WO2017157034A1 - Method, device, and storage medium for identifying two-dimensional code - Google Patents

Abstract

Disclosed in the present invention are a method of identifying a two-dimensional code, comprising: acquiring an image to be identified that contains a two-dimensional code on a light-emitting display; and extracting a position detection pattern from the image to be identified, determining, according to the position detection pattern, the location of the two-dimensional code in the image to be identified, and identifying the two-dimensional code at the location. Also disclosed in the present invention are a device and a storage medium for identifying a two-dimensional code.

Description

Method and device for identifying two-dimensional code and storage medium Technical field

The present invention relates to image recognition technology, and in particular, to a method and device for identifying a two-dimensional code, and a storage medium.

Background technique

With the rapid development of information technology, more and more different information media are widely used. Two-dimensional code is a simple, low-cost, and convenient new medium. Kind of work and life scenes can be seen everywhere. A two-dimensional code, also known as a two-dimensional bar code, is a black and white graphic that is distributed in a plane (two-dimensional direction) according to a certain rule by a specific geometric figure. In addition, the encoding of the two-dimensional code subtly utilizes the concept of "0" and "1" bit streams constituting the internal logic of the computer, and uses several geometric shapes corresponding to binary to represent the literal numerical information through the image input device or The terminal such as the photoelectric scanning device automatically reads the information to realize automatic processing of information.

A two-dimensional code is a more advanced bar code format than a one-dimensional code. Since the one-dimensional code can only store information in one direction (generally horizontal), the two-dimensional code can store information in both horizontal and vertical directions; the one-dimensional code can only be composed of numbers and letters, and the two-dimensional code can Store Chinese characters, numbers and pictures, so the application of QR codes is much broader, such as: product anti-counterfeiting / traceability, advertising push, website link, data download, positioning / navigation, electronic voucher, vehicle management, information transfer Wait.

Through the retrieval and investigation of the relevant two-dimensional code recognition technology, it is found that the current two-dimensional code recognition scene is mostly limited to the case of passive illumination, that is, the two-dimensional code is pasted on the surface of the generally non-lighting object, and the identification method of the two-dimensional code Although many, it is generally in accordance with the following processing flow: image graying, image enhancement, image filtering processing, uneven illumination processing, binarization, edge detection, image Positioning, image correction, and distortion correction. Among them, image graying is to convert the captured color picture into grayscale image, the process can eliminate the color information in the color picture and reduce the complexity of subsequent processing; image filtering is very important in the process of two-dimensional code recognition. A link can filter out Gaussian noise, salt and pepper noise generated during image acquisition, avoiding the influence of noise on decoding, and thus improve the recognition rate; binarization selects an appropriate threshold to convert the grayscale image into only " A binarized image of 0" and "1"; image correction is to use an spatial positional relationship to correct an image that interferes with decoding due to factors such as a wrong angle of shooting to a horizontal, easily decoded image.

Through the above processing flow, a general two-dimensional code can be recognized quickly and accurately, and a good solution has not been proposed for how to identify the two-dimensional code in the active lighting scene. In particular, with the popularity of light-emitting diodes (LEDs) as a new generation of green light sources, LEDs have advantages such as high brightness, low power consumption, long life, fast start, no stroboscopic, and less prone to visual fatigue. Gradually replacing traditional energy-saving lamps and incandescent lamps, it has become the most popular and respected green lighting technology. In addition, since the LED also has the characteristics of short response time and high-speed modulation, it can be applied to visible light communication and indoor positioning while being illuminated. Therefore, the two-dimensional code based on the LED array display has been applied in many occasions.

However, there is no effective solution for quickly and accurately identifying the two-dimensional code that is actively illuminated by the LED array.

Summary of the invention

In view of this, the embodiment of the present invention is to provide a method and device for identifying a two-dimensional code and a storage medium, which can quickly and accurately identify a two-dimensional code that is actively illuminated by an LED array, and improve the efficiency of reading two-dimensional code information. , thereby improving the user's perception of use.

