Image matching method and device, electronic equipment and chip

Abstract

The present disclosure relates to an image matching method, device, electronic equipment and chip. The image matching method comprises: acquiring a to-be-matched image; matching the to-be-matched image with multiple templates; in the case that the to-be-matched image matches one of the multiple templates successfully and fails to match the other templates, verifying the matching based on the overlap rate of the to-be-matched image and the other templates; and in the case that the verification is passed, determining that the to-be-matched image matches successfully. The present disclosure performs matching verification based on the overlap rate of the to-be-matched image and the other templates on the basis of the successful single template matching, improves the accuracy of the matching, reduces the false matching rate, and thus realizes high-precision image matching.

Description

Technical Field

[0001] This disclosure relates to the field of image processing, and more particularly to an image matching method, apparatus, electronic device, and chip. Background Technology

[0002] The most fundamental matching techniques in the field of image matching include template matching and feature matching. Template matching involves setting one or more target templates and then iteratively moving them against the image to be matched to determine if they are compatible. Feature matching, on the other hand, uses specific structures within the image as features and then leverages the structure or location of these features for matching. It involves both feature extraction and feature matching.

[0003] Small-size image matching mainly refers to situations where multiple images are entered at once, but only one image is captured during matching (such as fingerprint matching). This requires high accuracy. Current small-size image matching systems typically use a method of pre-entering multiple templates and matching each template with the newly acquired sample one by one. If a single sub-template matches successfully, the match is considered successful; otherwise, if no sub-template matches the new sample, the match fails.

[0004] However, due to limitations in the size and shape of the acquisition equipment, this matching method has the following problems: if the new sample is acquired by an acquisition device that is small in size or has an unsuitable shape (such as a narrow strip acquisition device), then templates and samples acquired from different image sources may have some areas with large similarities, which may lead to incorrect matching results.

[0005] How to adjust and optimize the image matching process to improve matching accuracy and achieve high-precision image matching is an urgent problem to be solved. Summary of the Invention

[0006] In view of this, the present disclosure proposes an image matching method, apparatus, electronic device, and chip.

[0007] According to one aspect of this disclosure, an image matching method is provided, comprising:

[0008] Get the image to be matched;

[0009] The image to be matched is matched with multiple templates;

[0010] If the image to be matched successfully matches one of the multiple templates but fails to match the other templates, the matching is verified based on the overlap rate between the image to be matched and the other templates.

[0011] If the verification passes, the image to be matched is determined to be a successful match.

[0012] In one possible implementation, the verification of the match based on the overlap rate between the image to be matched and other templates includes:

[0013] Determine the positional relationship between the image to be matched and the plurality of templates;

[0014] Based on the positional relationship, the overlap rate between the image to be matched and other templates is determined;

[0015] The matching is verified based on the overlap rate between the image to be matched and other templates.

[0016] In one possible implementation, the step of verifying the match based on the overlap rate between the image to be matched and other templates further includes:

[0017] If the overlap rate between the image to be matched and other templates is less than a given threshold, the verification passes and the image to be matched is determined to be successfully matched.

[0018] In one possible implementation, the step of verifying the match based on the overlap rate between the image to be matched and other templates further includes:

[0019] If any of the other templates has an overlap rate with the image to be matched that is not less than a given threshold, then the template with the overlap rate not less than the given threshold will be re-matched with the image to be matched.

[0020] If, among the templates with an overlap rate not less than the given threshold, there exists a given proportion or a given number of templates that successfully match the image to be matched, then the verification passes and the image to be matched is determined to be successfully matched.

[0021] In one possible implementation, the step of verifying the match based on the overlap rate between the image to be matched and other templates further includes:

[0022] If none of the templates with an overlap rate not less than the given threshold are successfully matched with the image to be matched, the verification fails and the image to be matched is determined to be unmatched.

[0023] In one possible implementation, determining the positional relationship between the image to be matched and the plurality of templates includes:

[0024] During the matching process, the positional relationship between the successfully matched template and the image to be matched is obtained;

[0025] By combining the positional relationship between the successfully matched template and the image to be matched, and the positional relationship between the given multiple templates, the positional relationship between the image to be matched and the multiple templates is determined.

