Automatic identification method and system based on goods specification information capture

Abstract

The invention discloses an automatic identification method and system based on goods specification information capture, and relates to the technical field of warehouse management, and the method comprises the steps: carrying out the three-dimensional modeling of goods; acquiring reflected sound wave intensity of the sample bar code; obtaining cargo reflection sound waves with the intensity being the reference sound wave intensity; calculating to obtain an estimated coordinate of the bar code; determining the cargo surface where the bar code is located; obtaining an image of a target surface containing the bar code as a target image; segmenting the target image to obtain at least one identification block; obtaining at least one identification block containing a part of the bar code; obtaining a bar code image; a bar code correction image is obtained; and obtaining goods specification information corresponding to the bar code correction image. By arranging the coordinate calculation module, the image acquisition module, the block segmentation module, the judgment and recognition module and the code scanning module, the position of the bar code can be determined autonomously, the image of the bar code can be acquired accurately, and cargoes cannot be blocked.

Description

Technical Field

[0001] The present invention relates to the technical field of warehouse management, and in particular to an automatic identification method and system based on capturing product specification information of goods. Background Art

[0002] The identification of product specifications is one of the main technical difficulties in realizing unmanned intelligent warehousing. In traditional logistics warehousing, barcode scanning technology is usually used to detect and identify product specifications. For barcode technology, it attaches the encoded barcode to the surface of the goods and uses a dedicated scanning reader to transmit the information from the barcode to the scanning reader using optical signals.

[0003] However, the field of view that can be recognized by barcode recognition technology is small, and the barcode position needs to be determined in advance. Therefore, detection and identification are generally performed manually. Specifically, staff use handheld scanners to scan and register the barcodes representing product information on the cargo boxes in real time. When the logistics is large, it is limited by the speed of manual identification, which can easily lead to cargo congestion and hinder the realization of unmanned intelligent management of warehousing. Summary of the invention

[0004] In order to solve the above technical problems, an automatic identification method and system based on capturing the product specification information of goods are provided. This technical solution solves the problem raised in the above background technology. However, the field of view that can be identified by barcode recognition technology is small, and the position of the barcode needs to be determined in advance. Therefore, it is generally detected and identified by manual hand-held means. Specifically, the staff uses a handheld scanner to scan and register the barcode representing the product specification information of the cargo box in real time. When the logistics is large, it is limited by the speed of manual identification, which is prone to cargo congestion and hinders the realization of unmanned intelligent management of warehousing.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] An automatic identification method based on capturing product specification information of goods, comprising:

[0007] Carry out three-dimensional modeling of the cargo and obtain the functional equations of the six surfaces of the cargo respectively;

[0008] Transmitting sound waves to the sample, and obtaining the intensity of the sound waves reflected by the sample barcode as a reference sound wave intensity;

[0009] The sound waves are emitted to the cargo, the initial time of the emission is recorded, and the reflected sound waves of the cargo are obtained with the intensity being the reference sound wave intensity;

[0010] Obtain the emission direction of the sound wave reflected by the goods, and obtain the end time of receiving the sound wave reflected by the goods;

[0011] Calculate the estimated coordinates of the barcode;

[0012] Determine the surface of the goods where the barcode is located as the target surface;

[0013] acquiring an image of a target surface including the barcode as a target image;

[0014] Segmenting the target image to obtain at least one recognition block, wherein the area ratio of the recognition block to the sample barcode is less than a preset ratio, and the preset ratio is less than 1;

[0015] Performing barcode recognition on the recognition block, obtaining at least one recognition block including a portion of the barcode as a target block;

[0016] Merging at least one target block to obtain a barcode image;

[0017] Correcting the barcode image to obtain a barcode corrected image;

[0018] Scan the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

[0019] Preferably, the three-dimensional modeling of the cargo to obtain the functional equations of the six surfaces of the cargo respectively comprises the following steps:

[0020] The xyz coordinate system is obtained by taking the sound wave emission position as the coordinate origin, the north-south direction as the x-axis, the east-west direction as the y-axis, and the vertical direction as the z-axis;

[0021] Select one of the six surfaces of the cargo as the characteristic surface;

[0022] Obtain three non-collinear points on the feature surface as identification points;

[0023] Obtain the coordinates of the identification point in the xyz coordinate system, and obtain the equation model of the plane Ax+By+Cz+D=0, where A, B, C and D are unknown coefficients;

[0024] Substitute the coordinates of the identified points into the plane equation model, solve for A, B, C and D, and obtain the function equation of the feature surface;

[0025] When the characteristic surface traverses the six surfaces of the goods, the function equations of the six surfaces of the goods are obtained.