To achieve the above objective, the technical solution of the embodiment of the present invention is implemented as follows:

An embodiment of the present invention provides a method for identifying a two-dimensional code, where the method includes:

Acquiring an image to be recognized containing a two-dimensional code of the illuminating display;

Extracting a position detection pattern in the image to be identified, and determining according to the position detection pattern The two-dimensional code position in the image to be identified, and identifying the two-dimensional code in the two-dimensional code position.

In the above solution, the collecting the image to be recognized including the two-dimensional code of the illuminating display comprises:

Select a working mode for identifying the two-dimensional code;

Accessing and calling the bottom layer of the terminal camera identifying the two-dimensional code according to the selected working mode, adjusting the scanning parameter, and collecting the image to be recognized by using the metering mode corresponding to the selected working mode.

In the above solution, the collecting the image to be identified by using the metering mode corresponding to the selected working mode includes:

When the selected working mode is a single two-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by using a central key metering method, and the two-dimensional code region of the black and white is highlighted, and the two-dimensional code is not included. Background area blurring;

When the selected working mode is a multi-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by an average metering method, and the two-dimensional code is specially preprocessed.

In the above solution, the special preprocessing of the two-dimensional code includes: detecting a brightness distribution of the image to be recognized that includes the two-dimensional code, and performing corresponding processing according to different brightness distributions.

In the above solution, the detecting the brightness distribution of the image to be recognized including the two-dimensional code, and performing corresponding processing according to different brightness distributions, including:

If the position detection pattern conforms to the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, a plurality of two-dimensional code areas are sequentially determined according to the brightness level;

If there is no significant difference in the brightness distribution of different two-dimensional code regions, all the extracted position detection patterns are classified into one set, and any three position detection patterns in the collection are arranged and combined to detect whether each permutation combination satisfies certain conditions. The two-dimensional code region is determined according to the permutation combination satisfying the condition.

In the above solution, the detecting whether each permutation combination satisfies certain conditions includes:

According to the black-and-white hopping rule of the two-dimensional code, the corresponding position detection pattern is taken as a center The detection of the horizontal and vertical directions of the line filters out the arrangement of the position detection patterns that do not conform to the black and white hopping pattern.

In the above solution, after the determining the location of the two-dimensional code in the image to be identified, the method further includes:

Preprocessing the two-dimensional code in the two-dimensional code position, and decoding the pre-processed two-dimensional code to obtain corresponding information;

The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position.

In the above solution, the two-dimensional code is a two-dimensional code displayed based on an LED array.

An embodiment of the present invention further provides a device for identifying a two-dimensional code, where the device includes: an acquisition module and an identification module;

The acquiring module is configured to collect an image to be recognized that includes a two-dimensional code of the illuminating display;

The identification module is configured to extract a position detection pattern in the image to be identified, determine a two-dimensional code position in the image to be recognized according to the position detection pattern, and identify a two-dimensional position in the two-dimensional code position code.

In the above solution, the collection module is further configured to:

Select a working mode for identifying the two-dimensional code;

Accessing and calling the bottom layer of the terminal camera identifying the two-dimensional code according to the selected working mode, adjusting the scanning parameter, and collecting the image to be recognized by using the metering mode corresponding to the selected working mode.

In the above solution, the collection module is further configured to:

When the selected working mode is a single two-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by using a central key metering method, and the two-dimensional code region of the black and white is highlighted, and the two-dimensional code is not included. Background area blurring;

When the selected working mode is a multi-dimensional code recognition mode, the average metering mode is used to read The two-dimensional code in the image to be identified, and special preprocessing of the two-dimensional code.

In the above solution, the collecting module is further configured to: detect a brightness distribution of the image to be recognized that includes the two-dimensional code, and perform corresponding processing according to different brightness distributions.

In the above solution, the collection module is further configured to:

If the position detection pattern conforms to the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, a plurality of two-dimensional code areas are sequentially determined according to the brightness level;

If there is no significant difference in the brightness distribution of different two-dimensional code regions, all the extracted position detection patterns are classified into one set, and any three position detection patterns in the collection are arranged and combined to detect whether each permutation combination satisfies certain conditions. The two-dimensional code region is determined according to the permutation combination satisfying the condition.