[0026] In one possible implementation, the method further includes:

[0027] If the image to be matched successfully matches two or more of the multiple templates, then the image to be matched is determined to be successfully matched.

[0028] If the image to be matched fails to match any of the multiple templates, then the image to be matched is determined to have failed to match.

[0029] According to another aspect of this disclosure, an image matching apparatus is provided, comprising:

[0030] The acquisition module is used to acquire the image to be matched;

[0031] A matching module is used to match the image to be matched with multiple templates;

[0032] The verification module is used to verify the match based on the overlap rate between the image to be matched and other templates when the image to be matched successfully matches one of the multiple templates but fails to match other templates.

[0033] The determination module is used to determine that the image to be matched is successfully matched if the verification passes.

[0034] According to another aspect of this disclosure, an electronic device is proposed, comprising: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above-described method when executing instructions stored in the memory.

[0035] According to another aspect of this disclosure, a chip is provided that includes the above-described means.

[0036] Based on this, this disclosure provides an image matching method. First, an image to be matched is acquired, and then the image is matched against multiple templates. If the image to be matched successfully with one of the multiple templates but fails to match with other templates, the matching is verified based on the overlap rate between the image to be matched and other templates; if the verification passes, the image to be matched is determined to be successfully matched. This disclosure performs a multi-template verification on top of a successful single-template matching, which improves the accuracy of matching and reduces the false matching rate, thereby achieving high-precision image matching.

[0037] Other features and aspects of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0038] The accompanying drawings, which are included in and form part of this specification, illustrate exemplary embodiments, features, and aspects of this disclosure together with the specification and serve to explain the principles of this disclosure.

[0039] Figure 1 This diagram illustrates a situation where the sample does not match the template, but some areas show significant similarity.

[0040] Figure 2 A flowchart illustrating an image matching method according to an embodiment of the present disclosure is shown.

[0041] Figure 3a A flowchart illustrating a matching verification according to an embodiment of the present disclosure is shown.

[0042] Figure 3b This diagram illustrates the determination of the positional relationship between an image to be matched and a plurality of templates according to an embodiment of the present disclosure.

[0043] Figure 4 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. Detailed Implementation

[0044] Various exemplary embodiments, features, and aspects of this disclosure will now be described in detail with reference to the accompanying drawings. The same reference numerals in the drawings denote elements that have the same or similar functions. Although various aspects of the embodiments are shown in the drawings, they are not necessarily drawn to scale unless specifically indicated otherwise.

[0045] In the description of this disclosure, it should be understood that the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0046] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise expressly specified.

[0047] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0048] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0049] In some applications, matching between small images is required. For example, in fingerprint recognition, it is necessary to match a small fingerprint image with a pre-stored fingerprint template to achieve fingerprint recognition.

[0050] The following problems exist in the current small-size image matching process: if the new sample is collected by a small or unsuitable acquisition device (such as a narrow strip acquisition device), then there may be some areas of similarity between the template and the sample image. Figure 1 This diagram illustrates a situation where the sample and template do not match, but some regions show significant similarity. The two images were actually collected from different sources, but they have a large overlapping area and high similarity. Due to limitations in the performance of the matching algorithm, there are limitations in the template matching process for images. Figure 1 The sample shown is prone to mismatch with the template.

[0051] Based on this, embodiments of this disclosure provide an image matching method. This embodiment first acquires an image to be matched, and then matches the image to be matched with multiple templates. If the image to be matched successfully with one of the multiple templates but fails to match with other templates, the matching is verified based on the overlap rate between the image to be matched and other templates; if the verification passes, the image to be matched is determined to be successfully matched. This embodiment, based on successful matching with a single template, performs matching verification based on the overlap rate between the image to be matched and other templates, improving the accuracy of matching and reducing the false matching rate, thereby achieving high-precision image matching.

