CN107609559B - A recognition method and system based on VR anti-counterfeiting technology - Google Patents

A recognition method and system based on VR anti-counterfeiting technology Download PDF

Info

Publication number
CN107609559B
CN107609559B CN201710890189.XA CN201710890189A CN107609559B CN 107609559 B CN107609559 B CN 107609559B CN 201710890189 A CN201710890189 A CN 201710890189A CN 107609559 B CN107609559 B CN 107609559B
Authority
CN
China
Prior art keywords
commodity
counterfeiting information
pictures
phrase
watch
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201710890189.XA
Other languages
Chinese (zh)
Other versions
CN107609559A (en
Inventor
叶玉成
陈文锋
李蔼璇
徐其荣
邓江华
彭小红
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wbiao Technology Co ltd
Original Assignee
Wbiao Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wbiao Technology Co ltd filed Critical Wbiao Technology Co ltd
Priority to CN201710890189.XA priority Critical patent/CN107609559B/en
Publication of CN107609559A publication Critical patent/CN107609559A/en
Application granted granted Critical
Publication of CN107609559B publication Critical patent/CN107609559B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Character Discrimination (AREA)

Abstract

本发明涉及一种基于VR防伪技术的识别方法和系统,所述方法,包括:对商品进行扫描,得到扫描视频;根据扫描视频设置商品的防伪信息,并将防伪信息存储在服务器的数据库中;商品被交易后,用户根据待识别商品的外观查询防伪信息。本发明通过在商品进行出售前,先获取商品的图片和词组,将所述图片、词组和商品的防伪信息进行关联,并保存在数据库中。在商品出售后需要查询其防伪信息时,通过待识别商品的外观即可查询到防伪信息,简单方便。

Figure 201710890189

The invention relates to a recognition method and system based on VR anti-counterfeiting technology. The method includes: scanning a commodity to obtain a scanned video; setting anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in a database of a server; After the commodity is traded, the user queries the anti-counterfeiting information according to the appearance of the commodity to be identified. The present invention obtains the pictures and phrases of the commodities before the commodities are sold, associates the pictures, phrases and the anti-counterfeiting information of the commodities, and saves them in the database. When the anti-counterfeiting information of the commodity needs to be inquired after it is sold, the anti-counterfeiting information can be inquired through the appearance of the commodity to be identified, which is simple and convenient.