In the above solution, the collection module is further configured to:

According to the black-and-white hopping rule of the two-dimensional code, the horizontal direction and the vertical direction are respectively detected around the corresponding position detection pattern, and the arrangement combination of the position detection patterns that do not conform to the black-and-white hopping rule is filtered out.

In the above solution, the device further includes:

a pre-processing module, configured to pre-process the two-dimensional code in the two-dimensional code position after the identification module determines the two-dimensional code position in the image to be identified;

a decoding module, configured to decode the two-dimensional code preprocessed by the preprocessing module to obtain corresponding information;

The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position.

In the above solution, the two-dimensional code is a two-dimensional code displayed based on an LED array.

An embodiment of the present invention further provides a device for identifying a two-dimensional code, including a camera, a processor, and a memory;

The camera is configured to collect an image to be recognized that includes a two-dimensional code of the illuminating display;

Storing executable instructions for causing the processor to perform an operation of: extracting a position detection pattern in the image to be identified, and determining a two-dimensional image in the image to be recognized according to the position detection pattern The code position and identifying the two-dimensional code within the two-dimensional code position.

The embodiment of the invention further provides a storage medium, which stores executable instructions for performing the method for identifying the two-dimensional code provided by the embodiment of the invention.

The method and device for identifying a two-dimensional code and the storage medium provided by the embodiment of the present invention collect an image to be recognized that includes a two-dimensional code of the light-emitting display; and extract a position detection pattern in the image to be recognized, according to the position detection pattern Determining a two-dimensional code position in the image to be identified and identifying a two-dimensional code within the two-dimensional code position.

Since the position detection pattern is used for calibrating the two-dimensional code, the position of the two-dimensional code is located by identifying the position detection pattern in the image to be identified, and the acquisition of the two-dimensional code may be neglected, and the acquisition of the parameter may result in the determination of the two-dimensional code. The problem of imaging failure is based on the position of the positioned two-dimensional code, which in turn can identify the two-dimensional code displayed based on the LED array.

DRAWINGS

1 is a two-dimensional code image of an active light display of an LED array according to the present invention;

2 is a schematic flowchart of an implementation process of a method for identifying a two-dimensional code according to an embodiment of the present invention;

3 is a schematic flowchart of a system for implementing a method for identifying a two-dimensional code according to an embodiment of the present invention;

FIG. 4 is a schematic structural diagram of a device for identifying a two-dimensional code according to an embodiment of the present invention.

detailed description

The embodiments of the present invention are described in detail with reference to the accompanying drawings.

Figure 1 shows the two-dimensional code image displayed by the LED array active illumination. As shown in Figure 1, the aperture of a single LED bead will affect the adjacent LED, and the general LED array Insufficient intensity will result in a grainy display, and irregular stripes will occur due to the inconsistency between the refresh rate of the control LED and the exposure time of the shot. These unfavorable factors make it difficult to identify the two-dimensional code in the active lighting scene by using the ordinary two-dimensional code recognition method, thereby causing the reading time of the two-dimensional code to become longer, or the two-dimensional code cannot be correctly read.

At the same time, in order to balance the lighting function, the brightness of the LED array is generally higher in practical applications. Therefore, exposure with an ordinary camera is prone to overexposure. In addition, the ordinary two-dimensional code recognition software, such as WeChat sweep, simply borrows the camera in the mobile phone system application, and can not adjust the aperture, focal length and other parameters of the camera, so it will not be based on the actual light like the normal photo scene. Strong automatic adjustment of exposure mode, etc. In this way, the two-dimensional code area will be bright, and it is very likely that the two-dimensional code cannot be recognized. Therefore, how to quickly and accurately identify the two-dimensional code displayed by the LED array active illumination is an urgent problem to be solved.

As shown in FIG. 2, the implementation process of the method for identifying a two-dimensional code in the embodiment of the present invention includes the following steps:

Step 201: Acquire an image to be identified that includes a two-dimensional code of the illuminating display;

Wherein, the two-dimensional code is a two-dimensional code displayed based on an LED array.

This step 201 specifically includes:

Select a working mode for identifying the two-dimensional code;

Accessing and calling the bottom layer of the terminal camera identifying the two-dimensional code according to the selected working mode, adjusting the scanning parameter, and collecting the image to be recognized by using the metering mode corresponding to the selected working mode.

