JP2022524672A - Information recognition methods and devices, systems, electronic devices, storage media and computer programs - Google Patents

Abstract

The present invention relates to information recognition methods and devices, systems, electronic devices and storage media. In the information recognition method, the first device obtains an image sequence of an object to be recognized, which includes an image of at least two frames, and a step of identifying an image of at least one frame from the image sequence as an image to be recognized. And the step of specifying the information to be recognized based on the image to be recognized, and the information to be recognized is transmitted to the second device, and the first recognition is performed to the second device based on the information to be recognized. Includes a step to get the result. The information recognition method includes a step of receiving information to be recognized by a target to be recognized by the second device, and a step of performing first information recognition and acquiring a first recognition result based on the information to be recognized. , Further includes a step of transmitting recognition information to the first device based on the first recognition result. [Selection diagram] Fig. 1

Description

The present invention relates to the field of computer vision, and more particularly to information recognition methods and devices, systems, electronic devices, storage media and computer programs.
<Mutual citation of related applications>
The present invention claims the priority of a Chinese patent application filed on February 28, 2020 with an application number of 20100129842.2, and all the contents of the Chinese patent application are incorporated into the present invention by reference.

With the continuous development of terminal equipment, the number of services that can be completed remotely online is increasing. There are so many services that need to verify the user's identity or register the user's certificate information, so if the user manually enters the certificate information or uploads the ID photo, the interaction flow experience will be poor. , The error rate is high, and the certificate information is easily tampered with. In this way, risks lie in services that require high security.

Therefore, more effective information registration is needed to improve the user experience and ensure the security of the service.

The present invention submits a technical proposal for information recognition.

The first aspect of the present invention provides an information recognition method. In the information recognition method, the first device should acquire an image sequence of an object to be recognized, which includes an image of at least two frames, and the first device should recognize an image of at least one frame from the image sequence. The step of specifying as an image, the step of specifying the information to be recognized based on the image to be recognized, and the information to be recognized are transmitted to the second device, and the information to be recognized is sent to the previous second device. Includes a step of acquiring the first recognition result based on.

In one possible implementation, the step of identifying at least one frame of an image from the image sequence as an image to be recognized by the first device is that the first device identifies the recognition state and / or image of the image sequence. Based on the quality, an image of at least one frame from the image sequence is specified as the image to be recognized.

In one possible realization method, the first device selects at least one frame of an image from the image sequence as the image to be recognized based on the recognition state of the image sequence. , The second information recognition is performed for at least a part of the images in the image sequence, and one or more of the second recognition results are acquired, and the first device is the one or more of the second. Acquiring the reference recognition result based on the recognition result, comparing each of the second recognition results with the reference recognition result, and acquiring the reliability of each of the second recognition results. The reliability of the identified image to be recognized includes specifying each image corresponding to at least a part of all the second recognition results as the image to be recognized based on the reliability. It is higher than the reliability of the non-recognizable image in the image sequence.

In one possible implementation, the first device selects at least one frame of image from the image sequence as an image to be recognized, based on the image quality of the image sequence. Acquiring the image quality of at least a part of the image sequence in the image sequence with at least one evaluation criterion, and the first device being larger than the threshold value in the corresponding evaluation criterion in the image sequence. It comprises identifying at least one frame of image of the image quality as the image to be recognized.

In one possible implementation, the evaluation criteria include at least one of sharpness, perfection, high light conditions, dim light conditions, and shielding conditions.

In one possible implementation, after the image to be recognized has been identified, the method further comprises storing at least one frame in the image to be recognized.

In one possible implementation, the step of identifying information to be recognized by the first device based on the image to be recognized is a first encryption of the image to be recognized by the first device. Includes processing and / or signature processing to obtain information to be recognized.

In one possible implementation method, the first encryption process includes encoding / encryption of the image to be recognized to acquire the first encryption information, and the signature process is a signature process. It includes adding the signature information of the first device to the image to be recognized.

In one possible implementation, the object to be recognized includes a certification card object and / or a form object, and the first recognition result is the text, identifier, and picture recorded in the object to be recognized. Includes at least one term of.

A second aspect of the present invention provides an information recognition method. In the information recognition method, the step of receiving the information to be recognized by the second device and the information to be recognized by the second device is performed by the second device, and the first recognition result is obtained. The acquisition includes a step of acquiring the recognition information and a step of transmitting the recognition information to the first device based on the first recognition result.

In one possible realization method, the step of performing the first information recognition on the information to be recognized by the second device and acquiring the first recognition result is the information to be recognized by the second device. Acquiring the included image to be recognized, performing anti-counterfeiting detection on the image to be recognized, acquiring the detection result, and when the detection result is acceptable, the second device is said to have said. The first information recognition is performed on the image to be recognized, and the first recognition result is acquired.

In one possible realization method, acquiring the image to be recognized included in the information to be recognized by the second device acquires the signature information included in the information to be recognized by the second device. That is, when the acquired signature information matches the signature information of the first device, the second device decodes the first encrypted information included in the information to be recognized, and the image to be recognized. To get and include.

In one possible realization method, the second device performs anti-counterfeiting detection on the image to be recognized and obtains the detection result by classifying the image to be recognized by the second device. When the classification result of the image to be recognized is acquired and the image to be recognized is an image obtained by photographing the object to be recognized, the second classification result is shown. The classification result indicates that the device records the detection result as acceptable and / or the image to be recognized is an image obtained by photographing a copy or duplicate of the object to be recognized. In some cases, the second device records the detection result as a failure.

In one possible realization method, the second device recognizes the first information for the image to be recognized, and the second device obtains the first recognition result in the optical character recognition OCR model. OCR recognition is performed on the image to be recognized, and the first recognition result is acquired.

In one possible realization method, in the step of performing the first information recognition on the information to be recognized by the second device and acquiring the first recognition result, the second device performs the first recognition result. Further includes determining whether or not a match with a preset rule and acquiring the determination result.

In one possible realization method, the step of transmitting the recognition information to the first device by the second device based on the first recognition result is such that the second device has the first recognition result. 2 Performing the encryption process, or performing the second encryption process on the first recognition result and the determination result to acquire the second encryption information, and the second device performing the second encryption process. It includes transmitting the information as the recognition information to the first device.

In one possible implementation, the method further comprises the step of storing at least one frame in the image to be recognized by the second device.

A third aspect of the present invention provides an information recognition device. The information recognition device identifies an image sequence acquisition module for acquiring an image sequence of an object to be recognized, which includes an image of at least two frames, and an image of at least one frame from the image sequence as an image to be recognized. The specific module, the recognition target information generation module for specifying the information to be recognized based on the image to be recognized, and the information to be recognized are transmitted to the second device, and the recognition is sent to the second device. It is provided with a recognition target information transmission module for acquiring a first recognition result based on information to be.

A fourth aspect of the present invention provides an information recognition device. The information recognition device includes a receiving module for receiving information to be recognized by an object to be recognized, and a recognition module for performing first information recognition on the information to be recognized and acquiring a first recognition result. And a recognition information transmission module for transmitting transmission recognition information to the first device based on the first recognition result.

A fifth aspect of the present invention provides an electronic device. The electronic device comprises a processor and a non-temporary storage medium for storing processor executable instructions, the processor being configured to implement the information recognition method of the first aspect.

A sixth aspect of the present invention provides an electronic device. The electronic device comprises a processor and a non-temporary storage medium for storing processor executable instructions, the processor being configured to implement the information recognition method of the second aspect.

A seventh aspect of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the information recognition method of the first aspect is carried out.

An eighth aspect of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by a processor, the information recognition method of the second aspect is carried out.

A ninth aspect of the present invention provides a computer program. The information recognition method of any one of the above embodiments is performed when the computer program is executed by the processor.

In the embodiment of the present invention, an image sequence of an object to be recognized is acquired, and an image of at least one frame is selected as an image to be recognized based on the image sequence, so that the image to be recognized should be recognized according to the image to be recognized. Information is transmitted to the second device, and the second device is made to acquire the first recognition result based on the information to be recognized. By the above process, in the process of information recognition, it is possible to automatically select a frame for the object to be recognized and then perform recognition via the second device. By automatic frame selection, the image for recognition can have higher image accuracy and recognition effect than the directly acquired image, so that the finally acquired first recognition result becomes more accurate and at the same time. The failure rate of the information recognition process is also reduced, and the user experience in the information recognition process is improved.

It should be understood that the general description and the detailed description described above are merely exemplary and interpretive and are not intended to limit the invention. In the following, exemplary embodiments will be described in detail with reference to the drawings, and other features and embodiments of the present invention will be clarified.

The drawings herein are incorporated into the specification to form a portion of the specification and are used to describe the description of the specification as well as to explain the technical proposal of the present invention, while showing examples conforming to the present invention.
The flowchart of the information recognition method which concerns on one Embodiment of this invention is shown. The flowchart of the information recognition method which concerns on one Embodiment of this invention is shown. The block diagram of the information recognition apparatus which concerns on one Embodiment of this invention is shown. The block diagram of the information recognition apparatus which concerns on one Embodiment of this invention is shown. A schematic diagram of an application example according to the present invention is shown. The block diagram of the electronic device which concerns on embodiment of this invention is shown. The block diagram of the electronic device which concerns on embodiment of this invention is shown.