[0052] The embodiments of this disclosure can be widely applied to most image and texture matching terminal devices, including but not limited to image matching terminal devices for barcodes, fingerprints, characters, and invariant moment images. One exemplary application scenario of this disclosure is fingerprint matching using a fingerprint matching device. Based on the image matching method of this disclosure, after a single fingerprint template is successfully matched, a second matching verification is performed based on the overlap rate between the image to be matched (e.g., a fingerprint sample) and other fingerprint templates, thereby improving the accuracy of fingerprint matching.

[0053] Figure 2 A flowchart of an image matching method according to an embodiment of the present disclosure is shown, such as... Figure 2 As shown, the image matching method may include:

[0054] Step S100: Obtain the image to be matched;

[0055] In this embodiment, an image of the target to be matched can be acquired by a terminal device with image acquisition function. This embodiment does not limit the specific type of the target to be matched or the method of acquiring the image. In one specific embodiment, this step can be denoted as S, where a fingerprint sample to be matched is entered using a terminal device with fingerprint acquisition function (e.g., a smartphone, fingerprint attendance machine).

[0056] Step S200: Match the image to be matched with multiple templates;

[0057] In this context, multiple templates refer to pre-entered data collected multiple times on the same target. This can be the result of collecting data on the same target under different environments, angles, times, and other conditions. The pre-entered templates should be sufficient in number, and there should be no duplication between templates. This embodiment of the disclosure can calculate the positional relationship between multiple templates during the template registration process and use the result as the given positional relationship between the multiple templates. This embodiment of the disclosure does not limit the method for calculating the positional relationship between templates.

[0058] The positional relationship can be represented by the projection transformation relationship between the spaces where the templates are located, for example, as a transformation matrix. In a specific embodiment, multiple templates can be multiple fingerprint templates collected from the same finger, denoted as T0, T1, T2, T3... Taking any fingerprint template T0 as an example, the positional relationship between T0 and other fingerprint templates is denoted as A1, A2, A3... where A1 is the transformation matrix used to project the space where T0 is located onto the space where T1 is located; A2 is the transformation matrix used to project the space where T0 is located onto the space where T2 is located; A3 is the transformation matrix used to project the space where T0 is located onto the space where T3 is located, and so on...

[0059] In this embodiment, matching methods from related technologies such as feature matching algorithms can be used to match the image to be matched with multiple templates. Furthermore, in the matching process, this embodiment can obtain the positional relationship between the successfully matched template and the image to be matched based on the returned matching information, such as the transformation matrix As used to project the space of the image to be matched onto the space of the successfully matched template. Feature matching is an important technology in computer vision, capable of finding corresponding feature points in two or more images to complete tasks such as image matching, stitching, and tracking. Typically, the image feature matching algorithm process includes three steps: feature extraction, feature description, and feature matching. In the feature extraction step, the feature matching algorithm extracts key point information from the image, including the location of the key points. Therefore, the feature matching algorithm can determine the positional relationship between images while performing image matching. This embodiment does not limit the matching information extraction method used in this step or the feature extraction, feature description, feature matching methods, and decision models involved in the feature matching process.

[0060] In one specific embodiment, this step involves performing feature matching between the fingerprint sample S to be matched and multiple fingerprint templates. During the matching process, the positional relationship between the successfully matched fingerprint templates and the fingerprint sample is obtained based on the returned matching information. The feature matching algorithm may involve algorithms such as SURF, SIFT, FAST, and ORB.

[0061] Optionally, in step S300, if the image to be matched successfully matches two or more templates among the plurality of templates, then it is determined that the image to be matched is successfully matched;

[0062] If the image to be matched successfully matches two or more templates among multiple templates, then the embodiments of this disclosure can directly determine that the image to be matched is successfully matched.

[0063] Optionally, in step S400, if the image to be matched fails to match any of the multiple templates, then the image to be matched is determined to have failed to match.

[0064] If the image to be matched fails to match any of the multiple templates, then this embodiment of the disclosure can directly determine that the image to be matched has failed to match.