Wherein, the scanning parameters include: aperture, focal length and exposure mode.

Here, the selected working mode of identifying the two-dimensional code comprises: a single two-dimensional code recognition mode and a multi-dimensional code recognition mode; the user may pre-select the identification form in the two-dimensional code scanning application software according to actual application requirements. The two-dimensional code also recognizes the multi-dimensional code to facilitate the second terminal to adjust the subsequent corresponding processing according to different working modes, that is, selecting the identification single-dimensional code, and subsequently identifying The processing of the single two-dimensional code; selecting and identifying the multi-dimensional code, and subsequently performing the process of identifying the multi-dimensional code.

Here, the terminal displaying the two-dimensional code is the first terminal, and the terminal identifying the two-dimensional code is the second terminal, and the second terminal may be a wireless terminal or a wired terminal, wherein the wireless terminal may be provided to the user. A device for voice and/or data connectivity, a handheld device with wireless connectivity, or other processing device connected to a wireless modem.

In the embodiment of the present invention, each LED lamp bead is separately modulated by a Field-Programmable Gate Array (FPGA) program, and a black and white module in a two-dimensional code characterized by different gray values can be obtained. Here, how to individually modulate each LED lamp bead belongs to the prior art, and details are not described herein again.

Here, the collecting the image to be identified by using the metering mode corresponding to the selected working mode, specifically includes:

If the selected working mode of identifying the two-dimensional code is a single two-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by using a central key metering method, and the two-dimensional code region of the black and white is highlighted, and two The background area other than the dimension code is blurred; thus, the black-and-white module that can not distinguish the two-dimensional code due to the brightness of the LED array being too high can be avoided, so that the whole image is presented as a black and white QR code on the black matrix. The area is very convenient for the identification and reading of QR codes. In this case, there is almost no redundant information in the image, no complicated filtering calculation is required, and only basic pre-processing can be performed to accurately decode. Therefore, the method of reading the two-dimensional code has a relatively fast speed and accuracy.

The basic pre-processing includes filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position.

If the selected working mode of identifying the two-dimensional code is a multi-dimensional code recognition mode, since the unipolar effect of brightness does not occur in the case of multiple two-dimensional codes, and the luminance distribution under illumination of a plurality of LED arrays tends to be averaged, The over-exposure phenomenon does not occur, so the two-dimensional code in the image to be recognized is read by the average metering method, and the two-dimensional code is specially preprocessed.

Here, a plurality of different two-dimensional codes in the active lighting scene can be distinguished according to different brightness distributions of the two-dimensional code regions.

The performing the special pre-processing on the two-dimensional code includes: detecting a brightness distribution of the image to be recognized that includes the two-dimensional code, and performing corresponding processing according to different brightness distributions;

For example, if the position detection pattern conforms to the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, a plurality of two-dimensional code areas are sequentially determined according to the brightness level;

If there is no significant difference in the brightness distribution of different two-dimensional code regions, all the extracted position detection patterns are classified into one set, and any three position detection patterns in the collection are arranged and combined to detect whether each permutation combination satisfies certain conditions. The two-dimensional code region is determined according to the permutation combination satisfying the condition.

Here, the certain condition of the satisfaction is that the black and white hopping rule is met. Once the first terminal cannot satisfy the above condition when the two-dimensional code is recognized, the second terminal cannot identify the position detecting pattern in the image to be recognized, or incorrectly A pseudo position detection pattern similar to the position detection pattern is recognized, which in turn causes the positioning and recognition of the two-dimensional code to fail. The pseudo position detection pattern may be generated due to factors such as shooting conditions, LED light intensity, and the like. Therefore, the extracted position detection pattern is filtered, that is, the position detection pattern that does not conform to the black and white hopping rule is filtered out. The arrangement of the arrays plays an important role in accurately locating the position of the two-dimensional code in the image to be identified.

For example, the detecting whether each permutation combination satisfies certain conditions includes: performing detection in a horizontal direction and a vertical direction respectively according to a black and white hopping rule of the two-dimensional code, and filtering out the non-conformity in the horizontal direction and the vertical direction respectively Arrangement and combination of position detection patterns of black and white hopping rules.