Hereinafter, various exemplary embodiments, features and embodiments of the present invention will be described in detail with reference to the drawings. The same reference numerals in the drawings indicate elements having the same or similar functions. Although the drawings show various aspects of the embodiments, it is not necessary to draw the drawings to scale unless exclusively shown.

The term "exemplary" here means "exemplary, exemplary, or descriptive." No embodiment described herein as "exemplary" is to be construed as superior or better than any other embodiment.

The term "and / or" in the text merely describes the relationship of the related object and indicates that three types of relationships can exist. For example, A and / or B can represent three cases: A exists alone, A and B exist at the same time, and B exists alone. Further, the term "at least one kind" in the text indicates any one of a plurality of kinds or any combination of at least two kinds of a plurality of kinds. For example, including at least one of A, B, and C may indicate selecting any one or more elements from the set composed of A, B, and C.

Also, in order to better explain the invention, a large amount of specific details are given in the specific embodiments below. As will be appreciated by those skilled in the art, the invention can be similarly practiced without some specific details. In some embodiments, methods, means, elements and circuits well known to those of skill in the art are not described in detail so that the gist of the invention is more prominent.

FIG. 1 shows a flowchart of an information recognition method according to an embodiment of the present invention. The method is applicable to the first device. The first device may be a device capable of collecting an image sequence of an object to be recognized, that is, a device having an information collecting function. In one possible implementation method, the first device may be a hardware device such as a terminal device having a photographing function or another processing device. Terminal devices include user devices (User Equipment, UE), mobile devices, user terminals, terminals, mobile phones, cordless phones, personal digital assistants (PDAs), handheld devices, computing devices, in-vehicle devices, wearable devices, etc. May be.

In some possible implementations, the operation of collecting an image sequence of objects to be recognized should be performed by a single front-end device such as a camera head and then collected and recognized via the front-end device. The target image sequence may be transmitted to the first device. Next, the information recognition method is implemented by a method in which the processor of the first device calls a computer-readable instruction stored in the memory.

As shown in FIG. 1, in one possible implementation method, the information recognition method is applicable to the first device and includes the following steps.

In step S11, the image sequence of the object to be recognized is acquired. The image sequence contains at least two frames of images.

In step S12, an image of at least one frame is specified as an image to be recognized from the image sequence.

In step S13, the information to be recognized is specified based on the image to be recognized.

In step S14, the information to be recognized is transmitted to the second device, and the second device is made to acquire the first recognition result based on the information to be recognized.

The object to be recognized is an object to be recognized as information, and the object to be recognized may have a plurality of types of expression forms according to the actual demand for information recognition. For example, the object to be recognized may be an object whose content has a unified standard, such as a certification card object or a form object. The target of the proof card may be an identification card, a pass card, a bank card, or the like, and the target of the form may be a table or the like whose format is specified.

The image sequence of the object to be recognized may be an image sequence obtained by collecting images for the object to be recognized by the first apparatus or a group of images. In one possible implementation, the first device may acquire an image sequence of the object to be recognized by performing continuous scanning or video recording on the object to be recognized. In one possible implementation, the first device may acquire a multi-frame image of the object to be recognized by taking and collecting photographs of the object to be recognized at a constant frequency. .. The collected images of a plurality of frames may form an image sequence in the order before and after the collection time. Of course, the multi-frame images collected for the object to be recognized do not have to be time related to each other. At that time, one group of images may be configured instead of one image sequence.

In step S12, the image to be recognized may be an image of one frame or a plurality of frames selected by the first device from the acquired image sequence. In one possible realization method, a high quality image of only one frame may be selected as an image to be recognized from the image sequence. In one possible implementation, a high quality multi-frame image may be selected from the image sequence as the image to be recognized. The number of selected images to be processed can be flexibly specified depending on the actual case. After that, a case where one frame image is selected as an image to be recognized will be described as an example. When selecting an image of a plurality of frames as an image to be recognized, the realization principle is similar to the case of selecting an image of one frame, and the details will not be described again. However, it should be understood that the case of selecting an image of a plurality of frames as an image to be recognized is also included in the description range of the present invention.

In step S13, after the image to be recognized is specified, the information to be recognized may be specified based on the image to be recognized. The information to be recognized may be information including contents that need to be recognized in the object to be recognized. In one possible implementation, the information to be recognized may be a directly selected image to be recognized. In one possible realization method, the information to be recognized may be information obtained by performing a certain process on the image to be recognized. For the method of specifying the information to be recognized, each subsequent disclosure embodiment can be referred to.

In step S14, the information to be recognized may be transmitted to the second device, and the second device may acquire the first recognition result based on the information to be recognized. The second device may be a device having an information recognition function. The second device may be realized by hardware or software. In one possible implementation, the second device may be a hardware device such as a terminal device, server or other processing device. Here, the implementation method of the terminal device can be referred to in each of the above-mentioned disclosure embodiments, and will not be repeatedly described here. In one possible implementation method, the second device may be a cloud server, a local server, or the like when it is a server. When the second device is realized by software, the function of the second device can be realized, for example, by the processor of the CPU reading a computer program in the storage medium.

The first recognition result may be the result obtained by performing recognition based on the information to be recognized by the second device, and the specific type and content of the first recognition result are the expression method of the object to be recognized. It may be different depending on. The examples of the present invention are not limited. In one possible implementation, the object to be recognized may include a certification card object and / or a form object, and the first recognition result is the text, characters, icons, identifiers and identifiers recorded in the object to be recognized. It may contain at least one term of a picture or the like. Since the object to be recognized of the certification card object or the form object has a certain format norm, the first recognition may be completed based on the standardized content. The subject of the proof card may include, but is not limited to, an ID card, a bank card, and a pass card. The form target may include, but is not limited to, warranty and invoice. In general, the acquired first recognition result may have a type of adjustment depending on the actual demand and the standardized content possessed by the corresponding object to be recognized. For example, when the object to be recognized is an ID card, the first recognition result is one of the contents such as name, date of birth, address, ID number, and human image written on the front of the ID card. It may include a term or a plurality of terms. Of course, the first recognition result may be a further recognition result acquired based on the above content. For example, by further recognizing the recognized ID number, data such as the birthplace of the person to which the identification card belongs is specified.

As can be seen from the above-mentioned disclosure embodiment, the first recognition result is the content recorded in the object to be recognized, for example, a recorded text, a picture, an identifier for indicating the type of the object to be recognized, or the like. May be good. In one example, when the target to be recognized is the certification card target, the first recognition result may be a text included in the certification card target, for example, an address in an identification card, a bank card number in a bank card, or the like. .. Each subsequent disclosure embodiment will be described by exemplifying that the first recognition result is a text. When the first recognition result is another type such as a picture or an identifier, it may be flexibly expanded based on each subsequent disclosure embodiment and will not be described in detail again.

Further, for how to acquire the first recognition result based on the information to be recognized by the second device, it is sufficient to refer to each subsequent disclosure embodiment for the specific realization method.

In the embodiment of the present invention, an image sequence of an object to be recognized is acquired, and an image of at least one frame is selected as an image to be recognized from the image sequence, so that the image is recognized according to the selected image to be recognized. The information to be recognized is specified, the information to be recognized is transmitted to the second device, and the second device is made to acquire the first recognition result based on the information to be recognized. By the above process, in the process of information recognition, it is possible to automatically select a frame for the object to be recognized and then perform recognition via the second device. Since the image with the best image quality can be selected by automatically selecting the frame, the image for recognition has higher image accuracy and recognition effect than the directly acquired image, and thus is finally acquired. The first recognition result becomes more accurate, the failure rate of the information recognition process is reduced, and the user experience in the information recognition process is improved.

Even if the first device acquires an image sequence of a target to be recognized by using any one of the methods in step S11 and then specifies an image of at least one frame from the image sequence as an image to be recognized by step S12. good. This process may be flexibly determined according to the actual situation as to how to specifically specify the image to be recognized. In one possible implementation, step S12
It may include selecting at least one frame of image as the image to be recognized based on the recognition state and / or image quality of the image sequence.

The recognition state may indicate the state of the image content in the recognized image sequence, for example, the reliability of the recognized image content. It is stated that the better the recognition state of the image content, the more complete and accurate the recognizable content contained in the image. That is, the process of specifying an image to be recognized based on the recognition state may be understood as specifying an image to be recognized based on the good recognition state of images of different frames in the image sequence. The first recognition result acquired based on the image to be recognized can be more complete and have higher accuracy.

The image quality may be the quality of each frame image in the image sequence, and the high or low of the image quality may be determined according to a preset quality index. For example, the quality index may include one or more of sharpness, perfection, high light conditions, dim light conditions, shielding conditions, and the like, and is not limited in the text. The higher the image quality, the easier it is for the frame image to be recognized, and the more accurate the recognition result is. That is, the process of specifying an image to be recognized based on the image quality may be understood as specifying an image to be recognized based on the level of image quality between images of frames having different image sequences. The first recognition result obtained based on the image to be recognized is similarly more accurate and has an excellent recognition effect.

The specific realization method for specifying the image to be recognized based on the recognition state or the image quality may be flexibly selected according to the actual situation as well, and each subsequent disclosure embodiment can be referred to.