[0026] Preferably, the step of calculating the estimated coordinates of the barcode comprises the following steps:

[0027] According to the end time and the initial time, the round-trip time of the reflected sound wave from the sound wave emission position to the barcode is obtained;

[0028] Obtain the speed of sound waves and calculate the distance from the reflected sound waves of the cargo to the location where the sound waves are emitted;

[0029] According to the emission direction of the sound wave reflected by the goods, the estimated coordinates of the barcode in the xyz coordinate system are obtained.

[0030] Preferably, determining the surface of the cargo where the barcode is located as the target surface comprises the following steps:

[0031] Substitute the estimated coordinates of the barcode into the function equations of the six surfaces of the cargo to obtain six function values;

[0032] Take the absolute value of the function value and get the judgment sum;

[0033] Obtain at least one minimum value in the judgment sum as the target value;

[0034] The surface of the goods corresponding to the target value is obtained as the target surface.

[0035] Preferably, performing barcode recognition on the recognition block to obtain at least one recognition block containing a portion of the barcode comprises the following steps:

[0036] Obtaining a pixel value of a black pixel as a first reference pixel value;

[0037] Obtain a pixel value of a white pixel as a second reference pixel value;

[0038] In the recognition block, a pixel point whose pixel value is the first reference pixel value is identified as a first characteristic pixel point, and when there is no pixel point whose pixel value is the first reference pixel value, the recognition block is not a target block;

[0039] Merging the first characteristic pixel points to obtain at least one characteristic region;

[0040] The merging method is to randomly obtain two first feature pixel points as the feature pixel points to be tested, and determine whether the pixel points on the line between the two feature pixel points to be tested are all first feature pixel points. If so, the two feature pixel points to be tested are merged into the same feature area, if not, no processing is performed;

[0041] Determine whether at least one feature area is a rectangle, if not, determine that the identified block is not a target block;

[0042] If yes, determining whether the pixel values ​​of the pixel points in the area between the adjacent feature areas are all second reference pixel values;

[0043] If so, it is determined that the identified block is the target block, and if not, it is determined that the identified block is not the target block.

[0044] Preferably, the step of merging at least one target block to obtain a barcode image comprises the following steps:

[0045] Perform plane modeling in the target image to obtain a plane coordinate system;

[0046] Modeling at least one target block using a plane coordinate system to obtain coordinates of each pixel in the at least one target block;

[0047] Performing plane modeling in a blank image, assigning pixel values ​​to blank pixels in the blank image, wherein the pixel values ​​of the blank pixels are the pixel values ​​of pixels with the same coordinates in at least one target block;

[0048] After the pixel values ​​are assigned, the barcode image is obtained.

[0049] Preferably, the step of correcting the barcode image to obtain a corrected barcode image comprises the following steps:

[0050] Get the minimum rectangular outline containing the barcode image;

[0051] Get the long side of the minimum rectangular outline as the reference side;

[0052] Get the characteristic angle between the reference side of the minimum rectangular contour and the horizontal direction;

[0053] The barcode image is rotated and corrected by taking the characteristic angle as the rotation angle and the left end point of the reference edge as the rotation base point to obtain a barcode corrected image.