Here, in the image processing, the brightness can usually be represented by the gradation, so that the entire image to be recognized can be roughly divided according to the brightness by using the gray image, and several regions in which the average brightness level is sequentially decreased can be obtained, that is, each block The area corresponds to a two-dimensional code. In the process of grading the image to be recognized, a weighted averaging method may be used to convert it into a grayscale image. In addition, in the process of graying, the RGB values of each gray image pixel point will also be extracted to represent the brightness signal. interest.

It should be noted that in the two-dimensional code, a quick response (QR, Quick Response) code is taken as an example, and any three corners of the four corners of the QR code are printed with a smaller word like "back". The square pattern, the position detection pattern, can be seen in Figure 1. The three position detection patterns are patterns for positioning the decoding software, and satisfy the geometric positional relationship of a certain triangle. For example, the three position detection patterns of each QR code are respectively located at three vertices of the QR code to form an isosceles right angle. triangle. After obtaining the image to be identified through the finder frame, the second terminal searches for the position detection pattern in the image to be recognized according to the black and white hopping rule unique to the two-dimensional code, and the same as the existing two-dimensional code recognition method, the image can be detected by three positions. (such as the back of the QR code) to determine the edge and outline of the QR code. Here, in particular, how to determine the edge and contour of the two-dimensional code belongs to the prior art, and details are not described herein again.

Here, when the user needs to recognize the two-dimensional code through the second terminal, preferably, the terminal with the camera function can be used to collect the image to be recognized that includes the two-dimensional code; the two-dimensional code scanning application software used can be selected according to the selection. The recognition mode of the two-dimensional code, access and call the second terminal, such as the bottom layer of the mobile phone camera, adjust parameters such as aperture, focal length, and change the exposure mode of the camera.

In practical applications, the bottom layer of the camera may be adjusted according to factors such as the spatial position relationship between the two-dimensional code displayed on the LED array and the camera in the second terminal, and the distance between the two-dimensional code and the camera in the second terminal. Parameters and change the exposure mode of the camera. Here, how to adjust the underlying parameters and change the exposure mode is a prior art, and will not be described here.

Step 202: Extract a position detection pattern in the image to be identified, determine a two-dimensional code position in the image to be recognized according to the position detection pattern, and identify a two-dimensional code in the two-dimensional code position.

In step 202, after the determining the location of the two-dimensional code in the image to be identified, the method may further include: pre-processing the two-dimensional code in the two-dimensional code position, and The processed two-dimensional code is decoded to obtain corresponding information.

The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position.

Here, considering that the LED display halo will form edge sawtooth and the graininess caused by the dot matrix screen, the histogram fit can be used to calculate the threshold and the large window median filter is used to reduce its effect. In addition, the two-dimensional code can be corrected according to the Haval space transform. Here, the above-mentioned process is specifically implemented in the prior art, and details are not described herein again.

FIG. 3 is a schematic flowchart showing an implementation of a specific method for identifying a two-dimensional code according to the present invention. As shown in FIG. 3, the embodiment includes the following steps:

Step 301: The user selects an operation mode for identifying the two-dimensional code;

Here, the two-dimensional code is a two-dimensional code based on an LED array display, wherein the LED array illumination display belongs to one type of active illumination display, which is different from most existing passive illumination displays, that is, on a surface of a generally non-emitting object. Paste the QR code.

Step 302: Determine the type of the selected working mode, if the selected working mode is a single two-dimensional code recognition mode, step 303 is performed, otherwise step 304 is performed;

Here, the working mode of the selected two-dimensional code selected by the user is divided into two types: a single two-dimensional code recognition mode and a multi-dimensional code recognition mode; the user can pre-select in the two-dimensional code scanning application software according to actual application requirements. Whether to identify a single two-dimensional code, or to identify a multi-dimensional code, and then adjust the steps that need to be performed according to different recognition modes.

