TWI823463B - Label integrity adaptive detection method and system - Google Patents
Label integrity adaptive detection method and system Download PDFInfo
- Publication number
- TWI823463B TWI823463B TW111125555A TW111125555A TWI823463B TW I823463 B TWI823463 B TW I823463B TW 111125555 A TW111125555 A TW 111125555A TW 111125555 A TW111125555 A TW 111125555A TW I823463 B TWI823463 B TW I823463B
- Authority
- TW
- Taiwan
- Prior art keywords
- label
- image
- roi
- detection
- tag
- Prior art date
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 114
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 31
- 239000000463 material Substances 0.000 claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 26
- 230000000007 visual effect Effects 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 5
- 230000000877 morphologic effect Effects 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 9
- 238000009432 framing Methods 0.000 description 7
- 238000002372 labelling Methods 0.000 description 7
- 238000000034 method Methods 0.000 description 6
- 238000007639 printing Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007645 offset printing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K5/00—Methods or arrangements for verifying the correctness of markings on a record carrier; Column detection devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/60—Rotation of whole images or parts thereof
- G06T3/608—Rotation of whole images or parts thereof by skew deformation, e.g. two-pass or three-pass rotation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30144—Printing quality
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Measurement Of Velocity Or Position Using Acoustic Or Ultrasonic Waves (AREA)
- Geophysics And Detection Of Objects (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
本發明公開了一種標籤完整度自適應檢測方法及系統,包括:S1、對貼完標籤的料盤拍照,自動定位標籤位置並提取標籤圖像;S2、自適應旋轉矯正標籤圖像,以獲得處於目標水平位置的檢測標籤圖像;S3、對處於目標水平位置的檢測標籤圖像進行影像處理,以識別多個ROI區域並進行框定;S4、依次對ROI區域標記ROI_n (n=1,2,3……),並讀取ROI_1的圖像資訊作為檢測標籤圖像的唯一標識;S5、將每個ROI區域與基準標籤圖像中對應ROI區域進行一一比對,以判斷標籤完整度,並輸出標籤是否完整的檢測結果。本發明的檢測方法是自適應的,利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定,並以此ROI群為範本基準,用來判斷新的列印標籤品質是否合格,無需人工干預。The invention discloses an adaptive detection method and system for label integrity, which includes: S1. Taking pictures of the labeled material tray, automatically locating the label position and extracting the label image; S2. Adaptively rotating and correcting the label image to obtain The detection label image at the target horizontal position; S3. Perform image processing on the detection label image at the target horizontal position to identify multiple ROI areas and frame them; S4. Mark the ROI areas in sequence ROI_n (n=1,2 ,3...), and read the image information of ROI_1 as the unique identifier of the detected label image; S5. Compare each ROI area one by one with the corresponding ROI area in the benchmark label image to determine the label integrity , and output the detection results of whether the label is complete. The detection method of the present invention is adaptive. It uses morphological operations and contour detection algorithms to frame the ROI of the printed information on the label, and uses this ROI group as a template to determine whether the quality of the new printed label is qualified. , without manual intervention.
Description
本發明與標籤檢測有關,特別是指一種標籤完整度自適應檢測方法及系統 The present invention relates to label detection, and in particular refers to a label integrity adaptive detection method and system.
當前貼標機情況是,印表機列印完條碼,機械手臂貼附完成後到達出料口,僅僅利用掃碼器對標籤上的條碼進行讀取,而對標籤上的列印資訊內容是否完整和格式是否正確不予檢測。出現貼有列印資訊發生偏移、漏列印等問題標籤的料盤,只要掃碼器能讀取出代表料號的條碼資訊,則料盤仍然會正常入庫,因而易發生貼標機出標品質差的問題,同時還影響到了後續生產流程。因此,對貼標後的料盤進行標籤完整度檢測意義重大。 The current situation of the labeling machine is that after the printer prints the barcode and the robot arm arrives at the outlet after attaching, it only uses the scanner to read the barcode on the label, and whether the printed information content on the label is Completeness and correct format will not be checked. If there are trays with labels with problems such as offset printing information or missing printing, as long as the scanner can read the barcode information representing the material number, the trays will still be put into the warehouse normally, so labeling machine outages are prone to occur. The problem of poor quality standards also affects the subsequent production process. Therefore, it is of great significance to test the label integrity of the labeled trays.
當前標籤完整度的檢測,掃碼器是無法辦到的,一般是通過人工來進行篩選,而人工篩選造成產線效率低下、易出現疏漏的問題。 Currently, the detection of label integrity cannot be done with a barcode scanner. Manual screening is usually performed. However, manual screening causes low efficiency in the production line and is prone to omissions.