[0054] An automatic identification system based on the capture of product specification information of goods, used to implement the above-mentioned automatic identification method based on the capture of product specification information of goods, comprising:

[0055] A three-dimensional modeling module, wherein the three-dimensional modeling module performs three-dimensional modeling on the goods and obtains function equations of six surfaces of the goods respectively;

[0056] A data acquisition module, wherein the data acquisition module acquires the intensity of the sound wave reflected by the sample barcode, acquires the sound wave reflected by the goods with an intensity equal to the reference sound wave intensity, acquires the emission direction of the sound wave reflected by the goods, and acquires the end time of receiving the sound wave reflected by the goods;

[0057] A coordinate calculation module, wherein the coordinate calculation module calculates the estimated coordinates of the barcode;

[0058] An image acquisition module, wherein the image acquisition module acquires an image of a target surface including a barcode as a target image;

[0059] A block segmentation module, wherein the block segmentation module segments the target image to obtain at least one identification block;

[0060] A determination and recognition module, wherein the determination and recognition module performs barcode recognition on the recognition block, and obtains at least one recognition block including a portion of the barcode as a target block;

[0061] An image merging module, which merges at least one target block to obtain a barcode image;

[0062] An image correction module, wherein the image correction module corrects the barcode image to obtain a barcode correction image;

[0063] The barcode scanning module scans the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] By setting up a coordinate calculation module, an image acquisition module, a block segmentation module, a judgment and recognition module and a code scanning module, the position of the barcode can be determined autonomously, and the image of the barcode can be accurately acquired through preliminary positioning and merging after segmentation, and the barcode image can be rotated and corrected to prevent it from being tilted. Thus, unmanned intelligent barcode acquisition can be realized, and then the barcode scanning can be completed using automated equipment to obtain the goods information contained in the barcode. The automated operation speed is fast, and when the amount of goods is large, the goods will not be blocked. At the same time, due to the automatic acquisition of barcodes, it can assist in unmanned intelligent management of warehouses. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 It is a flow chart of the automatic identification method based on capturing the product specification information of the present invention;

[0067] Figure 2 The present invention is to perform three-dimensional modeling of goods and obtain a flow chart of function equations of six surfaces of the goods;

[0068] Figure 3 A schematic diagram of the process of calculating estimated coordinates of a barcode according to the present invention;

[0069] Figure 4 This is a schematic diagram of the process of determining the surface of goods where the barcode is located as the target surface according to the present invention;

[0070] Figure 5 A schematic diagram of a process of performing barcode recognition on a recognition block and obtaining at least one recognition block including a portion of a barcode according to the present invention;

[0071] Figure 6 A schematic diagram of the process of merging at least one target block to obtain a barcode image according to the present invention;

[0072] Figure 7 The present invention is a schematic diagram of the process of correcting a barcode image to obtain a barcode correction image. DETAILED DESCRIPTION

[0073] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0074] Reference Figure 1 As shown, an automatic identification method based on capturing product specification information of goods includes:

[0075] Carry out three-dimensional modeling of the cargo and obtain the functional equations of the six surfaces of the cargo respectively;

[0076] Transmitting sound waves to the sample, and obtaining the intensity of the sound waves reflected by the sample barcode as a reference sound wave intensity;

[0077] The sound waves are emitted to the cargo, the initial time of the emission is recorded, and the reflected sound waves of the cargo are obtained with the intensity being the reference sound wave intensity;

[0078] Obtain the emission direction of the sound wave reflected by the goods, and obtain the end time of receiving the sound wave reflected by the goods;

[0079] Calculate the estimated coordinates of the barcode;

[0080] Determine the surface of the goods where the barcode is located as the target surface;

[0081] acquiring an image of a target surface including the barcode as a target image;

[0082] Segmenting the target image to obtain at least one recognition block, wherein the area ratio of the recognition block to the sample barcode is less than a preset ratio, and the preset ratio is less than 1;

[0083] Performing barcode recognition on the recognition block, obtaining at least one recognition block including a portion of the barcode as a target block;

[0084] Merging at least one target block to obtain a barcode image;

[0085] Correcting the barcode image to obtain a barcode corrected image;

[0086] Scan the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image;

[0087] In this solution, sound waves are used to preliminarily locate the position of the barcode, and the image of the surface of the goods with the barcode is determined as the target image. The target image is segmented to obtain at least one recognition block. The recognition block either contains part of the barcode or does not contain part of the barcode. Since the recognition block is very small, the area of ​​the part that is not the barcode in the recognition block containing part of the barcode is small. Therefore, the recognition blocks used as target blocks are merged to obtain a barcode image that is almost entirely composed of the barcode. In this way, the barcode image can be accurately obtained. However, due to different barcode pasting conditions, the obtained barcode image may have an angle with the horizontal direction. Therefore, the barcode needs to be rotated and corrected, otherwise, it will have a certain impact on scanning and recognition.