Figure 201710890189

Description

Identification method and system based on VR anti-counterfeiting technology
Technical Field
The invention relates to the technical field of identification, in particular to an identification method and system based on a VR anti-counterfeiting technology.
Background
At present, electronic products are basically identified by using serial numbers on a guarantee card, and after-sale services also need to use the guarantee card to identify the guarantee period of the electronic products. Since electronic products are often stored separately from the warranty card, such warranty cards are easily lost. Once lost, it is difficult for a general user to confirm the authenticity of an electronic product, the warranty period of the electronic product, and the like, for example, a watch.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides an identification method and system based on a VR anti-counterfeiting technology.
An identification method based on VR anti-counterfeiting technology comprises the following steps: scanning the commodity to obtain a scanning video; setting anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in a database of the server; after the commodity is traded, the user inquires the anti-counterfeiting information according to the appearance of the commodity to be identified.
Preferably, the step of setting the anti-counterfeiting information of the commodity according to the scanned video and storing the anti-counterfeiting information in the database of the server comprises: acquiring a preset number of pictures from the scanning video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; and associating the picture, the phrase and the anti-counterfeiting information to complete the setting of the anti-counterfeiting information of the commodity.
Preferably, the step of querying the anti-counterfeiting information by the user according to the appearance of the commodity to be identified comprises: scanning a commodity to be identified to obtain a scanning video; acquiring a preset number of pictures from the scanning video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; matching the phrases with phrases in a database; if the phrase matching is passed, matching the picture with the picture of the commodity which passes the phrase matching in the database; and if the pictures are matched, identifying the commodity and displaying the anti-counterfeiting information of the commodity to be identified.
Preferably, the step of querying the anti-counterfeiting information by the user according to the appearance of the commodity to be identified comprises: and inquiring the anti-counterfeiting information of the commodity according to the unique code of the commodity.
Preferably, the step of scanning the commodity to obtain the scanned video comprises: and shooting the commodity by 360 degrees by using the camera according to a preset shooting speed to obtain a scanned video.
An identification system based on VR anti-counterfeiting technology, comprising: the anti-counterfeiting information setting module and the anti-counterfeiting information identification module; the anti-counterfeiting information setting module is used for scanning the commodity to obtain a scanning video; setting anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in a database of the server; and the anti-counterfeiting information identification module is used for inquiring anti-counterfeiting information according to the appearance of the commodity to be identified by a user after the commodity is traded.
Preferably, the anti-counterfeiting information setting module is further configured to obtain a preset number of pictures from the scanned video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; and associating the picture, the phrase and the anti-counterfeiting information to complete the setting of the anti-counterfeiting information of the commodity.
Preferably, the anti-counterfeiting information identification module is further configured to scan the commodity to be identified to obtain a scanned video; acquiring a preset number of pictures from the scanning video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; matching the phrases with phrases in a database; if the phrase matching is passed, matching the picture with the picture of the commodity which passes the phrase matching in the database; and if the pictures are matched, identifying the commodity and displaying the anti-counterfeiting information of the commodity to be identified.
Preferably, the anti-counterfeiting information identification module is further configured to query the anti-counterfeiting information of the commodity according to the unique code of the commodity.
Preferably, the anti-counterfeiting information setting module is further configured to use a camera to shoot the commodity at 360 degrees according to a preset shooting speed, so as to obtain a scanned video.
The invention has the beneficial effects that: according to the invention, before the commodity is sold, the picture and the phrase of the commodity are obtained, and the picture, the phrase and the anti-counterfeiting information of the commodity are associated and stored in the database. When the anti-counterfeiting information of the commodity needs to be inquired after the commodity is sold, the anti-counterfeiting information can be inquired through the appearance of the commodity to be identified, and the method is simple and convenient.
Drawings
The invention is further illustrated with reference to the following figures and examples.