As can be seen from the above-mentioned disclosure embodiment, there are two types of specifying an image to be recognized from an image sequence: specifying based on the recognition state of the image sequence and specifying based on the image quality of the image sequence. May include the method of. In one possible realization method, in the process of identifying an image to be recognized, it is specified based only on the recognition state or only the image quality, that is, the first device automatically recognizes by one of the methods. You may specify the image to be used. In one possible realization method, the image may be specified based on both the recognition state and the image quality, that is, the image to be recognized by the first device in combination of the two methods may be specified. Specifically, in one example, the first device identifies the corresponding image to be recognized based on the recognition state and the image quality, respectively, and then both of these images specified by these two methods are used. Step S13 may be entered as the final image to be recognized. In one example, the first device identifies a corresponding image to be recognized based on the recognition state and image quality, respectively, and then finally selects one frame or several frames from the corresponding images in a certain manner or randomly. You may select it as an image to be recognized and enter step S13. In one example, the first device may provide the user with two options: to specify an image to be recognized based on the recognition state and to specify an image to be recognized based on the image quality. good. That is, the user is allowed to select which method should be used to specify the image to be recognized.

By specifying the image to be recognized based on the recognition state and / or the image quality of the image sequence, the quality of the image to be recognized can be ensured, and the final acquisition based on this image to be recognized is the first. 1 The recognition result becomes more accurate and has higher accuracy, while it is possible to flexibly select a different image identification method to be recognized in different cases, which improves the flexibility of the information recognition method.

In one possible implementation, selecting at least one frame of image as the image to be recognized based on the recognition state of the image sequence is the second information for at least some of the images in the image sequence. It may include performing recognition respectively and acquiring one or more second recognition results. The reference recognition result is acquired based on one or more second recognition results. The reliability of each second recognition result is obtained by comparing each second recognition result with the reference recognition result. Based on the reliability, each image corresponding to at least a part of all the second recognition results is specified as an image to be recognized. The reliability of the identified image to be recognized is higher than the reliability of the non-recognizable image in the image sequence. The image itself, which is not an image to be recognized, is an image that is not used for information recognition.

The second information recognition may be to specify the information to be recognized by performing an information recognition operation on the image sequence of the target to be recognized by the first device. In the above disclosure embodiment, it is mentioned that the first recognition result is acquired based on the information to be recognized by the second device, which is to perform the corresponding information recognition operation based on the information to be recognized by the second device. It means that it is also good. In order to distinguish the information recognition operations of different implementing subjects, in the embodiment of the present invention, the operation executed based on the information to be recognized by the second device is described as the first information recognition, and the acquired result is the first recognition. The operation performed by the first device for at least a part of the images in the image sequence is referred to as a second information recognition, and the acquired result is referred to as a second recognition result. The specific recognition methods of the first information recognition and the second information recognition may be the same or different. In one possible realization method, the second information recognition is the second because the main purpose of the second information recognition is to specify the image to be recognized rather than to specify the final recognition result. 1 It may be different from information recognition. In the second information recognition, a recognition method having a low recognition accuracy may be selected, and in the first information recognition, a recognition method having a high recognition accuracy may be selected. In one example, since information recognition recognizes text information, both the second information recognition and the first information recognition can be realized by optical character recognition (OCR, Optical Character Recognition). In the embodiment of the present invention, the OCR model scale used for the second information recognition is used for the first information recognition because the recognition accuracy of the second information recognition does not need to reach the recognition accuracy requirement of the first information recognition. It may be smaller than the OCR model scale. In this way, the realization of the second information recognition can be ensured, the realization speed of the second information recognition can be guaranteed, and the speed of the entire information recognition process can be further improved.

As can be seen from the above process, in the process of performing the second information recognition, the first device may perform the second information recognition for any of the images of each frame in the image sequence, and the first device may perform the second information recognition in the image sequence. The second information recognition may be performed for a part of the images of. Specifically, which frame image is selected to perform the second information recognition may be flexibly determined according to the actual situation, and is not limited in the embodiment of the present invention. Each subsequent disclosure embodiment will be described by exemplifying the second information recognition for the image of each frame in the image sequence, and in other cases, it can be flexibly expanded. In one possible realization method, when the second information recognition is performed for the image of each frame in the image sequence, the second recognition result of each frame image may be acquired respectively. Since the image sequence contains at least two frames of images, at least two second recognition results are correspondingly available. Therefore, the reference recognition result may be acquired based on at least two second recognition results. Here, the reference recognition result may be a relatively complete recognition result integrated based on at least two second recognition results. For example, among a plurality of second recognition results obtained by performing second information recognition on a plurality of frames of an image, there is a second recognition result lacking the first half of the content to be recognized, and the second recognition result is recognized. There may be a second recognition result that lacks the second half of the content to be recognized, and there may be a second recognition result that lacks one or several fields of the content to be recognized. Therefore, after statistics on these second recognition results, a relatively complete and accurate recognition result can be restored, and this relatively complete and accurate recognition result may be a reference recognition result. The specific restoration method is not limited to the embodiment of the present invention, and can be flexibly selected according to an actual situation. In one example, the reference recognition result may be specified by traversing each second recognition result, statistic of the recognition content that appears repeatedly in the second recognition result, and integrating according to the position of the recognition content that appears repeatedly. ..

After the reference recognition result is specified, each second recognition result may be compared with the reference recognition result to obtain the reliability of each second recognition result. The reliability represents the degree of polymerization of each second recognition result and the reference recognition result. When it is text information that is recognized, the reliability may represent the text overlap accuracy rate between each second recognition result and the reference recognition result, and the higher the reliability, the more the second recognition result is referred to. It means that it is close to the recognition result.

After the reliability of each second recognition result is acquired, the image to be recognized may be specified based on the magnitude of the reliability. The higher the reliability, the closer the second recognition result is to the reference recognition result. Therefore, the higher the reliability of the image corresponding to the second recognition result, the more the recognition information contained is based on the image. The accuracy of information recognition is also improved. As already described in the above disclosure embodiment, the image to be recognized may be one frame or a plurality of frames, so that the image having the highest reliability of one frame or a plurality of frames should be recognized. May be. Alternatively, one reliability threshold value may be set, and an image corresponding to the second recognition result having a reliability higher than the threshold value may be recognized as an image. Alternatively, the image corresponding to the second recognition result of 20% before ranking the reliability may be used as the image to be recognized. The examples that specify these images to be recognized are not limited, and other methods or other numerical values may be adopted.

By the above process, regardless of the quality of the camera head and the light environment, the relatively excellent image can be selected as the image to be recognized, so that information recognition can be performed. It is possible to improve the accuracy of the information recognition result as much as possible while ensuring the smooth realization of the process, and the acceptability of the information recognition method is also greatly improved.

In one possible implementation, selecting at least one frame of image as the image to be recognized based on the image quality of the image sequence is at least a portion of the image sequence in at least one evaluation criterion. It may include acquiring the image quality of each of the images of. Of the image sequences, at least one frame of image with image quality greater than the threshold in the corresponding evaluation criteria is specified as the image to be recognized.

In the process of acquiring the image quality of the image in the image sequence, the image quality of the image of each frame in the image sequence may be acquired respectively, and the image quality of a part of the frame image in the image sequence may be acquired. You may get it. The specific frame to be selected and how to be selected may be flexibly determined according to the actual situation. The examples of the present invention are not limited. Each subsequent disclosure embodiment will be described by taking as an example the acquisition of the image quality of the image of each frame in the image sequence. The implementation method in other cases can be flexibly expanded with reference to each of the following disclosure embodiments.

As already described in the above disclosure embodiment, the image quality may be the quality of the image in the image sequence, and for any one frame image, it is not possible to evaluate what the quality of the image will be. They may have different criteria, for example, they may be judged from different aspects such as sharpness or perfection. Therefore, image quality may be analyzed with different evaluation criteria as the judgment criteria differ. Specifically, analyzing image quality according to a certain evaluation standard or some evaluation criteria, and what kind of judgment standard each evaluation standard corresponds to, depends on the actual situation. It may be set flexibly. Later, when identifying an image to be recognized by comparing the image quality with the threshold value, it is not necessary to consider all the evaluation criteria, and the image quality is compared with the selected evaluation criteria. In one possible implementation, the evaluation criteria may include one or more of sharpness, perfection, high light conditions, dim light conditions and shielding conditions. Here, the sharpness may indicate whether or not there is a situation in which characters or images such as focal blur and motion blur cannot be recognized in the image. The perfect fifth may indicate whether or not all the corners of the object to be recognized (for example, a certificate) in the image are within the image range. High light conditions may indicate whether the image has overexposure or intense reflections. The dim light situation may indicate whether or not there is a situation in the object to be recognized (for example, a certificate) in the image, such as the whole or partial brightness being too dark to recognize characters or images. The shielding situation may indicate whether or not there is a situation in which the object to be recognized (for example, a certificate) in the image is shielded by another object. In a practical application, only one of the evaluation criteria may be considered, or a plurality of evaluation criteria thereof may be considered at the same time. In one example, five evaluation criteria such as sharpness, perfection, high light condition, dim light condition, and shielding condition may be considered at the same time. In such a case, after acquiring the image quality of each frame image in the image sequence according to these five evaluation criteria, the sharpness quality of each frame image is larger than the corresponding sharpness threshold value. Whether the perfection quality is greater than the corresponding perfection threshold, whether the strong light quality is greater than the corresponding strong light threshold, and whether the dim light quality is greater than the corresponding dim light threshold. And whether the shielding quality is greater than the corresponding shielding threshold, respectively. When there is an image of one frame or several frames satisfying the requirement larger than the threshold value corresponding to any of the five types, the image satisfying the requirement may be used as the selection image. In one example, when the evaluation criteria include the above five criteria, the image quality of some of the criteria of the image may be acquired. For example, quality may be obtained based on only three evaluation criteria: image sharpness, perfection, and shielding status. In such cases, when identifying the image to be recognized later, it is only necessary to consider whether the sharpness quality, perfection quality, and obstruction status quality of each frame image are larger than the corresponding threshold values. , The comparison situation of high light quality and dim light quality may be ignored.