Step 303: reading the two-dimensional code in the image to be recognized by using the central key metering method, highlighting the black and white two-dimensional code region, and blurring the background region other than the two-dimensional code;

Here, using the method of step 303, a two-dimensional code displayed by the LED array can be quickly identified, and the entire image is presented as a black and white two-dimensional code region on the black background without additional processing, which is very convenient. Identification and reading of the dimension code.

Step 304: Read the two-dimensional code in the image to be identified by using the average metering method, and compare the two The dimension code performs the preprocessing as in step 305;

Step 305: Detecting a brightness distribution of the image to be recognized that includes the two-dimensional code;

Here, a plurality of different two-dimensional codes in the active lighting scene can be distinguished according to different brightness distributions of the two-dimensional code regions.

Step 306: If the difference in brightness distribution of different two-dimensional code regions is large, step 307 is performed;

Here, a precondition is required that the position detection patterns of the different two-dimensional code regions conform to the geometric positional relationship of the two-dimensional code.

Step 307: sequentially determine a plurality of two-dimensional code regions according to the brightness level, and end the current processing flow;

Step 308: If the difference in the brightness distribution of the different two-dimensional code area is small, step 309 is performed;

Step 309: classify all the extracted position detection patterns into a set, and select and combine the three position detection patterns in the collection to detect whether each permutation combination satisfies certain conditions, and determine the two-dimensional code according to the permutation combination satisfying the conditions. region.

Here, the detecting whether each permutation combination satisfies certain conditions includes:

According to the black-and-white hopping rule of the two-dimensional code, the horizontal direction and the vertical direction are respectively detected around the corresponding position detection pattern, and the arrangement combination of the position detection patterns that do not conform to the black-and-white hopping rule is filtered out.

Wherein, the certain condition of the satisfaction is a black and white hopping rule conforming to the two-dimensional code.

The embodiment of the invention provides a method for recognizing a two-dimensional code in an active illumination scenario, as in an application example in which a two-dimensional code is displayed by an LED array, image graininess caused by LED illumination effect and shooting time can be avoided. The interference caused by the stripe phenomenon caused by the unsuitable exposure time, the application scenario of the two-dimensional code recognition technology is broadened, and the reading rate of the two-dimensional code in the complex scene is improved. Optionally, the embodiment of the present invention is based on Different brightness distributions in the image to be identified can also read a single two-dimensional code or multiple two-dimensional codes in different working modes, and adjust the image acquisition mode according to user requirements, which can speed up the reading speed of a single two-dimensional code, and The identification of multiple two-dimensional codes has higher reading efficiency.

In order to achieve the above method, an embodiment of the present invention further provides a device for identifying a two-dimensional code. As shown in FIG. 4, the device includes an acquisition module 41 and an identification module 42.

The acquiring module 41 is configured to collect an image to be recognized that includes a two-dimensional code of the illuminating display;

The identification module 42 is configured to extract a position detection pattern in the image to be identified, determine a two-dimensional code position in the image to be recognized according to the position detection pattern, and identify two in the two-dimensional code position. Dimension code.

Wherein, the two-dimensional code is a two-dimensional code displayed based on an LED array.

Here, the apparatus further includes: a pre-processing module 43 configured to pre-process the two-dimensional code in the two-dimensional code position after the identification module 42 determines the two-dimensional code position in the image to be identified ;

The decoding module 44 is configured to decode the two-dimensional code preprocessed by the preprocessing module 43 to obtain corresponding information.

The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position.

Here, the collection module 41 is further configured to:

Select a working mode for identifying the two-dimensional code;

Accessing and calling the bottom layer of the terminal camera identifying the two-dimensional code according to the selected working mode, adjusting the scanning parameter, and collecting the image to be recognized by using the metering mode corresponding to the selected working mode.

The collection module 41 is further configured to:

When the selected working mode is a single two-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by using a central key metering method, and the two-dimensional code region of the black and white is highlighted, and the two-dimensional code is not included. Background area blurring;

When the selected working mode is a multi-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by an average metering method, and the two-dimensional code is specially preprocessed.

Here, the acquisition module 41 is further configured to: detect a brightness distribution of the image to be recognized that includes the two-dimensional code, and perform corresponding processing according to different brightness distributions.