Fig. 1 is a schematic flow chart of an identification method based on VR anti-counterfeiting technology according to an embodiment.
Fig. 2 is a schematic flowchart of setting anti-counterfeiting information of a commodity according to a scanned video according to an embodiment.
Fig. 3 is a schematic flowchart of a user querying anti-counterfeit information according to the appearance of a to-be-identified commodity according to an embodiment.
Fig. 4 is a schematic structural diagram of an identification system based on VR anti-counterfeiting technology according to an embodiment.
Detailed Description
The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic views illustrating only the basic structure of the present invention in a schematic manner, and thus show only the constitution related to the present invention.
Example 1
Referring to fig. 1 to 3, an identification method based on VR anti-counterfeiting technology includes:
s11, scanning the commodity to obtain a scanned video; specifically, a camera is used for shooting the commodity at 360 degrees according to a preset shooting speed, and a scanned video is obtained. In particular, the front and back sides of the watch are carefully photographed. The preset photographing speed may be 30 fps. The shot watch appearance video is stored in the server.
The commodity of this embodiment is the wrist-watch, and the merchant carries out the anti-fake information setting of all wrist-watches before selling the wrist-watch. The anti-counterfeiting information is set based on AR anti-counterfeiting technology. Before the anti-counterfeiting information is set, the merchant needs to perform authentication in the AR system, mainly the qualification information of the merchant, including information such as company name, address, contact, business license and the like. The merchant qualification is approved by an AR system administrator, and the merchant after approval can set AR anti-counterfeiting information on the watch.
S12, setting anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in a database of the server;
and S13, after the commodity is traded, the user inquires the anti-counterfeiting information according to the appearance of the commodity to be identified.
Wherein, step S12 includes:
s121, acquiring a preset number of pictures from the scanning video according to a preset rule; specifically, a video recorded at a speed of 30fps is analyzed into 30 pictures every 1 second, and 5 pictures are fixedly acquired as effective pictures (1 st, 4 th, 9 th, 16 th and 25 th pictures respectively). Thus if a video is taken for N seconds, 5 x N pictures will be taken.
S122, carrying out character recognition on the picture by using an OCR plug-in unit to obtain recognized characters;
s123, segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; specifically, the recognized characters are divided into a plurality of different phrases according to spaces (") and connectors (" - "), and are sequentially stored in a database according to the recognized sequence, and if the recognized characters exist, only one character is stored, and the character is not stored repeatedly; one of the phrases is a unique code on the back of the mobile phone.
And S124, associating the picture, the phrase and the anti-counterfeiting information to complete the setting of the anti-counterfeiting information of the commodity, and storing the picture and the phrase in a database of a server. The anti-counterfeiting information comprises currently used merchants, sale time, sale places (GPS addresses), watch brands, watch models, watch bar codes and AR identification related pictures.
Wherein, step S13 includes:
s131, scanning the commodity to be identified to obtain a scanned video; using the camera, the watch was scanned 360 degrees.
S132, acquiring a preset number of pictures from the scanned video according to a preset rule;
s133, character recognition is carried out on the picture by utilizing an OCR plug-in unit to obtain recognized characters;
s134, segmenting the recognition characters according to preset segmentation rules to obtain more than one phrase;
s135, matching the phrases with phrases in a database; and if the phrase number of the phrases of the commodity to be identified is the same as the phrase number of the commodity stored in the data, the matching is passed.
S136, if the phrase matching passes, matching the picture with the picture of the commodity which passes the phrase matching in the database; the specific matching process is as follows:
if the length of the currently uploaded video is M seconds, the number of pictures is 5 × M, and the hash algorithm is as follows:
step 1, reducing the size: the image is reduced to a size of 8 x 8 for a total of 64 pixels. The step has the effects of removing the details of the image, only retaining the basic information of structure/brightness and the like, and abandoning the image difference caused by different sizes/proportions;
step 2, simplifying color: converting the reduced image into 64-level gray, namely that all pixel points have 64 colors in total;
step 3, calculating an average value: calculating the gray level average value of all 64 pixels;
and 4, comparing the gray scale of the pixel: comparing the gray scale of each pixel with the average value, and recording the average value greater than or equal to 1 and the average value smaller than 0;