[0065] Step S500: If the image to be matched successfully matches one of the multiple templates but fails to match other templates, the matching is verified based on the overlap rate between the image to be matched and other templates; if the verification passes, the image to be matched is determined to be successfully matched.

[0066] In cases where only one template out of multiple templates matches successfully, this embodiment does not directly determine whether the image to be matched is successfully matched. Instead, it verifies the matching result based on different scenarios. Based on the overlap rate between the image to be matched and other templates, this embodiment improves the accuracy of the matching and achieves high-precision image matching.

[0067] Figure 3a A flowchart illustrating a matching verification according to an embodiment of the present disclosure is shown. Figure 3a As shown, the matching verification process described in step S500 may include:

[0068] Step S501: Determine the positional relationship between the image to be matched and multiple templates.

[0069] In one possible approach, the above steps may include: obtaining the positional relationship between the successfully matched template and the image to be matched during the matching process; and determining the positional relationship between the image to be matched and the multiple templates by combining the positional relationship between the successfully matched template and the image to be matched, as well as the positional relationship between the given multiple templates.

[0070] In this embodiment, as described in step S200, the positional relationship between multiple templates can be obtained during the template registration process. During the matching process, the positional relationship between the successfully matched template and the image to be matched can be obtained based on the returned matching information. By combining the positional relationship between the successfully matched template and the image to be matched with the given positional relationship between the multiple templates, the positional relationship between the image to be matched and the multiple templates can be determined. In actual calculations, the positional relationship between the image to be matched and the multiple templates can be calculated using the transitive relationship of the transformation matrix. This embodiment does not limit the method of expressing the transformation relationship used in this step (a transformation matrix, or rotation and translation parameters, etc., can be used).

[0071] Figure 3bThis diagram illustrates the determination of the positional relationship between an image to be matched and multiple templates according to an embodiment of the present disclosure. In one specific embodiment, taking the determination of the positional relationship between a fingerprint sample and multiple fingerprint templates as an example, the positional relationship between the multiple fingerprint templates can be obtained during fingerprint template registration. The unique fingerprint template that successfully matches the sample is denoted as T0. Based on the positional relationship between the fingerprint sample S and the unique fingerprint template T0 that successfully matches it, and the given positional relationship between fingerprint template T0 and other templates T1, T2, T3…, the positional relationship between the fingerprint sample S and other fingerprint templates T1, T2, T3… is calculated and denoted as As1, As2, As3… where As1 is the transformation matrix used to project the space where S is located onto the space where T1 is located; As2 is the transformation matrix used to project the space where S is located onto the space where T2 is located; As3 is the transformation matrix used to project the space where S is located onto the space where T3 is located, and so on…

[0072] In practical calculations, As, A1, A2, A3… are known. As1, As2, As3… can be calculated using the transitive relationship of transformation matrices, i.e., Asx = Ax * As. The example used here is left multiplication of a matrix (x' = Ax). If it's right multiplication of a matrix, it's (x' = xA), i.e., Asx = As * Ax, where x = 1, 2, 3, 4…

[0073] Step S502: Determine the overlap rate between the image to be matched and other templates based on the positional relationship.

[0074] Step S503: Based on the relationship between the overlap rate of the image to be matched and other templates and a given threshold, the matching is verified.

[0075] In this embodiment, the overlap rate between the image to be matched and other templates can be determined by combining the positional relationship between the image to be matched and other templates obtained in the previous step, as well as the size of the two images themselves. The overlap rate indicates that the image to be matched and the template overlap in pixel positions in a certain area; this overlap can also be considered a form of similarity. A specific method may include: projecting all pixels of one image onto the coordinate system of the other image based on the pixel coordinates of the images and the positional relationship between the images (e.g., a transformation matrix); counting the number of pixels of the first image falling within the coverage area of ​​the second image; obtaining the size of the overlapping area of ​​the two images by the number of overlapping pixels; and then deriving the overlap rate based on the size of the two images themselves (overlap rate = overlapping area size / image size, where size can be represented by the number of pixels). Further, this embodiment may set an overlap rate judgment threshold and verify the match based on the relationship between the overlap rate of the image to be matched and other templates and the given threshold. Further, while ensuring efficiency and controlling overhead, this embodiment may not limit the number of times the matching verification process is performed. In this way, the embodiments of this disclosure calculate the overlap rate between the image to be matched and other templates, and perform matching verification based on the overlap rate, thereby improving the accuracy of matching and reducing the false matching rate caused by factors such as excessively small or narrow image acquisition size, which result in large similarity between the sample and some areas of the template. This achieves high-precision image matching and matching.