For example, if the position detection pattern conforms to the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, a plurality of two-dimensional code areas are sequentially determined according to the brightness level;

If there is no significant difference in the brightness distribution of different two-dimensional code regions, all the extracted position detection patterns are classified into one set, and any three position detection patterns in the collection are arranged and combined to detect whether each permutation combination satisfies certain conditions. The two-dimensional code region is determined according to the permutation combination satisfying the condition.

The collection module 41 is further configured to:

According to the black-and-white hopping rule of the two-dimensional code, the horizontal direction and the vertical direction are respectively detected around the corresponding position detection pattern, and the arrangement combination of the position detection patterns that do not conform to the black-and-white hopping rule is filtered out.

In an actual application, the acquisition module 41, the identification module 42, the pre-processing module 43, and the decoding module 44 may each be a central processing unit (CPU) located on a terminal displaying the two-dimensional code, and a microprocessor (MPU). , Micro Processor Unit), digital signal processor (DSP, Digital Signal Processor), or Field Programmable Gate Array (FPGA).

The embodiment of the present invention collects an image to be recognized that includes a two-dimensional code of the illuminating display; extracts a position detecting pattern in the image to be recognized, determines a position of the two-dimensional code in the image to be recognized according to the position detecting pattern, and identifies A two-dimensional code within the two-dimensional code position. In this way, according to the difference of the average brightness of different two-dimensional code regions, the two-dimensional code in the image to be recognized collected by using different metering methods is processed correspondingly, and the two-dimensional code displayed based on the LED array can be identified; optionally, the present invention The embodiment of the invention can also adjust the subsequent corresponding processing for the working mode of the user-selected identification two-dimensional code, and use different processing methods to quickly and accurately identify the single or multiple two-dimensional codes displayed by the LED array, which has high recognition efficiency. , thereby improving user perception of use, and two-dimensional code recognition technology The development is of great significance.

The above is only the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in Within the scope of protection of the present invention.

Industrial applicability

An embodiment of the present invention discloses a method for recognizing a two-dimensional code, comprising: acquiring an image to be recognized that includes a two-dimensional code of a light-emitting display; extracting a position detection pattern in the image to be recognized, and determining, according to the position detection pattern, The two-dimensional code position in the identified image is referred to, and the two-dimensional code within the two-dimensional code position is identified. The embodiment of the invention also discloses a two-dimensional code identification device and a storage medium. By implementing the present invention, it is possible to quickly and accurately identify a two-dimensional code that is actively illuminated by an LED array.

Claims (18)