step 5, calculating a hash value: the comparison results from the previous step are combined to form a 64-bit integer, which is the fingerprint of the image. The order of the combination is not important as long as it is guaranteed that all images take the same order;
and 6, after the fingerprints are obtained, different images can be compared, and how many of the 64 bits are different. In theory, this is equivalent to the "Hamming distance" (in the information theory, the Hamming distance between two equal-length character strings is the number of different characters at the corresponding positions of the two character strings). If the number of the different data bits does not exceed 5, the two images are very similar; if greater than 10, this indicates that these are two different images. If the 5 x N pictures are compared in the 5 x M pictures, the total number of the compared 5 x N pictures is 25 x M x N times, if 22.5 x M x N (namely the probability of 90 percent) pictures in the comparison have different digits not exceeding 5, the group of pictures and the server anti-counterfeiting picture are considered to be consistent, at the moment, the APP can prompt that the identification is successful, and the identified watch anti-counterfeiting information, such as the brand, the model, the purchase time and the purchase place (GPS address) of the watch, is displayed.
And S137, if the pictures are matched, identifying the commodity and displaying the anti-counterfeiting information of the commodity to be identified.
As an alternative embodiment, step S13 includes: and inquiring the anti-counterfeiting information of the commodity according to the unique code of the commodity. Specifically, a unique code on the back of the watch is input, the unique code is compared with a stored phrase in a database, and when the identical commodities are compared, the commodities to be identified are identified. It should be noted that, in the process of setting the anti-counterfeiting information of the commodity, the system can identify all phrases on the bottom cover, and one group in the phrases is the unique code; therefore, the system is internally provided with the unique codes of various watches.
According to the scheme, before the commodity is sold, the picture and the phrase of the commodity are obtained, the picture, the phrase and the anti-counterfeiting information of the commodity are associated and stored in the database. When the anti-counterfeiting information of the commodity needs to be inquired after the commodity is sold, the anti-counterfeiting information can be inquired by inputting the unique code on the back of the commodity or shooting the appearance of the commodity, and the method is simple and convenient.
Example 2
Referring to fig. 4, an identification system based on VR anti-counterfeiting technology includes: the anti-counterfeiting information setting module 11 and the anti-counterfeiting information identification module 12; the anti-counterfeiting information setting module 11 is used for scanning the commodity to obtain a scanning video; setting anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in a database of the server; the anti-counterfeiting information identification module 12 is used for inquiring anti-counterfeiting information according to the appearance of the commodity to be identified by a user after the commodity is traded.
In this embodiment, the anti-counterfeiting information setting module 11 is further configured to obtain a preset number of pictures from the scanned video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; and associating the picture, the phrase and the anti-counterfeiting information to complete the setting of the anti-counterfeiting information of the commodity.
In this embodiment, the anti-counterfeiting information identification module 12 is further configured to scan the to-be-identified commodity to obtain a scanned video; acquiring a preset number of pictures from the scanning video according to a preset rule; carrying out character recognition on the picture by utilizing an OCR plug-in to obtain recognized characters; segmenting the recognition characters according to a preset segmentation rule to obtain more than one phrase; matching the phrases with phrases in a database; if the phrase matching is passed, matching the picture with the picture of the commodity which passes the phrase matching in the database; and if the pictures are matched, identifying the commodity and displaying the anti-counterfeiting information of the commodity to be identified.
In this embodiment, the anti-counterfeit information identification module 12 is further configured to query the anti-counterfeit information of the commodity according to the unique code of the commodity.
In this embodiment, the anti-counterfeit information setting module is further configured to use the camera to shoot the commodity at 360 degrees according to a preset shooting speed, so as to obtain a scanned video.
Before the commodity is sold, the anti-counterfeiting information setting module acquires the picture and the phrase of the commodity, associates the picture, the phrase and the anti-counterfeiting information of the commodity and stores the image, the phrase and the anti-counterfeiting information in the database. When the anti-counterfeiting information of the commodity needs to be inquired after the commodity is sold, the anti-counterfeiting information can be inquired by the anti-counterfeiting information identification module through the appearance of the commodity to be identified, and the method is simple and convenient.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.