Further, in one possible implementation method, when the number of images satisfying the requirements is larger than the number of images to be recognized, the image qualities of the images satisfying these requirements are further compared to obtain the total image quality. High N images may be selected as images to be recognized. N is the number of images to be recognized required. Specifically, the calculation method of the total quality may be set according to the actual situation, and the specific calculation method may be selected according to the actual situation. For example, one weight may be set for each image quality in each evaluation standard, the weighted average image quality of each frame image may be calculated, and the weighted average image quality may be set as the total image quality or the like. In one possible implementation, no image may meet the requirements, and overall image quality is achieved by comparing the image qualities of these images to ensure the smooth progress of the information recognition process. N high-quality images may be selected as images to be recognized.

In one possible realization method, the process of acquiring an image sequence of an object to be recognized and the process of specifying a selected image based on image quality may be performed at the same time. That is, while collecting the image sequence of the object to be recognized, the image quality may be evaluated for the already collected images. If the already collected image contains an image that meets the image quality requirements of each evaluation criterion, such an image should be recognized and the continuous collection of the image sequence of the object to be recognized should be stopped. May be good. In such a case, the image itself of the last frame of the acquired image sequence may be an image to be recognized.

Further, the threshold value corresponding to the image quality in each evaluation standard is not limited in the embodiment of the present invention and may be set according to an actual situation, and the threshold value of the image quality in different evaluation criteria is the same. It may or may not be different.

By acquiring the image quality of at least a part of the image of the image sequence in at least one evaluation criterion, the image of at least one frame in which the image quality in each evaluation criterion is larger than the corresponding threshold is obtained. The image should be recognized. Since a high-quality image to be recognized can be selected from the image sequence by the above process, the first recognition result obtained by performing information recognition based on the image to be recognized has higher accuracy. The accuracy of information recognition is greatly improved.

In one possible realization method, the image to be recognized may be saved after the image to be recognized is specified by step S12. Therefore, in one possible implementation, after the image to be recognized has been identified, the method submitted in the embodiments of the present invention may further include the step of preserving at least one frame in the image to be recognized. ..

The storage position of the image to be recognized is not limited, and may be stored in the first device, may be stored in the second device, or may be stored in the first device and the second device at the same time. This allows the stored image to be recognized to be read directly if there is an image that needs to be used for an object to be recognized later or if the object to be recognized needs to be recognized again. Therefore, the efficiency and the user's experience are greatly improved. The number of storage frames of the image to be recognized is not limited, and may be flexibly determined according to the size of the storage space of the first device and the second device. In one possible implementation method, if the image to be recognized is multiple frames, all the images to be recognized may be saved, and one frame or some frames may be selected and saved. You may. In one possible realization method, when the image to be recognized is one frame, the image to be recognized may be directly saved.

Further, the identification of the image to be recognized based on the recognition state and the identification of the image to be recognized based on the image quality may be performed simultaneously or independently. Correspondingly, saving at least one frame in the image to be recognized may be performed simply after identifying the image to be recognized based on the recognition state (ie, the recognition specified based on the recognition state). It may be performed after identifying the image to be recognized based on the image quality (ie, storing only the image to be recognized based on the image quality). At the same time, it may be performed after identifying the image to be recognized based on the recognition state and the image quality (that is, the image to be recognized comprehensively identified based on the above two types of identification method is saved). .. In one possible implementation, the image to be recognized identified based on the image quality has better image quality than the image to be recognized identified based on the recognition state, thus resulting in a passing image quality. Only the image to be recognized identified based on it may be saved.

As can be further understood from each of the above-mentioned disclosure examples, after the image to be recognized is specified, the information to be recognized may be specified based on the image to be recognized by step S13. In one possible implementation, step S13
The image to be recognized may be subjected to a first encryption process and / or a signature process to acquire information to be recognized.

The method for realizing the first encryption process and the signature process is not limited, and may be flexibly selected according to the actual situation. In one possible implementation, the first encryption process may include encoding and encrypting the image to be recognized to obtain the first encryption information, and the signature process may be the first. 1 It may include adding the signature information of the device to the selected image. Here, what encryption method is used to encrypt the image to be recognized is not limited in the embodiment of the present invention, and any encryption method is used as the first encryption processing realization method. Can be done. The signature information of the first device may be information including the first device identification identifier, and the specific information content and format thereof are not limited in the embodiments of the present invention. In one example, the signature information of the first device may be the signature information in the software development kit (SDK, Software Development Kit) in the first device. Similarly, the specific addition position and method for adding the signature information of the first device to the image to be recognized is not limited to the embodiment of the present invention, and may be flexibly selected according to the actual situation.

One or two of the first encryption processing and the signature processing may be performed on the image to be recognized. When both the first encryption processing and the signature processing are performed on the image to be recognized, these two types of processing may be performed at the same time, or may be performed before and after in a certain order, and may be performed in an actual order. It may be selected flexibly according to the situation. In one possible implementation method, the first encryption process and the signature process may be performed on the images to be recognized in order. That is, the image to be recognized is re-encoded in a certain encryption format, and then the information obtained by encoding / encryption is packaged with the signature information of the first device to acquire the information to be recognized. do. In one possible implementation method, the signature processing and the first encryption processing may be performed on the images to be recognized in order. That is, the image to be recognized and the signature information of the first device are packaged, and then the packaged information is re-encoded in a certain encryption format to acquire the information to be recognized.

Information because the first encryption process can effectively reduce the possibility of leakage of certification card information when the object to be recognized is an identification card or an object with high security demand such as a bank card. The safety of the recognition process can be improved. Since the device information of the first device is included in the information to be recognized by the signature process, it is convenient to verify the authority for the information to be recognized when the second device recognizes the information, and the information to be recognized is The possibility of tampering is reduced, the safety of the information recognition process is improved, and the accuracy of the information recognition result is also improved.

After the information to be recognized is acquired, the information to be recognized may be transmitted to the second device in step S14. The specific transmission method is flexibly specified based on the connection relationship between the first device and the second device. In one possible implementation, if the first device is a terminal device and the second device is a server, the first device is via a network connected between the first device and the second device. Then, the information to be recognized may be uploaded to the second device.

In one possible implementation method, the recognition information fed back by the second device may be received after transmitting the information to be recognized to the second device. Since the first recognition result can be acquired based on the information to be recognized by the second device, the recognition information may be information related to the first recognition result. For the specific realization method of the recognition information, the following disclosure examples can be referred to. The method for receiving the recognition information by the first device is not limited, and may be flexibly determined according to the communication method between the first device and the second device, and will not be described repeatedly here.

After receiving the recognition information, the first device may display the recognition information to the user, or may store the recognition information at the same time as displaying the recognition information. Specifically, how to apply the recognition information may be flexibly determined according to the actual demand of the first device, and is not limited in the embodiment of the present invention.

FIG. 2 shows a flowchart of an information recognition method according to an embodiment of the present invention. This method is applicable to the second device, and the method for realizing the second device may refer to the above-mentioned disclosure embodiments, and therefore will not be repeatedly described here.

As shown in FIG. 2, in one possible implementation method, the information recognition method is applicable to the second device and includes steps S21 to S23. In step S21, the information to be recognized of the object to be recognized is received. In step S22, the first information recognition is performed on the information to be recognized, and the first recognition result is acquired. In step S23, the recognition information is transmitted to the first device based on the first recognition result.

Since the information to be recognized and the information to be recognized referred to in the above-mentioned disclosure embodiment match, they will not be described repeatedly here. The method for receiving the information to be recognized by the second device may be flexibly determined according to the method for transmitting the information to be recognized by the first device, and is not limited in the embodiment of the present invention. After receiving the information to be recognized, the second device may perform the first information recognition in step S22, and the specific recognition process can be referred to each of the following disclosure embodiments. The second device may perform the first information recognition, acquire the first recognition result, and then transmit the recognition information to the first device based on the first recognition result in step S23. Here, the recognition information may be acquired based on the first recognition result. In one possible realization method, the first recognition result may be directly used as recognition information. In one possible realization method, recognition information may be acquired by separately performing some other processing or content based on the first recognition result. For the specific content of recognition information and the generation method, each disclosure embodiment can be referred to later.

By receiving the information to be recognized of the object to be recognized, the first information is recognized for the information to be recognized and the first recognition result is acquired. Therefore, the recognition information is first based on the first recognition result. Send to the device. Information recognition for the object to be recognized is effectively realized by the interaction coordination between the first device and the second device. Since the first device performs the frame selection function, the second device performs the recognition function, and both of the two devices perform a single function, the calculation requirement is low. Therefore, in the application, the cooperation of the two devices can have a faster processing speed and a stronger calculation effect, and greatly improve the efficiency and accuracy of the entire information recognition process.