A method for identifying a two-dimensional code, the method comprising: Acquiring an image to be recognized containing a two-dimensional code of the illuminating display; Extracting a position detection pattern in the image to be identified, determining a two-dimensional code position in the image to be recognized according to the position detection pattern, and identifying a two-dimensional code in the two-dimensional code position. The method of claim 1, wherein the acquiring the image to be recognized comprising the two-dimensional code of the illuminating display comprises: Select a working mode for identifying the two-dimensional code; Accessing and calling the bottom layer of the terminal camera identifying the two-dimensional code according to the selected working mode, adjusting the scanning parameter, and collecting the image to be recognized by using the metering mode corresponding to the selected working mode. The method according to claim 2, wherein the collecting the image to be recognized by using the photometry corresponding to the selected working mode comprises: When the selected working mode is a single two-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by using a central key metering method, and the two-dimensional code region of the black and white is highlighted, and the two-dimensional code is not included. Background area blurring; When the selected working mode is a multi-dimensional code recognition mode, the two-dimensional code in the image to be recognized is read by an average metering method, and the two-dimensional code is specially preprocessed. The method according to claim 3, wherein said performing special pre-processing on said two-dimensional code comprises: detecting a brightness distribution of said image to be recognized containing said two-dimensional code, and performing corresponding processing according to different brightness distributions. The method according to claim 4, wherein the detecting the brightness distribution of the image to be recognized containing the two-dimensional code and performing corresponding processing according to different brightness distributions comprises: If the position detection pattern conforms to the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, a plurality of two-dimensional code areas are sequentially determined according to the brightness level; If there is no significant difference in the brightness distribution of different two-dimensional code regions, all the extracted position detection patterns are classified into one set, and any three position detection patterns in the collection are arranged and combined to detect whether each permutation combination satisfies certain conditions. The two-dimensional code region is determined according to the permutation combination satisfying the condition. The method according to claim 5, wherein said detecting whether each permutation combination satisfies certain conditions includes: According to the black-and-white hopping rule of the two-dimensional code, the horizontal direction and the vertical direction are respectively detected around the corresponding position detection pattern, and the arrangement combination of the position detection patterns that do not conform to the black-and-white hopping rule is filtered out. The method of claim 1, wherein after the determining the location of the two-dimensional code in the image to be identified, the method further comprises: Preprocessing the two-dimensional code in the two-dimensional code position, and decoding the pre-processed two-dimensional code to obtain corresponding information; The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position. The method according to any one of claims 1 to 7, wherein the two-dimensional code is a two-dimensional code displayed based on an LED array of light-emitting diodes. A device for identifying a two-dimensional code, the device comprising: an acquisition module and an identification module; wherein The acquiring module is configured to collect an image to be recognized that includes a two-dimensional code of the illuminating display; The identification module is configured to extract a position detection pattern in the image to be identified, determine a two-dimensional code position in the image to be recognized according to the position detection pattern, and identify a two-dimensional position in the two-dimensional code position code. The apparatus according to claim 9, wherein The collection module is further configured to select an operation mode for identifying the two-dimensional code; according to the selection The working mode accesses and calls the bottom layer of the terminal camera that identifies the two-dimensional code, adjusts the scanning parameters, and collects the image to be recognized by using the metering mode corresponding to the selected working mode. The device according to claim 10, wherein The collecting module is further configured to read the two-dimensional code in the image to be recognized by using a central key metering mode when the selected working mode is a single two-dimensional code recognition mode, and highlight the two-dimensional code area of the black and white And blurring the background area other than the QR code; The collecting module is further configured to: when the selected working mode is a multi-dimensional code recognition mode, read the two-dimensional code in the image to be recognized by using an average metering mode, and perform special on the two-dimensional code Pretreatment. The apparatus according to claim 11, wherein the acquisition module is further configured to detect a brightness distribution of the image to be recognized including the two-dimensional code, and perform corresponding processing according to different brightness distributions. The device according to claim 12, wherein The acquiring module is further configured to: if the position detecting pattern meets the geometric positional relationship of the two-dimensional code, and the brightness distribution of the different two-dimensional code areas is significantly different, determining a plurality of two-dimensional code areas according to the brightness level; The collecting module is further configured to classify all the extracted position detection images into one set if the brightness distribution of the different two-dimensional code areas is not significantly different, and arrange and combine the three position detection patterns in the collection, and detect each Whether the combination of the arrays satisfies certain conditions, and determines the two-dimensional code region according to the arrangement and combination of the satisfied conditions. The device according to claim 13, wherein The acquiring module is further configured to detect the horizontal direction and the vertical direction respectively according to the black and white hopping rule of the two-dimensional code, and filter the position detecting patterns that do not conform to the black and white hopping rule. Permutations. The apparatus of claim 9 wherein said apparatus further comprises: a pre-processing module, configured to pre-process the two-dimensional code in the two-dimensional code position after the identification module determines the two-dimensional code position in the image to be identified; a decoding module, configured to decode the two-dimensional code preprocessed by the preprocessing module to obtain corresponding information; The pre-processing includes: filtering out noise that interferes with the decoding of the two-dimensional code, and correcting the two-dimensional code in the two-dimensional code position. The apparatus according to any one of claims 9 to 15, wherein the two-dimensional code is a two-dimensional code displayed based on an LED array. A two-dimensional code recognition device, comprising a camera, a processor and a memory; The camera is configured to collect an image to be recognized that includes a two-dimensional code of the illuminating display; Storing executable instructions for causing the processor to perform an operation of: extracting a position detection pattern in the image to be identified, and determining a two-dimensional image in the image to be recognized according to the position detection pattern The code position and identifying the two-dimensional code within the two-dimensional code position. A storage medium storing executable instructions for performing the method of identifying a two-dimensional code according to any one of claims 1 to 8.

Images