Claims (2)

1.一种基于VR防伪技术的识别方法,其特征在于,包括:1. an identification method based on VR anti-counterfeiting technology, is characterized in that, comprises: S11,对商品进行扫描,得到扫描视频;S11, scan the commodity to obtain a scanned video; S12,根据扫描视频设置商品的防伪信息,并将防伪信息存储在服务器的数据库中;S12, setting the anti-counterfeiting information of the commodity according to the scanned video, and storing the anti-counterfeiting information in the database of the server; S13,商品被交易后,用户根据待识别商品的外观查询防伪信息;S13, after the commodity is traded, the user queries the anti-counterfeiting information according to the appearance of the commodity to be identified; 其中,步骤S12包括:Wherein, step S12 includes: S121,从所述扫描视频中按照预设规则获取预设数量的图片;具体的,按照30fps的速度录制的视频,每1秒的视频将解析为30张图片,固定获取5张照片作为有效照片;这样如果拍摄了N秒时间的视频,将获取5*N张的图片;S121, obtaining a preset number of pictures from the scanned video according to a preset rule; specifically, for a video recorded at a speed of 30fps, every 1 second of video will be parsed into 30 pictures, and 5 pictures are fixedly obtained as valid pictures ; In this way, if a video of N seconds is taken, 5*N pictures will be obtained; S122,利用OCR插件对所述图片进行文字识别,得到识别文字;S122, using the OCR plug-in to perform text recognition on the picture to obtain the recognized text; S123,按照预设分割规则对所述识别文字进行分割,得到不止一个的词组;具体地,对所识别出来的文字,按照空格和连接符进行分割为多个不同的词组,按照识别出来的顺序依次保存到数据库中,如果存在重复识别的文字,则只保存一份,不重复保存;其中的一种词组为手机背面的唯一码;S123, dividing the recognized text according to a preset dividing rule to obtain more than one phrase; specifically, dividing the recognized text into a plurality of different phrases according to spaces and connectors, and according to the recognized order Save them to the database one by one, if there are repeatedly recognized words, only one copy is saved, not repeated; one of the phrases is the unique code on the back of the phone; S124,将所述图片、词组和防伪信息进行关联,完成商品的防伪信息的设置,并将所述图片、词组进行存储在服务器的数据库中;其中防伪信息包括当前使用的商家、销售时间、销售地点、手表品牌、手表型号、手表条码以及AR识别的相关图片;S124, associate the pictures, phrases and anti-counterfeiting information, complete the setting of anti-counterfeiting information of the commodity, and store the pictures and phrases in the database of the server; wherein the anti-counterfeiting information includes the currently used merchant, sales time, sales Location, watch brand, watch model, watch barcode and related pictures of AR recognition; 其中,步骤S13包括:Wherein, step S13 includes: S131,对待识别商品进行扫描,得到扫描视频;使用摄像头,对手表进行360度的扫描;S131, scan the commodity to be identified to obtain a scanned video; use a camera to scan the watch 360 degrees; S132,从所述扫描视频中按照预设规则获取预设数量的图片;S132, obtaining a preset number of pictures from the scanned video according to a preset rule; S133,利用OCR插件对所述图片进行文字识别,得到识别文字;S133, using the OCR plug-in to perform text recognition on the picture to obtain the recognized text; S134,按照预设分割规则对所述识别文字进行分割,得到不止一个的词组;S134, segment the recognized text according to a preset segmentation rule to obtain more than one phrase; S135,将所述词组和数据库内的词组进行匹配;若待识别商品的所述词组的词组数和数据中保存的商品的词组数相同,则匹配通过;S135, matching the phrase with the phrase in the database; if the phrase number of the phrase of the commodity to be identified is the same as the phrase number of the commodity stored in the data, the match is passed; S136,若词组匹配通过,则将所述图片和数据库内词组匹配通过的商品的图片进行匹配;具体的匹配过程如下:S136, if the phrase matching is passed, then the picture is matched with the picture of the commodity in the database that has passed the phrase matching; the specific matching process is as follows: 若当前上传视频的长度为M秒,则图片数为5*M,按照哈希算法如下:If the length of the currently uploaded video is M seconds, the number of pictures is 5*M, according to the hash algorithm as follows: 步骤1.缩小尺寸:将图像缩小到8*8的尺寸,总共64个像素;这一步的作用是去除图像的细节,只保留结构/明暗基本信息,摒弃不同尺寸/比例带来的图像差异;Step 1. Reduce the size: reduce the image to 8*8 size, with a total of 64 pixels; the function of this step is to remove the details of the image, retain only the basic information of structure/light and shade, and discard the image differences caused by different sizes/ratios; 步骤2.简化色彩:将缩小后的图像,转为64级灰度,即所有像素点总共只有64种颜色;Step 2. Simplify colors: Convert the reduced image to 64-level grayscale, that is, all pixels have only 64 colors in total; 步骤3.计算平均值:计算所有64个像素的灰度平均值;Step 3. Calculate the mean value: Calculate the grayscale mean value of all 64 pixels; 步骤4.比较像素的灰度:将每个像素的灰度,与平均值进行比较,大于或等于平均值记为1,小于平均值记为0;Step 4. Compare the grayscale of the pixels: compare the grayscale of each pixel with the average value, if it is greater than or equal to the average value, it is recorded as 1, and if it is less than the average value, it is recorded as 0; 步骤5.计算哈希值:将上一步的比较结果,组合在一起,就构成了一个64位的整数,这就是这张图像的指纹;组合的次序并不重要,只要保证所有图像都采用同样次序就行了;Step 5. Calculate the hash value: Combine the comparison results of the previous step to form a 64-bit integer, which is the fingerprint of this image; the order of combination is not important, as long as all images use the same order is enough; 步骤6.