[0076] Step S504: If the overlap rate between the image to be matched and other templates is less than a given threshold, the verification is passed, and the image to be matched is determined to be successfully matched.

[0077] In this embodiment, if the overlap rate between the image to be matched and other templates is less than a given threshold sample, the verification is considered successful, and the image to be matched is determined to be matched successfully. The fact that the overlap rate between the image to be matched and other templates is less than the given threshold indicates that there is no overlapping area between the image to be matched and other templates, or the overlapping area is too small. During the sample image acquisition process, the target to be matched may be too close to the edge, or the acquisition force may be too large. In this case, apart from a specific template that can successfully match the image to be matched, there are indeed no other templates that can successfully match it, and other templates have no overlap with the image to be matched, or their overlap rate is less than the threshold. That is to say, the templates that previously failed to match also have very little overlap with the image to be matched in pixel position; these two conclusions are not contradictory but consistent. In this case, the matching result can be trusted, that is, the matching verification is considered successful, and the image to be matched is considered to be matched successfully.

[0078] Step S505: If there is a template in other templates whose overlap rate with the image to be matched is not less than a given threshold, then the template with the overlap rate not less than the given threshold is re-matched with the image to be matched.

[0079] The single-image feature matching algorithm inevitably suffers from performance issues, with the possibility of failing to match when it should. After determining the overlap rate between the image to be matched and other templates, if it is found that among the other templates that failed to match the image in the first match, there are templates with an overlap rate not less than a given threshold—for example, if one or more templates among the other failed matches have an overlap rate with the image to be matched greater than or equal to the given threshold—it indicates that among these other templates, there are also templates that overlap significantly with the sample in certain regions, suggesting that such templates may have failed to match the image to be matched when they should. In this case, this embodiment of the present disclosure considers the previously obtained matching result of the image to be matched with only one template to be questionable, and re-matches the templates with an overlap rate not less than the given threshold with the image to be matched for matching verification. Furthermore, while ensuring efficiency and controlling overhead, this embodiment of the present disclosure does not limit the number of times the re-matching is performed.

[0080] Step S506: If, among the templates with an overlap rate not less than the given threshold, there are templates that successfully match the image to be matched by a given proportion or a given number of templates, then the verification is passed, and the image to be matched is determined to be successfully matched.

[0081] In this embodiment, a pre-set standard for the proportion or number of templates that successfully re-match can be used to determine whether the verification passes, and no specific limitation is made on the given proportion or number. The "above" in this embodiment includes the stated number. If, among templates with an overlap rate not less than a given threshold, there are templates with a given proportion or number or more that successfully match the image to be matched (for example, assuming a given number of 2), and among the templates that failed to match, 3 templates have an overlap rate greater than the given threshold with the image to be matched, and 2 or 3 of these templates successfully match the image to be matched again, exceeding the given number of 2, it indicates that besides the templates that successfully matched initially, there are other templates that can successfully match the image to be matched, and these successfully matched templates have a large overlap area with the image to be matched, meaning that two or more templates out of all templates successfully match the image to be matched. In this case, this embodiment determines that the matching result is correct. Further, this embodiment determines that the matching verification passes and confirms that the image to be matched is successfully matched. In this way, the present invention performs matching verification based on overlap rate, which improves the accuracy of matching and reduces the false matching rate caused by factors such as small or narrow image acquisition size, which cause large similarity between sample and template regions, thereby achieving high-precision image matching.

[0082] Step S507: If none of the templates with an overlap rate not less than the given threshold can be successfully matched with the image to be matched, then the verification fails and the image to be matched is determined to be unmatched.