The specific method in which the second device performs the first information recognition may be flexibly determined according to the actual situation. In one possible implementation, step S22 may include steps S221-S223. In step S221, an image to be recognized included in the information to be recognized is acquired. In step S222, anti-counterfeiting detection is performed on the image to be recognized, and the detection result is acquired. In step S223, when the detection result is pass, the first information recognition is performed on the image to be recognized, and the first recognition result is acquired.

As already described in the above-mentioned disclosure embodiment, the image to be directly recognized may be used as the information to be recognized, or the image to be recognized may be subjected to a certain process to obtain the information to be recognized. Therefore, the realization method of step S221 may change along with the difference in the information generation method to be recognized. For details, refer to the following disclosure examples. After the image to be recognized is acquired, anti-counterfeiting detection may be performed on the image to be recognized in step S222. If the object to be recognized is an object with high safety demand such as a certification card object, there is a possibility that some users will recognize the copy or duplicate of the object to be recognized as an object to be recognized. be. In order to improve the safety of information recognition, it is necessary to perform anti-counterfeiting detection on the image to be recognized and reduce the occurrence of such a situation. The specific anti-counterfeiting detection method may be selected according to the actual situation, and each disclosure embodiment can be referred to later. Only after the anti-counterfeiting detection is passed, the first information recognition can be performed on the image to be recognized for the first time. When anti-counterfeiting detection fails, information such as detection failure or alarm presentation may be fed back to the first device. In this way, the security of the information recognition process is further improved.

After acquiring the image to be recognized contained in the information to be recognized, anti-counterfeiting detection is performed on the image to be recognized, the detection result is acquired, and the image to be recognized when the detection result is pass is obtained. The first information is recognized and the first recognition result is acquired. Through the above process, the safety of the entire information recognition process can be effectively improved.

The implementation method of step S221 may be flexibly selected according to the actual situation. In one possible realization method, when the information to be recognized is an image to be recognized, the image to be recognized may be read from the information to be recognized directly. In one possible realization method, when the information to be recognized is the information obtained by performing the first encryption process on the image to be recognized, the image to be recognized by decoding the information to be recognized. May be obtained. In one possible implementation method, when the information to be recognized is the information obtained by performing the first encryption processing and the signature processing on the image to be recognized, step S221 performs steps S2211 and S2212. It may be included. In step S2211, the signature information included in the information to be recognized is acquired. In step S2212, when the acquired signature information matches the signature information of the first device, the first encrypted information included in the information to be recognized is decoded, and the image to be recognized is acquired.

In one possible implementation, the second device may first verify the authority of the information to be recognized based on the signature information contained in the information to be recognized. Matching the signature information with the signature information of the first device means that the information to be recognized has not been tampered with by another device or user in the process of being transmitted to the second device. That is, the image to be recognized in the information to be recognized may be an image used for information recognition. Next, the second device may restore the image to be recognized identified by the first device by decrypting the first encrypted information. The decryption method may be flexibly specified according to the encryption method, and is not limited in the embodiment of the present invention.

Further, the fact that the signature information included in the information to be recognized does not match the signature information of the first device means that the information to be recognized may have been tampered with. At that time, the second device may stop the acquisition of the image to be recognized and feed back information such as matching failure or alarm presentation to the first device. In this way, the security of the information recognition process is further improved.

By the above process, authority verification for the information to be recognized is feasible. When the information to be recognized is falsified, an alarm can be presented, meaningless decoding and recognition processes can be reduced, and the safety and efficiency of information recognition are improved.

Similarly, the implementation method of step S222 is not limited. That is, the method for performing anti-counterfeiting detection on the image to be recognized is not limited, and may be flexibly selected according to the actual situation. Whether or not the image to be recognized is a frame image corresponding to the copy or duplicate based on the unique characteristics of the copy or duplicate of the object to be recognized in one possible implementation method. It may be specified. For example, there may be situations such as light reflection in the duplicate, and the duplicate may have a significant difference in color from the original. In one possible implementation, step S222 may include the following steps: In step S2221, the image to be recognized is classified, and the classification result of the image to be recognized is acquired. In step S2222, when the classification result indicates that the image to be recognized is an image obtained by photographing the object to be recognized, the detection result is recorded as pass. And / or, in step S2223, when the classification result indicates that the image to be recognized is an image obtained by photographing a copy or a duplicate of the object to be recognized, the detection result is recorded as a failure. ..

In one possible implementation, the type of image to be recognized may be specified by classifying the image to be recognized. In this way, anti-counterfeiting detection for the image to be recognized is feasible. How to classify the images to be recognized is not limited to the realization method. In one possible implementation, the images to be recognized may be classified via a classification neural network model. The specific implementation method of the classification neural network model is not limited. After establishing one initial neural network model in one possible implementation, a large number of images of the object to be recognized, a copy image of the object to be recognized, and an object to be recognized obtained by shooting. One trained classification neural network model may be obtained by training the initial neural network model using the duplicate image of the above as a training sample. After inputting the image to be recognized into the classification neural network model, one probability value may be output. It represents the probability that the image to be recognized is the original image of the object to be recognized. If this probability value is larger than the set probability threshold, it can mean that the image to be recognized is the original image of the object to be recognized, otherwise the image to be recognized should be recognized. It means that it is a copy image or a copy image of the target. The specific probability threshold value may be flexibly set according to an actual situation, and is not limited in the embodiment of the present invention.

The images to be recognized are classified and the classification result is acquired. If the classification result indicates that the image to be recognized is an image obtained by photographing the object to be recognized, the detection result is recorded as pass, otherwise it is recorded as failure. Through this process, anti-counterfeiting detection is achieved for images to be recognized using the classification method, and since there is high detection efficiency and high detection accuracy, the accuracy and speed of the entire information recognition process is greatly improved. ..

If the detection result is acceptable, the first information recognition may be performed on the image to be further recognized. As already described in the above disclosure embodiment, the method of recognizing the first information and the method of recognizing the second information may be the same or different, and may be flexibly according to an actual situation. It may be selected. In one possible implementation, step S223 may include performing OCR recognition on the image to be recognized by the optical character recognition OCR model and acquiring the first recognition result. In one possible realization method, there is a demand for high recognition accuracy because the purpose of the first information recognition is to recognize the corresponding information contained in the image to be recognized. Therefore, in the embodiment of the present invention, the first information recognition may be performed via an OCR model of a relatively large scale, and the accuracy and accuracy of the information recognition may be improved.

Due to the existence of various factors, the acquired first recognition result may match the content contained in the object itself to be recognized, and there may be a certain deviation. If there is a deviation, further verification may be performed on the first recognition result. Therefore, in one possible implementation, step S22 may further include step S224. In step S224, it is determined whether or not the first recognition result matches the preset rule, and the determination result is acquired.

The preset rule may be some verification rule specified based on the special feature of the information in the object to be recognized. In one example, when the object to be recognized is an identification card and the first recognition result is an ID number, the last four digits of the ID number follow a certain coding rule, so this coding rule is set in advance. As a rule, it may be determined whether or not the ID number of the first recognition result is an actual number. Similarly, when the object to be recognized is a bank card and the first recognition result is a bank card number, the coding rule of the bank card number may be a preset rule. When the object to be recognized is another type, the preset rules can be analogically expanded with reference to each of the above disclosure embodiments, and are not listed here one by one.

When the first recognition result matches the preset rule, the judgment result is recorded as successful in matching, and when the first recognition result does not match the preset rule, the judgment result is matched. It may be recorded as a failure. Since the first recognition result can be further verified by the above process, a predetermined hint or alarm may be issued when the first recognition result does not match the preset rule. In this way, it is convenient for the user to confirm whether or not the recognition result is accurate, whether or not it is necessary to recognize it again, and the like.

After the first recognition result is acquired, the recognition information may be transmitted to the first device in step S23 based on the first recognition result. The implementation method of step S23 may be flexibly determined according to the actual situation. In one possible implementation, step S23 may include steps S231 and S232. In step S231, the first recognition result is subjected to the second encryption process, or the first recognition result and the determination result are subjected to the second encryption process, and the second encryption information is acquired. In step S232, the second encrypted information is transmitted to the first device as recognition information.

In one possible implementation method, the second encryption process may be directly performed on the first recognition result to acquire the second encryption information. In this way, the second encrypted information is transmitted to the first device as recognition information. The "first" and "second" in the second encryption process and the first encryption process are simply used to distinguish between the subject and the target that execute the encryption process. That is, the first encryption process is the encryption performed on the image to be recognized by the first device, and the second encryption process is the encryption performed on the first recognition result by the second device. Yes, it is not limited whether or not the encryption methods are the same. That is, the encryption rules of the first encryption process and the second encryption process may be the same or different, and may be flexibly selected according to the actual situation.

In one possible realization method, in order to acquire the judgment result by matching the first recognition result with the preset rule, the judgment result and the first recognition result are packaged and the packaged information is used. The second encryption processing may be collectively performed to acquire the second encryption information, and the second encryption information may be transmitted to the first device as recognition information. In this way, it is convenient for the user or the first device to determine whether or not it is necessary to perform information recognition again based on the determination result.