得到指纹以后,对比不同的图像,看看64位中有多少位是不一样的;如果不相同的数据位数不超过5,就说明两张图像很相似;如果大于10,就说明这是两张不同的图像;如果5*M张图片中对比5*N张图片一共有25*M*N次对比,对比中如果有22.5*M*N张图片不同位数不超过5,则认为这组图片和服务器防伪图片是一致的,此时APP提示识别成功,展示识别出来的手表防伪信息,包括手表的品牌、型号、购买时间、购买地点;Step 6. After obtaining the fingerprint, compare different images to see how many bits in the 64 bits are different; if the number of different data bits does not exceed 5, it means that the two images are very similar; if it is greater than 10, it means that the two images are very similar. These are two different images; if there are 25*M*N comparisons in the 5*M images compared with 5*N images, and if there are 22.5*M*N images in the comparison, the number of different digits does not exceed 5, then It is believed that this group of pictures is consistent with the server anti-counterfeiting pictures. At this time, the APP prompts that the identification is successful, and displays the identified anti-counterfeiting information of the watch, including the brand, model, purchase time, and purchase location of the watch; S137,若图片匹配通过,则识别到所述商品,展示待识别商品的防伪信息。S137 , if the image matching is passed, the commodity is identified, and the anti-counterfeiting information of the commodity to be identified is displayed. 2.一种基于VR防伪技术的识别系统,其特征在于,用于实现权利要求1中的方法,包括:防伪信息设置模块和防伪信息识别模块;2. An identification system based on VR anti-counterfeiting technology, characterized in that, for realizing the method in claim 1, comprising: an anti-counterfeiting information setting module and an anti-counterfeiting information identification module; 所述防伪信息设置模块,用于对商品进行扫描,得到扫描视频;The anti-counterfeiting information setting module is used to scan the commodity to obtain the scanned video; 具体地,使用摄像头按照预设拍摄速度对商品进行360度的拍摄,得到扫描视频;对手表的正反两面进行细致拍摄;预设拍摄速度为30fps;拍摄的手表外观视频将保存到服务器中;Specifically, the camera is used to shoot 360 degrees of the product according to the preset shooting speed to obtain a scanned video; the front and back sides of the watch are carefully shot; the preset shooting speed is 30fps; the shot video of the appearance of the watch will be saved to the server; 所述商品为手表,商家在出售手表前,先进行所有手表的防伪信息设置;设置防伪信息时基于AR防伪技术;在设置防伪信息之前,商家需要在AR系统中进行认证,包括商家的资质信息,具体为公司名称、地址、联系人、营业执照信息;商家资质由AR系统管理员进行审批,审批通过后的商家才可以对手表进行AR防伪信息的设置;The commodity is a watch. Before selling the watch, the merchant must first set the anti-counterfeiting information of all watches; when setting the anti-counterfeiting information, it is based on AR anti-counterfeiting technology; before setting the anti-counterfeiting information, the merchant needs to perform authentication in the AR system, including the merchant's qualification information , specifically the company name, address, contact person, and business license information; the merchant qualification is approved by the AR system administrator, and only after the approval can the merchant set the AR anti-counterfeiting information on the watch; 所述防伪信息设置模块,还用于从所述扫描视频中按照预设规则获取预设数量的图片;根据扫描视频设置商品的防伪信息,并将防伪信息存储在服务器的数据库中;The anti-counterfeiting information setting module is further configured to obtain a preset number of pictures from the scanned video according to preset rules; set the anti-counterfeiting information of the commodity according to the scanned video, and store the anti-counterfeiting information in the database of the server; 具体地,从所述扫描视频中按照预设规则获取预设数量的图片;具体的,按照30fps的速度录制的视频,每1秒的视频将解析为30张图片,固定获取5张照片作为有效照片;这样如果拍摄了N秒时间的视频,将获取5*N张的图片;Specifically, a preset number of pictures are obtained from the scanned video according to a preset rule; specifically, for a video recorded at a speed of 30fps, every 1 second of video will be parsed into 30 pictures, and 5 pictures are fixedly obtained as valid Photos; in this way, if a video of N seconds is taken, 5*N pictures will be obtained; 利用OCR插件对所述图片进行文字识别,得到识别文字;Use the OCR plug-in to perform text recognition on the picture to obtain the recognized text; 按照预设分割规则对所述识别文字进行分割,得到不止一个的词组;具体地,对所识别出来的文字,按照空格和连接符进行分割为多个不同的词组,按照识别出来的顺序依次保存到数据库中,如果存在重复识别的文字,则只保存一份,不重复保存;其中的一种词组为手机背面的唯一码;Divide the recognized text according to the preset segmentation rules to obtain more than one phrase; specifically, the recognized text is divided into a plurality of different phrases according to spaces and connectors, and stored in sequence according to the recognized order. In the database, if there is a repeated identification of the text, only one copy is saved, not repeated; one of the phrases is the unique code on the back of the mobile phone; 将所述图片、词组和防伪信息进行关联,完成商品的防伪信息的设置,并将所述图片、词组进行存储在服务器的数据库中;其中防伪信息包括当前使用的商家、销售时间、销售地点、手表品牌、手表型号、手表条码以及AR识别的相关图片;Associate the pictures, phrases and anti-counterfeiting information, complete the setting of the anti-counterfeiting information of the commodity, and store the pictures and phrases in the database of the