[0088] Reference Figure 2 As shown, the three-dimensional modeling of the goods and the function equations of the six surfaces of the goods are obtained respectively, including the following steps:

[0089] The xyz coordinate system is obtained by taking the sound wave emission position as the coordinate origin, the north-south direction as the x-axis, the east-west direction as the y-axis, and the vertical direction as the z-axis;

[0090] Select one of the six surfaces of the cargo as the characteristic surface;

[0091] Obtain three non-collinear points on the feature surface as identification points;

[0092] Obtain the coordinates of the identification point in the xyz coordinate system, and obtain the equation model of the plane Ax+By+Cz+D=0, where A, B, C and D are unknown coefficients;

[0093] Substitute the coordinates of the identified points into the plane equation model, solve for A, B, C and D, and obtain the function equation of the feature surface;

[0094] When the characteristic surface traverses the six surfaces of the goods, the function equations of the six surfaces of the goods are obtained.

[0095] Reference Figure 3 As shown, calculating the estimated coordinates of the barcode includes the following steps:

[0096] According to the end time and the initial time, the round-trip time of the reflected sound wave from the sound wave emission position to the barcode is obtained;

[0097] Obtain the speed of sound waves and calculate the distance from the reflected sound waves of the cargo to the location where the sound waves are emitted;

[0098] According to the emission direction of the sound wave reflected by the goods, the estimated coordinates of the barcode in the xyz coordinate system are obtained;

[0099] The xyz coordinate system takes the sound wave emission position as the origin, and the emission direction of the sound wave reflected by the cargo is fixed. Therefore, the angles between the sound wave reflected by the cargo and the x-axis, y-axis and z-axis of the xyz coordinate system are fixed.

[0100] Project the distance from the reflected sound wave of the goods to the sound wave emission position on the x-axis, y-axis and z-axis of the xyz coordinate system to obtain the estimated coordinates of the barcode in the xyz coordinate system.

[0101] Reference Figure 4 As shown, determining the surface of the cargo where the barcode is located as the target surface includes the following steps:

[0102] Substitute the estimated coordinates of the barcode into the function equations of the six surfaces of the cargo to obtain six function values;

[0103] Take the absolute value of the function value and get the judgment sum;

[0104] Obtain at least one minimum value in the judgment sum as the target value;

[0105] Obtain the surface of the goods corresponding to the target value as the target surface;

[0106] According to the knowledge of stereo analytic geometry, when a point is on a plane, the coordinates of the point are substituted into the equation corresponding to the plane, and the equation is 0. Therefore, if the barcode is on one of the surfaces of the goods, the result of substituting the estimated coordinates of the barcode into the equation of the surface must be closest to 0. Because there is an error in the estimated coordinates of the barcode, it is not exactly on the surface of the goods. Therefore, the smallest value in at least one judgment sum is obtained as the target value, and the surface of the goods corresponding to the target value is taken as the target surface. The target surface must be the surface where the barcode is located.

[0107] Reference Figure 5 As shown, performing barcode recognition on the recognition block to obtain at least one recognition block containing a portion of the barcode includes the following steps:

[0108] Obtaining a pixel value of a black pixel as a first reference pixel value;

[0109] Obtain a pixel value of a white pixel as a second reference pixel value;

[0110] The barcode is a black and white stripe. Therefore, in the recognition block, whether the internal image is a black and white stripe needs to be known in advance.