In one possible implementation, the information recognition method used in the second instrument submitted in the embodiments of the present invention may further include the step of storing at least one frame in the image to be recognized.

As already described in the above disclosure embodiment, at least one frame in the image to be recognized may be stored in the process of the first device performing information recognition. For the same reason, the second device may store at least one frame of the image to be recognized because the second device can recover the image to be recognized from the received information to be recognized.

Similar to the above-mentioned disclosure embodiment, when the image to be recognized by the second device is saved, it is specifically saved one frame of the image to be recognized or a plurality of frames of the image to be recognized. It may be flexibly determined according to the actual situation. I will not repeat it here. The image to be recognized may be an image selected by the first device based on the recognition state, and may be an image selected by the first device based on the image quality based on a plurality of evaluation criteria. Along with the difference in selection method, the quality of the image to be recognized also causes a corresponding change. Therefore, in one possible realization method, the second device may select a different storage method depending on the difference in the selection method of the image to be recognized. The specific selection may be flexibly set according to the actual situation, and is not limited to the following disclosure examples.

Since there is a possibility that the image to be recognized identified based on the recognition state may lack completeness or sharpness in one possible implementation method, the second device is an image with a plurality of evaluation criteria. The quality of the image to be recognized stored in the second device may be improved by choosing to store only the image to be recognized identified based on the quality. In one possible realization method, when the number of images to be recognized is multiple acquired by the second device, another image quality selection is performed for these multiple images to be recognized. Then, the image with the highest image quality may also be stored in the second device. The method for selecting the image quality in the second device may be the same as or different from the sorting method in the first device, and may be flexibly selected according to the actual situation.

By storing at least one frame of the image to be recognized in the second device, it is possible to realize remote storage of the image to be recognized, and it is necessary to recognize the target to be recognized again or use the image of the target to be recognized. When there is, it is possible to directly call the image to be recognized from the second device, the user's operation is reduced, and the user experience is improved.

FIG. 3 shows a block diagram of the information recognition device 30 according to the embodiment of the present invention. As shown in FIG. 3, the apparatus 30 may include an acquisition module 31, a specific module 32, a recognition target information generation module 33, and a recognition target information transmission module 34. The acquisition module 31 acquires an image sequence of an object to be recognized, and the image sequence includes at least two frames of images. The specific module 32 identifies an image of at least one frame from the image sequence as an image to be recognized. The recognition target information generation module 33 specifies information to be recognized based on an image to be recognized. The recognition target information transmission module 34 transmits information to be recognized to the second device, and causes the second device to acquire the first recognition result based on the information to be recognized.

In one possible implementation, the particular module identifies an image of at least one frame from the image sequence as an image to be recognized, based on the recognition state and / or image quality of the image sequence.

In one possible implementation, the particular module further performs a second information recognition on at least a portion of the image in the image sequence, respectively, to obtain one or more second recognition results, 1 Acquire the reference recognition result based on one or more second recognition results, compare each second recognition result with the reference recognition result, acquire the reliability of each second recognition result, and all based on the reliability. Each image corresponding to at least a part of the second recognition result of is specified as an image to be recognized. However, the reliability of the identified image to be recognized is higher than the reliability of the non-recognizable image in the image sequence.

In one possible implementation, the particular module also obtains the image quality of at least a portion of the image in the image sequence at least one evaluation criterion, respectively, and the corresponding evaluation criteria in the image sequence. An image of at least one frame with an image quality greater than the threshold in is specified as an image to be recognized.

In one possible implementation, the evaluation criteria include at least one of sharpness, perfection, high light conditions, dim light conditions, and shielding conditions.

In one possible implementation, the device 30 further comprises a first storage module. The first storage module stores at least one frame in the image to be recognized.

In one possible implementation method, the recognition target information generation module performs the first encryption processing and / or the signature processing on the image to be recognized, and acquires the information to be recognized.

In one possible implementation, the first encryption process involves encoding and encrypting the image to be recognized to obtain the first encryption information, and the signature process is the first device. Includes adding the signature information of the to the image to be recognized.

In one possible implementation, the objects to be recognized include the certification card object and / or the form object, and the first recognition result is the text, characters, identifiers, icons and pictures recorded in the object to be recognized. Includes at least one of them.

FIG. 4 shows a block diagram of an information recognition device according to an embodiment of the present invention. As shown in the figure, the device 40 may include a receiving module 41, a recognition module 42, and a recognition information transmission module 43. The receiving module 41 receives the information to be recognized of the object to be recognized. The recognition module 42 performs the first information recognition for the information to be recognized and acquires the first recognition result. The recognition information transmission module 43 transmits the recognition information to the first device based on the first recognition result.

In one possible implementation, the recognition module acquires the image to be recognized contained in the information to be recognized, performs anti-counterfeiting detection on the image to be recognized, acquires the detection result, and the detection result is If the result is passed, the first information recognition is performed on the image to be recognized, and the first recognition result is acquired.

In one possible implementation, the recognition module further acquires the signature information contained in the information to be recognized, and when the acquired signature information matches the signature information of the first device, the information to be recognized. The first encrypted information contained in is decrypted, and an image to be recognized is acquired.

In one possible implementation, the recognition module further classifies the image to be recognized, obtains the classification result of the image to be recognized, and captures the object to be recognized by the image to be recognized. When the classification result indicates that the image is an image, the detection result is recorded as a pass, and / or the image to be recognized is an image obtained by photographing a copy or a duplicate of the object to be recognized. The detection result is recorded as a failure if indicated by the classification result.

In one possible realization method, the recognition module further performs OCR recognition on the image to be recognized by the optical character recognition OCR model and acquires the first recognition result.

In one possible implementation, the recognition module further determines whether the first recognition result matches a preset rule and obtains the determination result.

In one possible implementation, the recognition information transmission module performs a second encryption process on the first recognition result, or performs the second encryption process on the first recognition result and the determination result. The second encrypted information is acquired, and the second encrypted information is transmitted to the first device as the recognition information.

In one possible implementation, the device 40 further comprises a second storage module. The second storage module stores at least one frame of the image to be recognized.

In one possible implementation, the embodiments of the invention further disclose one application. The application example submits an information recognition system. Based on this information recognition system, recognition and collection of identification information is feasible in service flows such as online loans, rentals or membership registration.

FIG. 5 is a schematic diagram of an application example of the present invention. As shown in FIG. 5, the information recognition system is mainly composed of a front-end first device and a back-end second device jointly. The first device of the front end (hereinafter abbreviated as the front end) may be a mobile phone device, a tablet device, a notebook computer having a camera head, a desktop computer device, or the like, and the second device of the back end (hereinafter, abbreviated as the front end). , Backend) may be a cloud server. As can be seen from the figure, the complete process by which the information recognition system recognizes and collects the identification information is at least one from the image sequence by the first device acquiring the image sequence of the object to be recognized. The frame is selected as an image to be recognized, and then the information to be recognized is transmitted to the second device by specifying the information to be recognized based on the image to be recognized, and the second device transmits the information to be recognized. After receiving, the first information recognition is performed for the information to be recognized, the first recognition result is acquired, and the recognition information is transmitted to the first device based on the first recognition result. good.

Specifically, the process of the information recognition system recognizing and collecting the identification information may be as follows.

The front end opens the camera head and continuously scans the certificate to be recognized to select a frame until one frame that meets the conditions is selected as the image to be recognized, and the selected image to be recognized. May be transmitted to the backend to perform backend processing. By encoding and encrypting the image to be recognized in the transmission process and adding the signature information in the front-end SDK for authority verification, the image to be recognized in the data transmission process should not be tampered with. To secure.

After receiving the image to be recognized transmitted from the front end, the back end performs decoding and authority verification, and after confirming that the data has not been tampered with, enters the recognition flow. .. The specific recognition flow may be as follows. First, by performing anti-counterfeiting detection on the certificate image using a neural network model, it is determined whether the certificate is original or not, and then character recognition is performed on the ID card, and OCR technology is applied. It adopts and recognizes each field of the certificate, and finally makes a verification judgment on the result of character recognition based on the preset logic. After the recognition is completed, the character recognition result and the logical judgment result are encrypted and transmitted to the front end to be supplied to the user.

Further, in the application example of the present invention, the procedure for the front end to select a frame may be carried out by any one of the following two methods.

In method 1, the frame is selected based on the text recognition result of each frame of the collected image sequence by the front end.

In this type of frame selection method, a small front-end OCR model is used to perform character recognition on the image of each frame collected by the camera head, and the quality of the frame is judged based on the reliability of the character recognition result. You may. Specifically, the front end performs text recognition on each frame image to obtain multiple text recognition results, then integrates the multiple text recognition results into one standard recognition result, and the multi-frame image. That is, the one-frame image whose text recognition result is closest to the standard recognition result is selected as the image to be recognized and passed to the back end for processing. Since the accuracy rate of the OCR small model and the scale of the character library are limited, it is still necessary to transmit the image to be recognized to the back end to recognize the OCR large model. With this kind of frame selection method, it is possible to have good acceptability, and it is possible to have good frame selection results even in different quality camera heads and light environment.

In method 2, the frame is selected based on the image quality.