server; wherein the anti-counterfeiting information includes the currently used merchant, sales time, sales location, Related pictures of watch brand, watch model, watch barcode and AR recognition; 所述防伪信息识别模块,用于商品被交易后,用户根据待识别商品的外观查询防伪信息;对待识别商品进行扫描,得到扫描视频;根据所述商品的唯一码查询所述商品的防伪信息;The anti-counterfeiting information identification module is used for users to inquire anti-counterfeiting information according to the appearance of the commodity to be identified after the commodity is traded; scan the commodity to be identified to obtain a scanned video; query the anti-counterfeiting information of the commodity according to the unique code of the commodity; 具体地,对待识别商品进行扫描,得到扫描视频;使用摄像头,对手表进行360度的扫描;从所述扫描视频中按照预设规则获取预设数量的图片;利用OCR插件对所述图片进行文字识别,得到识别文字;按照预设分割规则对所述识别文字进行分割,得到不止一个的词组;将所述词组和数据库内的词组进行匹配;若待识别商品的所述词组的词组数和数据中保存的商品的词组数相同,则匹配通过;若词组匹配通过,则将所述图片和数据库内词组匹配通过的商品的图片进行匹配;具体的匹配过程如下:Specifically, scan the product to be identified to obtain a scanned video; use a camera to scan the watch 360 degrees; obtain a preset number of pictures from the scanned video according to preset rules; use the OCR plug-in to text the picture Recognition to obtain the recognized text; segment the recognized text according to the preset segmentation rules to obtain more than one phrase; match the phrase with the phrase in the database; if the number of phrases and data of the phrase of the commodity to be identified If the number of phrases of the commodities stored in the database is the same, the matching is passed; if the phrase matching is passed, the picture is matched with the pictures of the commodities whose phrases are matched in the database; the specific matching process is as follows: 若当前上传视频的长度为M秒,则图片数为5*M,按照哈希算法如下:If the length of the currently uploaded video is M seconds, the number of pictures is 5*M, according to the hash algorithm as follows: 步骤1.缩小尺寸:将图像缩小到8*8的尺寸,总共64个像素;这一步的作用是去除图像的细节,只保留结构/明暗基本信息,摒弃不同尺寸/比例带来的图像差异;Step 1. Reduce the size: reduce the image to 8*8 size, with a total of 64 pixels; the function of this step is to remove the details of the image, retain only the basic information of structure/light and shade, and discard the image differences caused by different sizes/ratios; 步骤2.简化色彩:将缩小后的图像,转为64级灰度,即所有像素点总共只有64种颜色;Step 2. Simplify colors: Convert the reduced image to 64-level grayscale, that is, all pixels have only 64 colors in total; 步骤3.计算平均值:计算所有64个像素的灰度平均值;Step 3. Calculate the mean value: Calculate the grayscale mean value of all 64 pixels; 步骤4.比较像素的灰度:将每个像素的灰度,与平均值进行比较,大于或等于平均值记为1,小于平均值记为0;Step 4. Compare the grayscale of the pixels: compare the grayscale of each pixel with the average value, if it is greater than or equal to the average value, it is recorded as 1, and if it is less than the average value, it is recorded as 0; 步骤5.计算哈希值:将上一步的比较结果,组合在一起,就构成了一个64位的整数,这就是这张图像的指纹;组合的次序并不重要,只要保证所有图像都采用同样次序就行了;Step 5. Calculate the hash value: Combine the comparison results of the previous step to form a 64-bit integer, which is the fingerprint of this image; the order of combination is not important, as long as all images use the same order is enough; 步骤6.得到指纹以后,对比不同的图像,看看64位中有多少位是不一样的;如果不相同的数据位数不超过5,就说明两张图像很相似;如果大于10,就说明这是两张不同的图像;如果5*M张图片中对比5*N张图片一共有25*M*N次对比,对比中如果有22.5*M*N张图片不同位数不超过5,则认为这组图片和服务器防伪图片是一致的,此时APP提示识别成功,展示识别出来的手表防伪信息,包括手表的品牌、型号、购买时间、购买地点;Step 6. After obtaining the fingerprint, compare different images to see how many bits in the 64 bits are different; if the number of different data bits does not exceed 5, it means that the two images are very similar; if it is greater than 10, it means that the two images are very similar. These are two different images; if there are 25*M*N comparisons in the 5*M images compared with 5*N images, and if there are 22.5*M*N images in the comparison, the number of different digits does not exceed 5, then It is believed that this group of pictures is consistent with the server anti-counterfeiting pictures. At this time, the APP prompts that the identification is successful, and displays the identified anti-counterfeiting information of the watch, including the brand, model, purchase time, and purchase location of the watch; 若图片匹配通过,则识别到所述商品,展示待识别商品的防伪信息。If the image matching is passed, the commodity is identified, and the anti-counterfeiting information of the commodity to be identified is displayed.
CN201710890189.XA 2017-09-27 2017-09-27 A recognition method and system based on VR anti-counterfeiting technology Active CN107609559B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710890189.XA CN107609559B (en) 2017-09-27 2017-09-27 A recognition method and system based on VR anti-counterfeiting technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710890189.XA CN107609559B (en) 2017-09-27 2017-09-27 A recognition method and system based on VR anti-counterfeiting technology