[0111] In the recognition block, a pixel point whose pixel value is the first reference pixel value is identified as a first characteristic pixel point, and when there is no pixel point whose pixel value is the first reference pixel value, the recognition block is not a target block;

[0112] Merging the first characteristic pixel points to obtain at least one characteristic region;

[0113] The merging method is to randomly obtain two first feature pixel points as the feature pixel points to be tested, and determine whether the pixel points on the line between the two feature pixel points to be tested are all first feature pixel points. If so, the two feature pixel points to be tested are merged into the same feature area, if not, no processing is performed;

[0114] Determine whether at least one feature area is a rectangle, if not, determine that the identified block is not a target block;

[0115] If yes, determining whether the pixel values ​​of the pixel points in the area between the adjacent feature areas are all second reference pixel values;

[0116] If yes, it is determined that the identified block is the target block, if no, it is determined that the identified block is not the target block;

[0117] First, the black pixels in the recognition block are identified to obtain at least one feature area. If the recognition block is the block where part of the barcode is located, the feature area is a black stripe, so it must be a rectangle, otherwise, the recognition block is not the target block. In addition, there must be white stripes between adjacent feature areas, otherwise, the recognition block is not the target block. In this way, the recognition block containing the barcode can be selected.

[0118] Reference Figure 6 As shown, merging at least one target block to obtain a barcode image includes the following steps:

[0119] Perform plane modeling in the target image to obtain a plane coordinate system;

[0120] Modeling at least one target block using a plane coordinate system to obtain coordinates of each pixel in the at least one target block;

[0121] Performing plane modeling in a blank image, assigning pixel values ​​to blank pixels in the blank image, wherein the pixel values ​​of the blank pixels are the pixel values ​​of pixels with the same coordinates in at least one target block;

[0122] After the pixel values ​​are assigned, the barcode image is obtained.

[0123] Reference Figure 7 As shown, the barcode image is corrected to obtain a corrected barcode image, including the following steps:

[0124] Get the minimum rectangular outline containing the barcode image;

[0125] Get the long side of the minimum rectangular outline as the reference side;

[0126] Get the characteristic angle between the reference side of the minimum rectangular contour and the horizontal direction;

[0127] Taking the characteristic angle as the rotation angle and the left end point of the reference edge as the rotation base point, the barcode image is rotated and corrected to obtain a barcode corrected image;

[0128] The purpose of correcting the barcode image is to rotate the barcode image to a horizontal direction, thereby directly scanning the barcode to obtain the product information corresponding to the barcode.

[0129] An automatic identification system based on the capture of product specification information of goods, used to implement the above-mentioned automatic identification method based on the capture of product specification information of goods, comprising:

[0130] A three-dimensional modeling module, wherein the three-dimensional modeling module performs three-dimensional modeling on the goods and obtains function equations of six surfaces of the goods respectively;

[0131] A data acquisition module, wherein the data acquisition module acquires the intensity of the sound wave reflected by the sample barcode, acquires the sound wave reflected by the goods with an intensity equal to the reference sound wave intensity, acquires the emission direction of the sound wave reflected by the goods, and acquires the end time of receiving the sound wave reflected by the goods;

[0132] A coordinate calculation module, wherein the coordinate calculation module calculates the estimated coordinates of the barcode;

[0133] An image acquisition module, wherein the image acquisition module acquires an image of a target surface including a barcode as a target image;

[0134] A block segmentation module, wherein the block segmentation module segments the target image to obtain at least one identification block;

[0135] A determination and recognition module, wherein the determination and recognition module performs barcode recognition on the recognition block, and obtains at least one recognition block including a portion of the barcode as a target block;

[0136] An image merging module, which merges at least one target block to obtain a barcode image;

[0137] An image correction module, wherein the image correction module corrects the barcode image to obtain a barcode correction image;

[0138] The barcode scanning module scans the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

[0139] The working process of the above automatic identification system based on the capture of product specification information is as follows:

[0140] Step 1: The 3D modeling module performs 3D modeling on the goods and obtains the function equations of the six surfaces of the goods respectively;

[0141] Step 2: emit sound waves to the sample, and the data acquisition module obtains the intensity of the sound waves reflected by the sample barcode as the reference sound wave intensity;

[0142] Step 3: The sound waves are emitted to the goods, and the data acquisition module records the initial time of the emission, and obtains the reflected sound waves of the goods with an intensity equal to the reference sound wave intensity;

[0143] Step 4: The data acquisition module acquires the emission direction of the reflected sound wave of the goods and the end time of receiving the reflected sound wave of the goods;

[0144] Step 5: The coordinate calculation module calculates the estimated coordinates of the barcode;

