of a panel icon recognition method provided in an embodiment of this application is shown below. Figure 2 As shown, the method includes:

[0067] S201. Obtain the panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes the icon meaning, first position information and first confidence level, and the text information includes the text content, second position information and second confidence level. The confidence level is the accuracy of the icon meaning / text content.

[0068] In the above scheme, the panel of the garment processing equipment has many icons and many sets of text, which need to be matched one by one to obtain paired function groups. In this embodiment, the pairing is based on the positional relationship between the icons and text. After pairing, the specific function represented by the function pair is determined based on the confidence level corresponding to the meaning of the icon and the content of the text.

[0069] S202. Based on the first position information and the second position information, multiple icons and multiple texts in the panel image are paired to obtain multiple target function pairs, each target function pair including an icon and a set of texts.

[0070] In this step, generally speaking, in order to make it easier for users to identify and use, icons and text belonging to the same function pair will not be far apart in terms of position. Therefore, the function groups can be divided according to the relative position of the icons and text on the panel.

[0071] S203. Based on the first confidence level and the second confidence level, determine the recognition result for each target function pair. The recognition result includes one of the following: unrecognizable, icon meaning, or text content.

[0072] In the above scheme, confidence level represents the degree of certainty the recognition system has about its prediction results. Within the same function pair, the meaning identified by the icon and the content identified by the text may be the same or different. In such cases, it is necessary to compare the confidence levels of the two recognition results to represent the function pair with the recognition result having the highest confidence level possible. For example, if an icon is identified as "standard washing" with a confidence level of 0.85, then the probability that the icon represents "standard washing" is 85%. Similarly, if a set of text is identified as "fast washing" with a confidence level of 0.90, then the probability that the text in that area represents "fast washing" is 90%.

[0073] For example, if the confidence level of the text recognition result is higher than that of the icon recognition result, then the function of the function pair can be considered to be the content represented by the text; conversely, the function pair can be considered to be the meaning represented by the icon. Another possibility is that the confidence levels corresponding to both the text content and the icon meaning are low, i.e. unreliable. In this case, it can only be considered that there is no recognition result for the function pair and it cannot be recognized.

[0074] In this embodiment, icons and text on the panel image of the garment processing device are acquired to determine their graphic meaning and positional relationship. The meaning recognition of the icon and the content recognition of the text each have their own corresponding confidence level. The higher the confidence level, the more credible the meaning of the icon or the content of the text, and the more accurate the recognition result. The positional relationship between the icon and the text determines the icons and text that belong to the same function pair. Then, based on the confidence level of the icon meaning and the text content, the function pair is determined to achieve the binding recognition effect of icons and text.

[0075] The following is combined with Figure 3 The following specific embodiments illustrate the process of pairing icons and text in a panel image based on first and second position information in the panel icon recognition method of this application.

[0076] Figure 3 A flowchart of a panel icon recognition method provided in this application embodiment Figure 2 .like Figure 3 As shown, the method includes:

[0077] S301. Based on the first position information and the second position information, obtain the center point of the icon and the center point of the text respectively.

[0078] In this step, to facilitate obtaining the center point positions of the icon and text respectively, the position information can be the diagonal coordinates. For example, the position information of the icon is (X1, Y1; X2, Y2), where (X1, Y1) represents the position coordinates of the upper left corner of the icon, and (X2, Y2) represents the position coordinates of the lower right corner of the icon; the position information of the text is (X3, Y3; X4, Y4), where (X3, Y3) represents the position coordinates of the upper left corner of the text, and (X4, Y4) represents the position coordinates of the lower right corner of the text.

[0079] In actual operation, the values ​​of all coordinate points are located in the fourth quadrant to ensure that the coordinate point values ​​are all positive, which is beneficial for comparing position distances. The same applies below.

[0080] This embodiment preferably uses the nearest neighbor method to determine icons and text belonging to the same functional pair. Nearest neighbor matching is a simple and efficient matching method. It calculates the distance between icons and text in two-dimensional space to find the closest text and icon for matching. This method is suitable for scenarios with a large number of icons and text and a relatively regular layout, and can achieve good results in fast positioning and matching.

[0081] The center point of the icon and the center point of the text can be obtained using the formula for calculating the center point of coordinates, as follows:

[0082] X center = (X_min + X_max) / 2

[0083] Y center = (Y_min + Y_max) / 2

[0084] Among them, X center and Y center X_min and Y_min represent the position coordinates of the center point on the X-axis and Y-axis, respectively. X_min and Y_min represent the minimum coordinate values ​​on the X-axis and Y-axis, respectively. X_max and Y_min represent the maximum coordinate values ​​on the X-axis and Y-axis, respectively.