[0083] As mentioned earlier, the overlap rate indicates that the image to be matched and the template overlap in some areas, indicating a certain degree of similarity. If the overlap rate of the template is not less than a given threshold, it means that the template and the image to be matched have significant overlap in some areas. If none of the templates with an overlap rate not less than the given threshold successfully match the image to be matched, it means that the aforementioned templates and the image to be matched have significant overlap in some areas, but none of them match. This situation is likely the case described in the background art, where images from different image sources do not match the templates due to factors such as excessively small or narrow image acquisition sizes, yet there is significant overlap in some areas. In this case, the embodiments of this disclosure can determine that a successful match with a single template in the first match is a false match, and the matching verification fails, i.e., it is determined that the image to be matched has not matched successfully with multiple templates, and the matching of the image to be matched has failed. Thus, the embodiments of this disclosure, based on the overlap rate for matching verification, improve the accuracy of matching and reduce the false match rate caused by factors such as excessively small or narrow image acquisition sizes leading to significant similarity between samples and templates in some areas, thereby achieving high-precision image matching.

[0084] The following example uses fingerprint recognition as an illustration to demonstrate an application of this disclosure. In an exemplary application scenario, multiple fingerprint templates T0, T1, T2, T3... of the same finger can be pre-recorded using terminal devices capable of fingerprint acquisition and matching, such as smartphones and fingerprint attendance machines. When a fingerprint image S to be matched is acquired:

[0085] The fingerprint image S to be matched is matched with multiple fingerprint templates T0, T1, T2, T3... for feature matching.

[0086] If the fingerprint image S to be matched successfully matches one of multiple fingerprint templates, but fails to match with other templates, assuming the successfully matched fingerprint template is T0, the positional relationship between the successfully matched fingerprint template T0 and the fingerprint image S to be matched is obtained based on the returned matching information. The matching is then verified based on the overlap rate between the fingerprint image S to be matched and other fingerprint templates. The verification process may include:

[0087] Based on the positional relationships between multiple fingerprint templates, and the positional relationship between the successfully matched fingerprint template T0 and the fingerprint image S to be matched, the positional relationship between the fingerprint image S to be matched and other fingerprint templates is obtained. Based on the positional relationship between the fingerprint image S to be matched and other fingerprint templates, as well as the sizes of the two images themselves, the overlap rate between the fingerprint image S to be matched and other fingerprint templates is determined. Furthermore, the magnitude of the overlap rate is determined, and matching verification is performed based on the results.

[0088] If the overlap rate between the fingerprint image S to be matched and other fingerprint templates is less than a given threshold, it indicates that the overlap rate between the previously unsuccessful fingerprint templates and the fingerprint image S to be matched is very small at the pixel position. In this case, the matching result can be trusted, that is, the matching verification is considered to have passed, and the fingerprint image S to be matched is considered to have been successfully matched.

[0089] If there is a fingerprint template among other fingerprint templates with an overlap rate of not less than a given threshold with the fingerprint image S to be matched, then the fingerprint template with an overlap rate of not less than the given threshold will be matched with the fingerprint image S to be matched again.

[0090] If, among fingerprint templates with an overlap rate not less than a given threshold, there are a given proportion or a given number of templates that successfully match the fingerprint image S to be matched, it indicates that, in addition to the template that successfully matched initially, there are other templates that can successfully match the fingerprint image S to be matched, and these successfully matched fingerprint templates have a large overlap area with the fingerprint image S to be matched, that is, two or more fingerprint templates out of all templates successfully match the fingerprint image S to be matched. In this case, the matching verification passes, and the fingerprint image S to be matched is determined to be a successful match.

[0091] If none of the fingerprint templates with an overlap rate not less than the given threshold can successfully match the fingerprint image S to be matched, the verification fails, and the fingerprint image S to be matched is determined to have failed to match. This situation is likely due to factors such as the image acquisition size being too small or too narrow, resulting in the fingerprint images S from different image sources not matching the fingerprint templates, but having significant overlap in some areas. In this case, the matching result of a single fingerprint template that successfully matches in the first match is considered a mismatch, the matching verification fails, and the fingerprint image S to be matched is determined to have failed to match.