[0145] Step 6: The image acquisition module determines the surface of the goods where the barcode is located as the target surface;

[0146] Step 7: The image acquisition module acquires an image of the target surface including the barcode as a target image;

[0147] Step 8: The block segmentation module segments the target image to obtain at least one identification block;

[0148] Step nine: the judging and identifying module performs barcode identification on the identification block, and obtains at least one identification block including a portion of the barcode as the target block;

[0149] Step 10: The image merging module merges at least one target block to obtain a barcode image;

[0150] Step 11: The image correction module corrects the barcode image to obtain a barcode correction image;

[0151] Step 12: The barcode scanning module scans the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

[0152] Furthermore, the present solution also proposes a storage medium on which a computer-readable program is stored, and when the computer-readable program is called, the above-mentioned automatic identification method based on capturing the product specification information of the goods is executed.

[0153] It is understandable that the storage medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; an optical medium, such as a DVD; or a semiconductor medium, such as a solid state drive (SSD).

[0154] In summary, the advantages of the present invention are: by setting a coordinate calculation module, an image acquisition module, a block segmentation module, a judgment and recognition module and a code scanning module, the position of the barcode can be determined autonomously, and the image of the barcode can be accurately acquired by preliminary positioning and merging after segmentation, and the barcode image can be rotated and corrected to prevent it from being tilted. Thus, unmanned intelligent barcode acquisition can be realized, and then the barcode scanning can be completed using automated equipment to obtain the product information of the goods contained in the barcode. The automated operation speed is fast, and when the amount of goods is large, the goods will not be blocked. At the same time, due to the automatic acquisition of the barcode, it can assist in unmanned intelligent management of warehousing.

[0155] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An automatic identification method based on capturing product specification information of goods, characterized in that: include: Carry out three-dimensional modeling of the cargo and obtain the functional equations of the six surfaces of the cargo respectively; Transmitting sound waves to the sample, and obtaining the intensity of the sound waves reflected by the sample barcode as a reference sound wave intensity; The sound waves are emitted to the cargo, the initial time of the emission is recorded, and the reflected sound waves of the cargo are obtained with the intensity being the reference sound wave intensity; Obtain the emission direction of the sound wave reflected by the goods, and obtain the end time of receiving the sound wave reflected by the goods; Calculate the estimated coordinates of the barcode; Determine the surface of the goods where the barcode is located as the target surface; acquiring an image of a target surface including the barcode as a target image; Segmenting the target image to obtain at least one recognition block, wherein the area ratio of the recognition block to the sample barcode is less than a preset ratio, and the preset ratio is less than 1; Performing barcode recognition on the recognition block, obtaining at least one recognition block including a portion of the barcode as a target block; Merging at least one target block to obtain a barcode image; Correcting the barcode image to obtain a barcode corrected image; Scan the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

2. The automatic identification method based on capturing the product specification information of goods according to claim 1 is characterized in that: The three-dimensional modeling of the cargo to obtain the functional equations of the six surfaces of the cargo respectively comprises the following steps: The xyz coordinate system is obtained by taking the sound wave emission position as the coordinate origin, the north-south direction as the x-axis, the east-west direction as the y-axis, and the vertical direction as the z-axis; Select one of the six surfaces of the cargo as the characteristic surface; Obtain three non-collinear points on the feature surface as identification points; Obtain the coordinates of the identification point in the xyz coordinate system, and obtain the equation model of the plane Ax+By+Cz+D=0, where A, B, C and D are unknown coefficients; Substitute the coordinates of the identified points into the plane equation model, solve for A, B, C and D, and obtain the function equation of the feature surface; When the characteristic surface traverses the six surfaces of the goods, the function equations of the six surfaces of the goods are obtained.

3. The automatic identification method based on capturing the product specification information of goods according to claim 2 is characterized in that: The calculation of the estimated coordinates of the barcode comprises the following steps: According to the end time and the initial time, the round-trip time of the reflected sound wave from the sound wave emission position to the barcode is obtained; Obtain the speed of sound waves and calculate the distance from the reflected sound waves of the cargo to the location where the sound waves are emitted; According to the emission direction of the sound wave reflected by the goods, the estimated coordinates of the barcode in the xyz coordinate system are obtained.