[0085] The calculated X-coordinate of the center point of the icon is X. 12 = (X1+X2) / 2, the Y-coordinate of the center point of the icon is Y. 12= (Y1+Y2) / 2, the coordinates of the center point of the icon are (X... 12 Y 12 ).

[0086] The calculated X-coordinate of the center point of the text is X. 34 = (X3 + X4) / 2, where the Y-coordinate of the center point of the text is Y. 34 = (Y3+Y4) / 2, the coordinates of the center point of the text are (X 34 Y 34 ).

[0087] S302. For each icon, calculate the positional distance between the center point of the icon and the center point of each text.

[0088] In the above scheme, the distance between the two center points can be obtained using the Euclidean distance calculation formula, as follows:

[0089]

[0090] Where d represents the Euclidean distance.

[0091] S303. For each icon, obtain the text whose positional distance is less than a preset threshold, and divide the icon and each text whose positional distance is less than the preset threshold into a candidate function pair.

[0092] In this step, for each icon, the nearest text is found as a candidate matching object, that is, the text coordinate object with the smallest Euclidean distance between the center point of the icon and the center point of the text is selected.

[0093] In practice, to avoid incorrect matching, a reasonable distance threshold can be set based on the actual dimensions and design values ​​of the garment processing equipment's panel. Only when the distance between the icon and text is less than this threshold is it considered a match. If no text is found within the threshold range, the icon is considered not to have matched the text. For example, the preset threshold can be 5mm or 8mm.

[0094] In the actual implementation process, some icons may not have text that is less than the preset threshold in terms of position distance. This indicates that the icon may not have a matching text group. This can remind relevant operators to perform a second confirmation to avoid recognition errors by the recognition system. For example, a prompt message can be output to indicate that the icon has not matched any text.

[0095] S304. Based on the center point of the icon and the center point of the text, obtain the positional relationship between the icon and the text in each candidate function pair, and pair the icons and text of candidate function pairs whose icons and text are located in the same vertical / horizontal direction to obtain the target function pair.

[0096] As mentioned above, the icons and text on the garment processing equipment panel typically have a certain relative spatial layout relationship. For example, text is generally located around icons, and the text and icons overlap in the vertical / horizontal direction. Therefore, based on the nearest neighbor matching method, constraints on relative positional relationships can also be used to determine text and icons belonging to the same functional pair, ensuring that the text is located within a reasonable area of ​​the icon.

[0097] In this embodiment, it is assumed that the text is located below the icon, and the text and the icon overlap in the horizontal direction.

[0098] In one embodiment, text can be filtered to include text below an icon and text that are horizontally centered, based on the relative positions of the icon's center point and the text's center point.

[0099] (1) Text below the icon: Y3 > Y2, that is, in the fourth quadrant, the Y-axis coordinate of the upper left corner of the text is below the Y-axis coordinate of the lower right corner of the icon.

[0100] (2) The text and icons overlap horizontally: X 12 =X 34 That is, the center point of the icon and the center point of the text are located in the same vertical direction;

[0101] In another embodiment, the overlap between text and icon in the horizontal direction can be determined based on the diagonal coordinates of the text and icon respectively, and the text and icon that overlap in the horizontal direction can be filtered out, i.e. X3≤X2 and X4≥X1.

[0102] In another embodiment, text and icons that overlap horizontally can also be filtered based on the fact that the center point of the text is located within the horizontal range corresponding to the icon, i.e., X. 34 Located within the horizontal range formed by X1 and X2; or, based on the center point of the icon being within the horizontal range corresponding to the text, text and icons that overlap horizontally can be filtered out, i.e., X... 12 It lies within the horizontal range formed by X3 and X4.

[0103] In this embodiment, the position coordinates of the center point of the icon and the center point of the text are first calculated using icon position information and text position information, and then the distance between the center point of each icon and the center point of each text is obtained. Next, for each icon, the text corresponding to all text center points that are close to the center point of the icon are determined, and the icons and each text that meet the above distance conditions are formed into candidate function pairs for the icon. Finally, based on the positional relationship between the icon and the text in each candidate function pair, the target function pair corresponding to the icon is determined from the candidate function pairs.

[0104] The following is combined with Figure 4 The specific embodiments illustrate the implementation process of determining the recognition result of each target function pair based on the first confidence level and the second confidence level in the panel icon recognition method of this application.