[0092] If the fingerprint image S to be matched successfully matches two or more fingerprint templates from multiple fingerprint templates, then the fingerprint image S to be matched is determined to be a successful match.

[0093] If the fingerprint image S to be matched fails to match with multiple fingerprint templates, then the fingerprint image S to be matched is determined to have failed to match.

[0094] An image matching apparatus is provided according to an embodiment of the present disclosure, comprising:

[0095] The acquisition module is used to acquire the image to be matched;

[0096] A matching module is used to match the image to be matched with multiple templates;

[0097] The verification module is used to verify the match based on the overlap rate between the image to be matched and other templates when the image to be matched successfully matches one of the multiple templates but fails to match other templates.

[0098] The determination module is used to determine that the image to be matched is successfully matched if the verification passes.

[0099] In one possible implementation, the verification of the match based on the overlap rate between the image to be matched and other templates includes:

[0100] Determine the positional relationship between the image to be matched and the plurality of templates;

[0101] Based on the positional relationship, the overlap rate between the image to be matched and other templates is determined;

[0102] The matching is verified based on the overlap rate between the image to be matched and other templates.

[0103] In one possible implementation, the verification of the match based on the overlap rate between the image to be matched and other templates includes:

[0104] If the overlap rate between the image to be matched and other templates is less than a given threshold, the verification passes and the image to be matched is determined to be successfully matched.

[0105] In one possible implementation, the step of verifying the match based on the overlap rate between the image to be matched and other templates further includes:

[0106] If any of the other templates has an overlap rate with the image to be matched that is not less than a given threshold, then the template with the overlap rate not less than the given threshold will be re-matched with the image to be matched.

[0107] If, among the templates with an overlap rate not less than the given threshold, there exists a given proportion or a given number of templates that successfully match the image to be matched, then the verification passes and the image to be matched is determined to be successfully matched.

[0108] In one possible implementation, the step of verifying the match based on the overlap rate between the image to be matched and other templates further includes:

[0109] If none of the templates with an overlap rate not less than the given threshold are successfully matched with the image to be matched, the verification fails and the image to be matched is determined to be unmatched.

[0110] In one possible implementation, determining the positional relationship between the image to be matched and the plurality of templates includes:

[0111] During the matching process, the positional relationship between the successfully matched template and the image to be matched is obtained;

[0112] By combining the positional relationship between the successfully matched template and the image to be matched, and the positional relationship between the given multiple templates, the positional relationship between the image to be matched and the multiple templates is determined.

[0113] In one possible implementation, the device further includes:

[0114] The matching success module is used to determine that the image to be matched is successfully matched if the image to be matched is successfully matched with two or more templates among the plurality of templates;

[0115] The matching failure module is used to determine that the matching of the image to be matched has failed if the image to be matched fails to match any of the multiple templates.

[0116] An electronic device is provided according to an embodiment of the present disclosure, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0117] According to one embodiment of the present disclosure, a chip is provided, the chip including the above-described apparatus.

[0118] For specific embodiments of the above-mentioned devices, electronic devices, and chips, please refer to the Method section.

[0119] For example, electronic devices can also be user equipment (UE), mobile devices, user terminals, terminals, handheld devices, computing devices, or in-vehicle devices, etc. Examples of terminals include: displays, smartphones or portable devices, mobile phones, tablets, laptops, PDAs, mobile internet devices (MID), wearable devices, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical surgery, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, wireless terminals in vehicle-to-everything (V2X) networks, etc.

[0120] Figure 4 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. For example, the electronic device 1900 may be provided as a server or a terminal device. (Refer to...) Figure 4 The electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by memory 1932 for storing instructions, such as application programs, that can be executed by the processing component 1922. The application programs stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processing component 1922 is configured to execute instructions to perform the methods described above.