4. The automatic identification method based on capturing the product specification information of goods according to claim 3 is characterized in that: Determining the surface of the cargo where the barcode is located as the target surface comprises the following steps: Substitute the estimated coordinates of the barcode into the function equations of the six surfaces of the cargo to obtain six function values; Take the absolute value of the function value and get the judgment sum; Obtain at least one minimum value in the judgment sum as the target value; The surface of the goods corresponding to the target value is obtained as the target surface.

5. The automatic identification method based on capturing the product specification information of goods according to claim 4 is characterized in that: The step of performing barcode recognition on the recognition block to obtain at least one recognition block including a portion of the barcode comprises the following steps: Obtaining a pixel value of a black pixel as a first reference pixel value; Obtain a pixel value of a white pixel as a second reference pixel value; In the recognition block, a pixel point whose pixel value is the first reference pixel value is identified as a first characteristic pixel point, and when there is no pixel point whose pixel value is the first reference pixel value, the recognition block is not a target block; Merging the first characteristic pixel points to obtain at least one characteristic region; The merging method is to randomly obtain two first feature pixel points as the feature pixel points to be tested, and determine whether the pixel points on the line between the two feature pixel points to be tested are all first feature pixel points. If so, the two feature pixel points to be tested are merged into the same feature area, if not, no processing is performed; Determine whether at least one feature area is a rectangle, if not, determine that the identified block is not a target block; If yes, determining whether the pixel values ​​of the pixel points in the area between the adjacent feature areas are all second reference pixel values; If so, it is determined that the identified block is the target block, and if not, it is determined that the identified block is not the target block.

6. The automatic identification method based on capturing the product specification information of goods according to claim 5 is characterized in that: The step of merging at least one target block to obtain a barcode image comprises the following steps: Perform plane modeling in the target image to obtain a plane coordinate system; Modeling at least one target block using a plane coordinate system to obtain coordinates of each pixel in the at least one target block; Performing plane modeling in a blank image, assigning pixel values ​​to blank pixels in the blank image, wherein the pixel values ​​of the blank pixels are the pixel values ​​of pixels with the same coordinates in at least one target block; After the pixel values ​​are assigned, the barcode image is obtained.

7. The automatic identification method based on capturing the product specification information of goods according to claim 6 is characterized in that: The step of correcting the barcode image to obtain a corrected barcode image comprises the following steps: Get the minimum rectangular outline containing the barcode image; Get the long side of the minimum rectangular outline as the reference side; Get the characteristic angle between the reference side of the minimum rectangular contour and the horizontal direction; The barcode image is rotated and corrected by taking the characteristic angle as the rotation angle and the left end point of the reference edge as the rotation base point to obtain a barcode corrected image.

8. An automatic identification system based on the capture of product specification information of goods, used to implement the automatic identification method based on the capture of product specification information of goods as described in any one of claims 1 to 7, characterized in that: include: A three-dimensional modeling module, wherein the three-dimensional modeling module performs three-dimensional modeling on the goods and obtains function equations of six surfaces of the goods respectively; A data acquisition module, wherein the data acquisition module acquires the intensity of the sound wave reflected by the sample barcode, acquires the sound wave reflected by the goods with an intensity equal to the reference sound wave intensity, acquires the emission direction of the sound wave reflected by the goods, and acquires the end time of receiving the sound wave reflected by the goods; A coordinate calculation module, wherein the coordinate calculation module calculates the estimated coordinates of the barcode; An image acquisition module, wherein the image acquisition module acquires an image of a target surface including a barcode as a target image; A block segmentation module, wherein the block segmentation module segments the target image to obtain at least one identification block; A determination and recognition module, wherein the determination and recognition module performs barcode recognition on the recognition block, and obtains at least one recognition block including a portion of the barcode as a target block; An image merging module, which merges at least one target block to obtain a barcode image; An image correction module, wherein the image correction module corrects the barcode image to obtain a barcode correction image; The barcode scanning module scans the barcode correction image to obtain the product specification information of the goods corresponding to the barcode correction image.

Images