[0105] Figure 4 A flowchart of a panel icon recognition method provided in this application embodiment Figure 3 .like Figure 4 As shown, the method includes:

[0106] S401. For each target function pair, determine whether both the first confidence level and the second confidence level are less than the preset confidence level.

[0107] In the above scheme, after identifying the icons and text that belong to the same function pair, it is necessary to determine the function represented by the function pair. This function may be the meaning represented by the icon, the content represented by the text, or it may not represent any function at all. At this time, it is necessary to use the confidence level information.

[0108] S402. If so, then the identification result of the target function pair is determined to be unrecognizable.

[0109] In this step, a threshold can be set to filter out text and icon recognition results with low confidence levels, performing preliminary screening. If the confidence levels for both icon meaning recognition and text content recognition are lower than the preset confidence levels, it means that neither recognition result is reliable, and in this case, the function cannot be effectively recognized.

[0110] In the actual implementation process, the preset reliability can be adjusted according to the recognition results of the actual icons and text, or it can be fixed. For example, the preset reliability can be 0.6 or 0.8.

[0111] S403. If not, determine whether there exists a confidence level less than the preset confidence level between the first confidence level and the second confidence level.

[0112] In the above scheme, if the confidence scores corresponding to the icon and the text are not both less than the preset confidence score, it is necessary to determine whether there is a confidence score less than the preset confidence score. Alternatively, it can be considered as determining whether both confidence scores are greater than or equal to the preset confidence score.

[0113] S404. If it exists, determine the first target confidence from the first confidence and the second confidence, and determine the recognition result of the target function pair as the icon meaning / text content corresponding to the first target confidence, wherein the first target confidence is not less than the preset confidence.

[0114] In this step, if one confidence level is less than the preset threshold, it means that the two confidence levels are not both greater than or equal to the preset threshold. That is, if one of the confidence levels corresponding to the icon and the confidence level corresponding to the text is greater than the preset threshold and the other is less than the preset threshold, then the result with the confidence level higher than the preset threshold is output.

[0115] S405. If it does not exist, determine whether the icon meaning and text content of the target function pair are the same.

[0116] In the above scheme, if there is no confidence score less than the preset threshold, it means that both confidence scores are greater than or equal to the preset threshold. At this time, it is necessary to further determine whether the recognition result of the icon is consistent with the recognition result of the text, that is, whether the meaning of the icon and the content of the text are consistent.

[0117] S406. If they are the same, the recognition result of the target function pair is determined to be the icon meaning / text content.

[0118] In this step, if the confidence scores of both the icon and the text are greater than the preset threshold, and the icon recognition result is consistent with the text recognition result, then the result is output directly.

[0119] S407. If they are not the same, then determine whether the first confidence level and the second confidence level are equal.

[0120] In the above scheme, if the icon recognition result and the text recognition result are inconsistent, then it is necessary to determine what function the target function pair represents based on the relationship between the two confidence levels.

[0121] S408. If they are equal, then the recognition result of the target function pair is determined to be text content.

[0122] In this step, when the confidence scores for the icon and the text are equal, and the icon recognition result is inconsistent with the text recognition result, the text recognition result is output first. This is because the panel icons of different models of garment processing equipment vary greatly, but the text descriptions generally change little or not at all, so text is prioritized.

[0123] S409. If they are not equal, then determine the second target confidence level from the first confidence level and the second confidence level, and determine the recognition result of the target function pair as the icon meaning / text content corresponding to the second target confidence level. The second target confidence level is the higher of the first confidence level and the second confidence level.

[0124] In the above scheme, although the recognition results of icons and text are inconsistent, the confidence scores of both have passed the preliminary screening conditions corresponding to the preset thresholds, and the confidence scores are relatively high. The final output result tends to be the result with higher confidence scores. For example, if the preset confidence score is 0.6, the confidence score corresponding to the text recognition result "Quick Wash" is 0.9, and the confidence score corresponding to the icon recognition result "Standard Wash" is 0.85, then the final output result is "Quick Wash".

[0125] In this embodiment, after identifying icons and text belonging to the same function pair, a comprehensive judgment is made based on the confidence levels of the icons and text respectively to ensure that the output results have high credibility. The output results are different under different confidence levels. For example, when both confidence levels are low, the recognition result is unrecognizable; when both confidence levels are high and unequal, the result with higher confidence is output first; when both confidence levels are high and equal, the text recognition result is output first.