In this kind of frame selection method, the quality of the certificate image may be detected based on the five criteria of sharpness, perfection, high light condition, dim light condition, and obstruction condition. In one example, the definitions of these five criteria are as follows.
The sharpness mainly describes the case where characters and images cannot be recognized due to focal blur, motion blur, and the like. A perfect fifth mainly describes whether the corners of the certificate are entirely within the range of the image. High light conditions mainly describe whether the certificate has overexposure or strong reflections. The dim light situation mainly describes the case where the entire or partial brightness of the certificate is too dark to recognize characters or images. The occluded status mainly describes whether or not the certificate in the image is occluded by another object.

In the process of scanning by the front end, the above five criteria are detected for each frame image, and the detection result is set as a preset threshold value (the preset threshold value can be adjusted according to the actual situation). When all of the detection results of these five criteria satisfy the threshold value, the frame selection result may be output and the subsequent backend recognition may be performed. This type of frame selection method selects high quality images and saves them with a copy.

It should be noted that the method submitted in the above application example is applied to other online services that have a demand for information recognition, such as online card making or identification verification scenes in special cases, other than the above-mentioned situations. Also, the application example is not limited to the above.

As can be understood, the above-mentioned method examples referred to in the present invention may be combined with each other to form a post-combination example if they do not violate the principle logic. Due to space limitations, the present invention will not be repeated.

As can be understood by those skilled in the art, in the above method of a specific embodiment, the description order of each step does not mean a strict execution order, and does not impose any limitation on the implementation procedure. The specific order of execution of each step should be specified by its function and possible intrinsic logic.

The embodiments of the present invention further provide a computer-readable storage medium. The computer-readable storage medium stores computer program instructions, and the method is performed when the computer program instructions are executed by a processor. The computer-readable storage medium may be a volatile computer-readable storage medium or a non-volatile computer-readable storage medium.

The embodiments of the present invention further provide electronic devices. The electronic device includes a processor and a memory for storing processor-executable instructions. However, the processor is configured to perform the above method.

In practical applications, the memory may be a volatile memory, such as a RAM, or a non-volatile memory, such as a ROM, a flash memory, a hard disk drive, an HDD. Alternatively, it may be a solid state disk (Solid-State Drive, SSD) or a combination of the above-mentioned types of memories, and supplies instructions and data to the processor.

The processor may be at least one of an ASIC, DSP, DSPD, PLD, FPGA, CPU, controller, microcontroller, and microprocessor. As can be understood, the electronic device for realizing the processor function for different devices may be other. In the examples of the present invention, there is no specific limitation.

The electronic device may be provided as a terminal, a server or other form of device.

Based on the same technical concept as the above-mentioned embodiment, the embodiment of the present invention further provides a computer program. The above method is performed when the computer program is executed by the processor.

FIG. 6 is a block diagram of the electronic device 800 according to the embodiment of the present invention. For example, the electronic device 800 may be a terminal such as a mobile phone, a computer, a digital broadcasting terminal, an information transmitting / receiving device, a game console, a tablet device, a medical device, a fitness device, or a personal digital assistant.

Referring to FIG. 6, the electronic device 800 includes processing component 802, memory 804, power supply component 806, multimedia component 808, audio component 810, input / output (I / O) interface 812, sensor component 814 and communication component 816. It may include one or more of these components.

The processing component 802 typically controls operations related to general operations of the electronic device 800, such as display, telephone call, data communication, camera operation and recording operation. The processing component 802 may include one or more processors 820 that execute instructions to perform all or part of the steps of the above method. Also, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and the other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

The memory 804 is configured to store each type of data in order to support operations in the electronic device 800. Examples of these data include instructions of any application program or method for operating in the electronic device 800, contact data, telephone directory data, messages, pictures, video and the like. Memory 804 may include 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. It may be realized by (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic memory, a flash memory, a magnetic disk, or an optical disk.

The power component 806 supplies power to various components of the electronic device 800. The power component 806 may include a power management system, one or more power sources, as well as other components relating to the generation, management, and distribution of power for the electronic device 800.

The multimedia component 808 includes a screen that provides one output interface between the electronic device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). When the screen includes a touch panel, it may be realized as a touch screen so as to receive an input signal from the user. The touch panel includes one or more touch sensors to sense touches, slides and gestures on the touch panel. The touch sensor can not only sense the boundaries of the touch or slide motion, but also further detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes one front camera head and / or a back camera head. When the electronic device 800 is in an operating mode, eg, shooting mode or video mode, the front camera head and / or the back camera head can receive external multimedia data. Each of the front camera head and the back camera head may be one fixed optical lens system or may have focal length and optical zoom capability.

The audio component 810 is configured to output and / or input an audio signal. For example, the audio component 810 comprises a microphone (MIC), and the microphone is configured to receive an external audio signal when the electronic device 800 is in an operating mode, eg, a calling mode, a recording mode, and a voice recognition mode. To. The received audio signal can be further stored in memory 804 or transmitted via the communication component 816. In some embodiments, the audio component 810 further includes a speaker for outputting an audio signal.

The I / O interface 812 supplies an interface between the processing component 802 and the peripheral interface module, and the peripheral interface module may be a keyboard, a click wheel, a button, or the like. These buttons may include, but are not limited to, a home page button, a volume button, a start button and a lock button.

The sensor component 814 includes one or more sensors for supplying the electronic device 800 with state estimation in various aspects. For example, the sensor component 814 can detect the on / off state of the electronic device 800 and the relative position of the component. For example, the component is a display and a numeric keypad of the electronic device 800. The sensor component 814 also further repositions the electronic device 800 or the component of the electronic device 800, the presence or absence of contact between the user and the electronic device 800, the orientation or acceleration / deceleration of the electronic device 800, and the temperature change of the electronic device 800. Can be further detected. Sensor component 814 may include a proximity sensor to detect the presence of nearby objects in the absence of any physical contact. The sensor component 814 may further include an optical sensor used for imaging applications, such as a CMOS or CCD image sensor. In some embodiments, the sensor component 814 may further include an accelerometer, gyro sensor, magnetic sensor, pressure sensor or temperature sensor.

The communication component 816 is configured to facilitate wireless or wired communication between the electronic device 800 and other user devices. The electronic device 800 can access a wireless network based on a communication standard, for example, WiFi, 2G or 3G, or a combination thereof. In one exemplary embodiment, the communication component 816 receives broadcast signals or broadcast-related notification information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 816 may further include a Near Field Communication (NFC) module to facilitate short-range communication. For example, NFC modules may be implemented by radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth® (BT) technology and other technologies.

In an exemplary embodiment, the electronic device 800 is one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic for performing the above methods. It may be implemented by a device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic component.

An exemplary embodiment further provides a non-volatile computer readable storage medium, eg, a memory 804 containing computer program instructions. The computer program instruction may be executed by the processor 820 of the electronic device 800 to carry out the method.

FIG. 7 is a block diagram of the electronic device 1900 according to the embodiment of the present invention. For example, the electronic device 1900 may be provided as a server. Referring to FIG. 7, the electronic device 1900 includes a processing component 1922, which further comprises one or more processors and a memory resource typified by the memory 1932, the memory 1932 being processed. Stores instructions that can be executed by component 1922, such as application programs. The application program stored in memory 1932 may include one or more modules, each corresponding to a set of instructions. Further, the processing component 1922 is configured to implement the above method by executing an instruction.

The electronic device 1900 includes a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and inputs / outputs (I). / O) An interface 1958 may be further provided. The electronic device 1900 may operate an operating system stored in memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

An exemplary embodiment further provides a non-volatile computer readable storage medium, eg, memory 1932 containing computer program instructions. The method can be implemented by executing the computer program instructions by the processing component 1922 of the electronic device 1900.

The present invention provides systems, methods and / or computer program products. Computer program products may include computer readable storage media. The computer-readable storage medium contains computer-readable program instructions for causing the processor to perform each aspect of the present invention.

The computer-readable storage medium may be a tangible device that holds and stores the instructions used by the instruction executing device. The computer-readable storage medium may be, for example, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination described above, but is not limited thereto. More specific examples of computer-readable storage media (non-exhaustive list) are portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory). ), Static random access memory (SRAM), portable compressed disk read-only memory (CD-ROM), digital multifunction disk (DVD), memory stick, floppy disk, mechanical coding device, for example, instructions are stored. Includes punch cards or in-groove protrusion structures, and any suitable union as described above. The computer-readable storage medium used herein is an instantaneous signal itself, eg, a radio wave or other freely propagating electromagnetic wave, a waveguide or an electromagnetic wave propagating through another transmission medium (eg, an optical fiber cable). It is not interpreted as an optical signal transmitted through an optical pulse) or an electric wire.

The computer-readable program instructions described herein are downloaded from a computer-readable storage medium to each arithmetic / processing device, or via a network such as the Internet, local area network, wide area network and / or wireless network to an external computer or external. You may download it to a storage device. The network may include copper transmission cables, fiber optic transmissions, wireless transmissions, routers, firewalls, switches, gateway computers and / or edge servers. The network adapter or network interface in each arithmetic / processing device receives a computer-readable program instruction from the network and transfers the computer-readable program instruction to store the computer-readable program instruction in the computer-readable storage medium in each arithmetic / processing apparatus.