Publications (2)

Publication Number Publication Date
CN107609559A CN107609559A (en) 2018-01-19
CN107609559B true CN107609559B (en) 2021-08-31

Family

ID=61059163

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710890189.XA Active CN107609559B (en) 2017-09-27 2017-09-27 A recognition method and system based on VR anti-counterfeiting technology

Country Status (1)

Country Link
CN (1) CN107609559B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109344676B (en) * 2018-11-22 2021-09-24 福州图腾易讯信息技术有限公司 Automatic induction triggering method and system based on Hash algorithm
CN110135491A (en) * 2019-05-13 2019-08-16 四川中新华搜信息技术有限公司 A kind of exterior of commodity method for anti-counterfeit of image or video identification based on SVM

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101369317A (en) * 2008-10-14 2009-02-18 郑之敏 Method for generating simple recognition code based on serial number conversion in bill system
TWM469566U (en) * 2013-08-29 2014-01-01 Int Currency Tech Valuable document identification machine for identification using fast response codes
CN103942297A (en) * 2014-04-14 2014-07-23 立德高科(北京)数码科技有限责任公司 Method for calling relevant information through network based on picture comparison result
CN105512316B (en) * 2015-12-15 2018-12-21 中国科学院自动化研究所 A kind of Knowledge Service System of combination mobile terminal

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
《哈希算法实现图像相似度比较》;郝凡;《https://blog.csdn.net/haofan_/article/details/77097473》;20170811;全文 *

Also Published As

Publication number Publication date
CN107609559A (en) 2018-01-19

Similar Documents

Publication Publication Date Title
US9396388B2 (en) Systems, methods and computer program products for determining document validity
US9824099B2 (en) Data capture and identification system and process
US9898657B2 (en) Four-dimensional code, image identification system and image identification method based on the four-dimensional code, and retrieval system and retrieval method
US20200104594A1 (en) Item recognition processing over time
CN107423732A (en) Vehicle VIN recognition methods based on Android platform
JP5816393B1 (en) Product evaluation apparatus, method and program
US20160044203A1 (en) Electronic Ticket Transfer
US10778867B1 (en) Steganographic camera communication
CN106203225B (en) Pictorial element based on depth is deleted
CN113627411A (en) Super-resolution-based commodity identification and price matching method and system
US20200098028A1 (en) Durable memento method
CN109242473A (en) A kind of method of payment, device and electronic equipment
CN107609559B (en) A recognition method and system based on VR anti-counterfeiting technology
US20230351412A1 (en) Information processing apparatus, information processing method, information processing program, and information processing system
US20140046760A1 (en) Methods, systems, and computer readable media for identifying qualifying consumer offers
JP2017033157A (en) Product information providing system, product information providing method, terminal, application program, and management server
CN111753568B (en) Receipt information processing method and device, electronic equipment and storage medium
JP6432182B2 (en) Service providing apparatus, method, and program
CN109597905A (en) A kind of data-acquisition system and method applied to artistic work
TW202115645A (en) Back-end product launching method of self-checkout system
CN110969451A (en) Medical instrument display classification system based on intelligent product picture album
US20220292933A1 (en) Reading device
CN107729422A (en) A personality testing method and system based on commodity identification
TW202213213A (en) Method of generating checkout and training data and checkout system do not need to spend much time and labor force costs for establishing trained samples of training image recognition models
WO2009147675A1 (en) Method and device for inserting identification marks in a printed document

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
PE01 Entry into force of the registration of the contract for pledge of patent right
PE01 Entry into force of the registration of the contract for pledge of patent right

Denomination of invention: A recognition method and system based on VR anti-counterfeiting technology

Granted publication date: 20210831

Pledgee: China Co. truction Bank Corp Guangzhou Panyu branch

Pledgor: WBIAO TECHNOLOGY CO.,LTD.

Registration number: Y2024980024084