[0126] In summary, the panel icon recognition method provided in this application acquires a panel image of a garment processing device, thereby obtaining the positional relationship between icons and text on the panel image, as well as the meaning represented by the icons and the content represented by the text. The recognition results of the icon meaning and the recognition results of the text content each correspond to a confidence level. Subsequently, based on the relative positional relationship between the icons and text, the icons and text on the panel are grouped and paired to obtain multiple function pairs. Each function pair contains an icon and a set of text. Finally, for each function pair, the function pair is identified and determined according to the confidence levels corresponding to the icon meaning and the text content.

[0127] Figure 5 This is a schematic diagram of the structure of a panel icon recognition device provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the panel icon recognition device may include various functional modules for implementing the aforementioned panel icon recognition method, and any functional module may be implemented by software / or hardware.

[0128] For example, the panel icon recognition device may include: an acquisition module 501, a first processing module 502, and a second processing module 503;

[0129] The acquisition module 501 is used to acquire the panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes the icon meaning, the first position information and the first confidence level, and the text information includes the text content, the second position information and the second confidence level. The confidence level is the accuracy of the icon meaning / text content.

[0130] The first processing module 503 is used to pair multiple icons and multiple texts in the panel image based on the first position information and the second position information to obtain multiple target function pairs, each target function pair including an icon and a set of texts;

[0131] The second processing module 504 is used to determine the recognition result of each target function pair based on the first confidence level and the second confidence level. The recognition result includes one of the following: unrecognizable, icon meaning, or text content.

[0132] Optionally, the first processing module 503 can also be used to obtain the center point of the icon and the center point of the text based on the first position information and the second position information respectively; calculate the positional distance between the center point of the icon and the center point of each text for each icon; and pair the icons and text in the panel image based on the positional distance, the center point of the icon, and the center point of the text.

[0133] Optionally, the first processing module 503 may also be specifically used to: for each icon, obtain text whose positional distance is less than a preset threshold, and divide the icon and each text whose positional distance is less than the preset threshold into a candidate function pair; according to the center point of the icon and the center point of the text, obtain the positional relationship between the icon and the text in each candidate function pair, and pair the icons and text in the panel image based on the positional relationship.

[0134] Optionally, the first processing module 503 can also be used to pair the icons and text of candidate function pairs whose icons and text are located in the same vertical / horizontal direction to obtain the target function pair.

[0135] Optionally, the first processing module 503 can also be specifically used to: if for each icon, no text with a position distance less than a preset threshold is obtained, output a prompt message, the prompt message being used to indicate that the icon has not matched any text.

[0136] Optionally, the second processing module 504 can also be used to determine, for each target function pair, whether both the first confidence level and the second confidence level are less than a preset confidence level; if so, the recognition result of the target function pair is determined to be unrecognizable; if not, it is determined whether either the first confidence level or the second confidence level is less than the preset confidence level; if so, the first target confidence level is determined from the first confidence level and the second confidence level, and the recognition result of the target function pair is determined to be the icon meaning / text content corresponding to the first target confidence level, wherein the first target confidence level is not less than the preset confidence level; if not, the recognition result of the target function pair is determined based on the icon meaning, text content, first confidence level and second confidence level.

[0137] Optionally, the second processing module 504 can also be specifically used to: determine whether the icon meaning and text content of the target function pair are the same; if they are the same, determine that the recognition result of the target function pair is icon meaning / text content; if they are different, determine whether the first confidence level and the second confidence level are equal; if they are equal, determine that the recognition result of the target function pair is text content; if they are different, determine the second target confidence level from the first confidence level and the second confidence level, and determine that the recognition result of the target function pair is the icon meaning / text content corresponding to the second target confidence level, wherein the second target confidence level is the higher of the first confidence level and the second confidence level.

[0138] The panel icon recognition device is used to execute the technical solution provided in the aforementioned panel icon recognition method embodiment. Its implementation principle and technical effect are similar to those in the aforementioned method embodiment, and will not be repeated here.

[0139] This application also provides a panel icon recognition device, including: at least one processor and a memory;

[0140] The memory stores the instructions that the computer executes;

[0141] At least one processor executes computer execution instructions stored in memory, such that at least one processor executes a panel icon recognition method.

[0142] Figure 6 This is a hardware schematic diagram of a panel icon recognition device provided in an embodiment of the present invention. Figure 6 As shown, the panel icon recognition device 60 provided in this embodiment includes at least one processor 601 and a memory 602. The device 60 also includes a communication component 603. The processor 601, memory 602, and communication component 603 are connected via a bus 604.

[0143] In the specific implementation process, at least one processor 601 executes computer execution instructions stored in memory 602, causing at least one processor 601 to execute the above panel icon recognition method.