The computer program instructions for performing the operations of the present invention are assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcodes, firmware instructions, state setting data, or one or more types. It may be source code or target code created by any combination of programming languages. The programming language includes an object-oriented programming language (eg, Smalltalk, C ++, etc.) and a conventional process programming language (eg, "C" language) or a similar programming language. Computer-readable program instructions may be executed entirely on the user computer, partially on the user computer, or as one independent software package, some on the user computer. The other part may be executed on the remote computer, or may be entirely executed on the remote computer or the server. In the case of a remote computer, the remote computer may be connected to the user computer or to an external computer via any type of network (including local area network (LAN) or wide area network (WAN)). (For example, connect to the Internet using an Internet service provider). In some embodiments, electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs) or programmable logic arrays (PLAs) are personalized and customized using state information from computer-readable program instructions. The electronic circuit can implement each aspect of the present invention by executing computer-readable program instructions.

Here, each aspect of the present invention has been described with reference to the flowchart and / or block diagram of the method, apparatus (system) and computer program product according to the embodiment of the present invention. As can be understood, each block of the flowchart and / or the block diagram and each combination of the blocks in the flowchart and / or the block diagram can be realized by computer-readable program instructions.

These computer-readable program instructions can be fed to the processor of a general purpose computer, a dedicated computer or other programmable data processing device to create a machine. Thus, a device that, when executed by the processor of a computer or other programmable data processing device, realizes the function / operation specified by one or more blocks in the flowchart and / or block diagram. , Generated. These computer-readable program instructions may be stored in a computer-readable storage medium. With these instructions, computers, programmable data processing equipment and / or other equipment operate in a particular manner. As described above, the computer-readable medium in which the instruction is stored includes one manufactured product, which is an instruction of each aspect that realizes the function / operation specified by one or more blocks in the flowchart and / or the block diagram. including.

Computer-readable program instructions may be loaded into a computer, other programmable data processor, or other equipment. In this way, a series of operational steps are performed on a computer, other programmable data processor or other device, and the process of realization by the computer is created. Thereby, an instruction executed on a computer, other programmable data processing device, or other device realizes a function / operation defined by one or more blocks in a flowchart and / or a block diagram.

Flow charts and block diagrams in the drawings show feasible systematic architectures, functions and operations of systems, methods and computer program products according to a plurality of embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent part of a module, program segment or instruction. A part of the module, program segment or instruction includes one or more executable instructions for performing a defined logical function. In some alternative embodiments, the functions marked in the block may occur in a different order than shown in the drawings. For example, two consecutive blocks may, in fact, be executed essentially in parallel, and may be executed in reverse order, depending on such function. It should be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, is realized in a system based on dedicated hardware that performs a specified function or operation. It may be realized by a combination of dedicated hardware and computer instructions.

In the above, each embodiment of the present invention has been described. The above description is exemplary, not exhaustive, and is not limited to each disclosed embodiment. Many modifications and changes will be apparent to those skilled in the art, provided that they do not deviate from the scope and spirit of each of the embodiments described. The terms in the text are chosen to best interpret the principles of each embodiment, the actual application, or the technical improvements to the technology in the market, or to allow one of ordinary skill in the art to understand each embodiment disclosed in the text. To.

Claims (21)

It ’s an information recognition method.
A step in which the first device acquires an image sequence of an object to be recognized, including at least two frames of images.
A step of identifying at least one frame of an image from the image sequence as an image to be recognized by the first device.
A step of specifying information to be recognized by the first device based on the image to be recognized, and
Information recognition including a step of transmitting the information to be recognized by the first device to the second device and causing the second device to acquire the first recognition result based on the information to be recognized. Method. The step of identifying at least one frame of an image from the image sequence as an image to be recognized by the first device is
1. The first apparatus comprises selecting an image of at least one frame from the image sequence as the image to be recognized based on the recognition state and / or the image quality of the image sequence. Information recognition method described in. The first apparatus may select an image of at least one frame from the image sequence as the image to be recognized based on the recognition state of the image sequence.
The first device performs second information recognition on at least a part of the images in the image sequence, and obtains one or more second recognition results.
When the first device acquires a reference recognition result based on the one or more second recognition results,
The first device compares each of the second recognition results with the reference recognition result, and obtains the reliability of each of the second recognition results.
Based on the reliability, the first device identifies each image corresponding to at least a part of all the second recognition results as the image to be recognized, and the reliability of the identified image to be recognized. 2 is the information recognition method according to claim 2, wherein the image sequence has a higher reliability than that of an image that is not an image to be recognized in the image sequence. The first apparatus may select an image of at least one frame from the image sequence as the image to be recognized based on the image quality of the image sequence.
The first device obtains the image quality of at least a part of the image sequence in the image sequence according to at least one evaluation criterion, and
The first apparatus is characterized by comprising specifying at least one frame of the image quality of the image sequence, which is larger than the threshold value in the corresponding evaluation criteria, as the image to be recognized in the image sequence. The information recognition method according to claim 2 or 3. The information recognition method according to claim 4, wherein the evaluation standard includes at least one of a sharpness, a perfection, a strong light condition, a dim light condition, and a shielding condition. The step of identifying the information to be recognized by the first device based on the image to be recognized is
Any one of claims 1 to 5, wherein the first apparatus performs a first encryption process and / or a signature process on the image to be recognized to acquire information to be recognized. The information recognition method described in the section. The first encryption process includes obtaining the first encryption information by encoding / encrypting the image to be recognized.
The information recognition method according to claim 6, wherein the signature process includes adding the signature information of the first device to the image to be recognized. The objects to be recognized include the certification card object and / or the form object.
The first recognition result is described in any one of claims 1 to 7, wherein the first recognition result includes at least one of a text, a character, an identifier, an icon and a picture recorded in the object to be recognized. Information recognition method. It ’s an information recognition method.
The step of receiving the information to be recognized by the second device and the object to be recognized,
The step of performing the first information recognition on the information to be recognized by the second device and acquiring the first recognition result,
An information recognition method comprising: a step of transmitting recognition information to the first device based on the first recognition result of the second device. The step of performing the first information recognition on the information to be recognized by the second device and acquiring the first recognition result is
Acquiring the image to be recognized included in the information to be recognized by the second device, and
The second device performs anti-counterfeiting detection on the image to be recognized and acquires the detection result.
9. The claim 9 is characterized in that, when the detection result is pass, the second device recognizes the first information on the image to be recognized and acquires the first recognition result. Information recognition method described in. Acquiring the image to be recognized included in the information to be recognized by the second device is
Acquiring the signature information included in the information to be recognized by the second device,
When the acquired signature information matches the signature information of the first device, the second device decodes the first encrypted information included in the information to be recognized and acquires the image to be recognized. The information recognition method according to claim 10, further comprising: The second device performs anti-counterfeiting detection on the image to be recognized and obtains the detection result.
The second device classifies the image to be recognized and obtains the classification result of the image to be recognized.
When the classification result indicates that the image to be recognized is an image obtained by photographing the object to be recognized, the second device records the detection result as pass and / or
When the image to be recognized is an image obtained by photographing a copy or a duplicate of the object to be recognized, the second device records the detection result as a failure when the classification result indicates. The information recognition method according to claim 9 or 10, wherein the information recognition method comprises. The step of performing the first information recognition on the information to be recognized by the second device and acquiring the first recognition result is
One of claims 10 to 12, wherein the second device further includes determining whether or not the first recognition result matches a preset rule, and acquiring the determination result. The information recognition method described in the section. The step in which the second device transmits the recognition information to the first device based on the first recognition result is
The second device performs a second encryption process on the first recognition result, or performs the second encryption process on the first recognition result and the determination result, and obtains the second encryption information. To get and
The information recognition method according to claim 13, wherein the second device transmits the second encrypted information as the recognition information to the first device. The information recognition method according to any one of claims 10 to 14, further comprising a step of storing at least one frame in the image to be recognized by the second device. It is an information recognition device
The information recognition device is used in the first device.
An image sequence acquisition module for acquiring an image sequence of an object to be recognized, including at least two frames of images, and an image sequence acquisition module.
A specific module for identifying at least one frame of an image as an image to be recognized from the image sequence,
A recognition target information generation module for specifying information to be recognized based on the image to be recognized, and
Information characterized by comprising a recognition target information transmission module for transmitting the information to be recognized to the second device and causing the second device to acquire the first recognition result based on the information to be recognized. Recognition device. It is an information recognition device
The information recognition device is used in the second device.
A receiving module for receiving information to be recognized, and a receiving module for receiving information to be recognized.
A recognition module for performing the first information recognition on the information to be recognized and acquiring the first recognition result,
An information recognition device including a recognition information transmission module for transmitting recognition information to a first device based on the first recognition result. It ’s an electronic device,
With the processor
Equipped with a non-temporary storage medium for storing processor executable instructions,
An electronic device, wherein the processor is configured to implement the information recognition method according to any one of claims 1 to 8 by calling an instruction stored in the storage medium. It ’s an electronic device,
With the processor
Equipped with a non-temporary storage medium for storing processor executable instructions,
The electronic device is characterized in that the processor is configured to implement the information recognition method according to any one of claims 9 to 15 by calling an instruction stored in the storage medium. A computer-readable storage medium that stores computer program instructions.
The computer-readable storage medium according to any one of claims 1 to 15, wherein the information recognition method is carried out when the computer program instruction is executed by the processor. It ’s a computer program,
The computer program according to any one of claims 1 to 15, wherein the information recognition method is executed when the computer program is executed by a processor.

Images