[0121] Electronic device 1900 may also include a power supply component 1926 configured to perform power management of electronic device 1900, a wired or wireless network interface 1950 configured to connect electronic device 1900 to a network, and an input / output (I / O) interface 1958. Electronic device 1900 can operate on an operating system stored in memory 1932, such as Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, or similar.

[0122] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions that can be executed by a processing component 1922 of an electronic device 1900 to perform the above-described method.

[0123] The above description is merely an exemplary embodiment of the present invention and is not intended to limit the scope of protection of the present invention, which is determined by the appended claims.

[0124] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0125] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0126] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0127] The various embodiments of this disclosure have been described above. These descriptions are exemplary and not exhaustive, and are not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.

Claims

1. An image matching method characterized by, The method comprises: acquiring a to-be-matched image; matching the to-be-matched image with a plurality of templates; in a case where the to-be-matched image is successfully matched with one of the plurality of templates and fails to be matched with other templates, verifying the matching based on an overlap rate of the to-be-matched image and the other templates, wherein the overlap rate = size of an overlapping area / size of an image; in a case where the verification is passed, determining that the to-be-matched image is successfully matched; the verifying the matching based on the overlap rate of the to-be-matched image and the other templates comprises: if the overlap rate of the to-be-matched image and the other templates are all less than a given threshold, the verification is passed.

2. The image matching method of claim 1, wherein, the verifying the matching based on the overlap rate of the to-be-matched image and the other templates comprises: determining a positional relationship between the to-be-matched image and the plurality of templates; determining the overlap rate of the to-be-matched image and the other templates according to the positional relationship; verifying the matching based on the overlap rate of the to-be-matched image and the other templates.

3. The image matching method according to claim 1 or 2, characterized in that, the verifying the matching based on the overlap rate of the to-be-matched image and the other templates further comprises: if there is a template in the other templates whose overlap rate with the to-be-matched image is not less than a given threshold, re-matching the template whose overlap rate is not less than the given threshold with the to-be-matched image; if there are more than a given proportion or a given number of templates in the templates whose overlap rate is not less than the given threshold that are successfully matched with the to-be-matched image, the verification is passed, and it is determined that the to-be-matched image is successfully matched.

4. The image matching method according to claim 3, characterized in that, the verifying the matching based on the overlap rate of the to-be-matched image and the other templates further comprises: if none of the templates whose overlap rate is not less than the given threshold is successfully matched with the to-be-matched image, the verification is failed, and it is determined that the to-be-matched image is failed to be matched.

5. The image matching method of claim 2, wherein, the determining the positional relationship between the to-be-matched image and the plurality of templates comprises: acquiring a positional relationship between the template that is successfully matched and the to-be-matched image in the process of matching; determining the positional relationship between the to-be-matched image and the plurality of templates in combination with the positional relationship between the template that is successfully matched and the to-be-matched image and a given positional relationship between the plurality of templates.

6. The image matching method of claim 1, wherein, the method further comprises: if the to-be-matched image is successfully matched with two or more templates in the plurality of templates, it is determined that the to-be-matched image is successfully matched; if the to-be-matched image is failed to be matched with the plurality of templates, it is determined that the to-be-matched image is failed to be matched.

7. An image matching apparatus characterized by comprising: the apparatus comprises: an acquiring module configured to acquire a to-be-matched image; a matching module configured to match the to-be-matched image with a plurality of templates; a verifying module configured to, in a case where the to-be-matched image is successfully matched with one of the plurality of templates and fails to be matched with other templates, verify the matching based on an overlap rate of the to-be-matched image and the other templates; a determining module configured to, in a case where the verification is passed, determine that the to-be-matched image is successfully matched, wherein the overlap rate = size of an overlapping area / size of an image; the verifying the matching based on the overlap rate of the to-be-matched image and the other templates comprises: If the overlap ratio of the image to be matched with other templates is less than a given threshold, the check passes.

8. An electronic device, comprising: Comprise: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to implement the method of any one of claims 1 to 6 when executing the instructions stored in the memory.

9. A chip, characterized by The chip comprises the apparatus of claim 7.

Images