[0144] The specific implementation process of processor 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0145] In the above Figure 6 In the illustrated embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0146] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0147] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0148] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the panel icon recognition method described above.

[0149] The aforementioned computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0150] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0151] The division of units described herein is merely a logical functional division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0152] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0153] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0154] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0155] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0156] The technical solutions of this application have been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of this application is obviously not limited to these specific embodiments. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

Claims

1. A method for recognizing panel icons, characterized in that, include: Acquire a panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes icon meaning, first position information and first confidence level. The text information includes text content, second position information and second confidence level. The confidence level is the accuracy of icon meaning / text content. Based on the first location information and the second location information, multiple icons and multiple texts in the panel image are paired to obtain multiple target function pairs, each target function pair including an icon and a set of texts; Based on the first confidence level and the second confidence level, the recognition result for each target function pair is determined, and the recognition result includes one of the following: unrecognizable, icon meaning, or text content.

2. The method according to claim 1, characterized in that, The step of pairing icons and text in the panel image based on the first location information and the second location information includes: Based on the first location information and the second location information, the center point of the icon and the center point of the text are obtained respectively; For each icon, calculate the positional distance between the center point of the icon and the center point of each text. Based on the location distance, icon center point, and text center point, the icons and text in the panel image are paired.

3. The method according to claim 2, characterized in that, The process of pairing icons and text in the panel image based on the location distance, icon center point, and text center point includes: For each icon, obtain the text whose positional distance is less than a preset threshold, and divide the icon and each text whose positional distance is less than the preset threshold into a candidate function pair; Based on the center point of the icon and the center point of the text, the positional relationship between the icon and the text in each candidate function pair is obtained, and the icons and text in the panel image are paired based on the positional relationship.

4. The method according to claim 3, characterized in that, The process of pairing icons and text in the panel image based on the positional relationship includes: Pair the icons and text of candidate function pairs that are located in the same vertical / horizontal direction to obtain the target function pair.

5. The method according to claim 3, characterized in that, If no text with a positional distance less than a preset threshold is found for each icon, the method further includes: Output a prompt message, which indicates that the icon has not been matched with any text.

6. The method according to claim 1 or 5, characterized in that, The step of determining the identification result of each target function pair based on the first confidence level and the second confidence level includes: For each target function pair, determine whether both the first confidence level and the second confidence level are less than the preset confidence level; If so, then the identification result of the target function pair is determined to be unidentifiable; If not, determine whether there exists a confidence level less than the preset confidence level between the first confidence level and the second confidence level; If it exists, a first target confidence level is determined from the first confidence level and the second confidence level, and the recognition result of the target function pair is determined to be the icon meaning / text content corresponding to the first target confidence level, wherein the first target confidence level is not less than the preset confidence level; If it does not exist, the recognition result of the target function pair is determined based on the meaning of the icon, the text content, the first confidence level and the second confidence level.

7. The method according to claim 6, characterized in that, The determination of the recognition result of the target function pair based on the icon meaning, text content, first confidence level, and second confidence level includes: Determine whether the icon meaning and text content of the target function pair are the same; If they are the same, then the recognition result of the target function pair is determined to be the icon meaning / text content; If they are not the same, then determine whether the first confidence level and the second confidence level are equal; If they are equal, then the recognition result of the target function pair is determined to be text content; If they are not equal, a second target confidence level is determined from the first confidence level and the second confidence level, and the recognition result of the target function pair is determined to be the icon meaning / text content corresponding to the second target confidence level. The second target confidence level is the higher of the first confidence level and the second confidence level.

8. A panel icon recognition device, characterized in that, include: The acquisition module is used to acquire a panel image of the garment processing equipment and determine the icon information and text information corresponding to the panel image. The icon information includes icon meaning, first position information and first confidence level, and the text information includes text content, second position information and second confidence level. The confidence level is the accuracy of icon meaning / text content. The first processing module is used to pair multiple icons and multiple texts in the panel image based on the first location information and the second location information to obtain multiple target function pairs, each target function pair including an icon and a set of texts; The second processing module is used to determine the recognition result of each target function pair based on the first confidence level and the second confidence level. The recognition result includes one of the following: unrecognizable, icon meaning, or text content.

9. A panel icon recognition device, characterized in that, include: At least one processor and memory; The memory stores computer-executed instructions; The at least one processor executes computer execution instructions stored in the memory, causing the at least one processor to perform the panel icon recognition method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the panel icon recognition method as described in any one of claims 1 to 7.

Images