因此,如何快速、準確的檢測標籤完整度並實現自動化,成為了一個亟待解決的問題。 Therefore, how to quickly and accurately detect label integrity and implement automation has become an urgent problem to be solved.
本發明的目的是提供一種標籤完整度自適應檢測方法及系統,解決上述問題。 The purpose of the present invention is to provide a label integrity adaptive detection method and system to solve the above problems.
本發明提供一種標籤完整度自適應檢測方法,包括下列步驟:S1、對貼完標籤的料盤拍照,自動定位該標籤位置並提取標籤圖像;S2、自適應旋轉矯正該標籤圖像,以獲得處於目標水平位置的檢測標籤圖像;S3、對處於目標水平位置的該檢測標籤圖像進行影像處理,以識別多個ROI區域並進行框定;S4、依次對多個ROI區域標記ROI_n(n=1,2,3......),並讀取ROI_1的圖像資訊作為該檢測標籤圖像的唯一標識;S5、將每一個ROI區域與基準標籤圖像中對應基準ROI區域進行一一比對,以判斷該標籤完整度,並輸出標籤是否完整的檢測結果。 The invention provides an adaptive detection method for label integrity, which includes the following steps: S1. Take a photo of the labeled material tray, automatically locate the label position and extract the label image; S2. Adaptively rotate and correct the label image to Obtain the detection label image at the target horizontal position; S3. Perform image processing on the detection label image at the target horizontal position to identify and frame multiple ROI areas; S4. Mark multiple ROI areas in sequence ROI_n(n =1,2,3...), and read the image information of ROI_1 as the unique identifier of the detection tag image; S5. Compare each ROI area with the corresponding benchmark ROI area in the benchmark tag image. Compare one by one to determine the completeness of the label, and output the detection result of whether the label is complete.
在一些實施例中,在步驟S1之前,還包括如下步驟:S0、採集基準標籤圖像,並將該基準標籤圖像旋轉至目標水平位置,對該基準標籤圖像進行影像處理,以識別多個基準ROI區域並進行框定,並依次對多個基準ROI區域標記ROI_n(n=1,2,3......),獲取多個基準ROI區域的數量、灰度值和位置資訊並預存。 In some embodiments, before step S1, the following steps are also included: S0. Collect a reference label image, rotate the reference label image to a target horizontal position, and perform image processing on the reference label image to identify multiple objects. benchmark ROI areas and frame them, and mark multiple benchmark ROI areas ROI_n (n=1,2,3...) in sequence, obtain the number, grayscale value and position information of multiple benchmark ROI areas and Pre-save.
在一些實施例中,步驟S3,還包括:對所述處於目標水平位置的檢測標籤圖像進行影像處理,獲取該檢測標籤圖像中每個ROI區域的數量、灰度值和位置資訊。 In some embodiments, step S3 also includes: performing image processing on the detection label image at the target horizontal position, and obtaining the number, grayscale value and position information of each ROI area in the detection label image.
在一些實施例中,該位置資訊包括:該標籤圖像的外接矩形的中心座標、寬度值和高度值。 In some embodiments, the position information includes: the center coordinates, width value and height value of the enclosing rectangle of the label image.
在一些實施例中,步驟S2,具體包括:根據該標籤圖像的外接矩形的中心座標、旋轉角度、旋轉矩陣,將該標籤圖像自我調整旋轉至目標水平位置,公式如下:
其中,M為該旋轉矩陣,θ為該旋轉角度,(x,y)為該標籤圖像中的點座標,(tx,ty)為該標籤圖像的外接矩形的中心座標,(x',y')為點(x,y)經旋轉矩陣M旋轉後的點座標。 Among them, M is the rotation matrix, θ is the rotation angle, (x, y) is the point coordinates in the label image, (t x , t y ) is the center coordinate of the circumscribed rectangle of the label image, (x ' ,y ' ) are the point coordinates of point (x, y) after being rotated by rotation matrix M.
在一些實施例中,步驟S5,包括步驟S51:比對該基準標籤的ROI區域數量與該檢測標籤圖像ROI區域的數量,判斷數量是否一致;若判斷數量不一致時,輸出該檢測標籤不完整結果;及若判斷數量一致時,進入下一步驟S52。 In some embodiments, step S5 includes step S51: compare the number of ROI areas of the reference label with the number of ROI areas of the detection label image, and determine whether the numbers are consistent; if it is determined that the numbers are inconsistent, output that the detection label is incomplete. result; and if the determined quantities are consistent, proceed to the next step S52.
在一些實施例中,步驟S5,包括步驟S52:將多個ROI_n標識相同的該檢測標籤圖像ROI區域的中心位置座標與該基準標籤圖像ROI區域中心位置座標一一比對,判斷數值是否在偏差閾值範圍內;若判斷數值不在偏差閾值範圍內時,輸出該檢測標籤不完整結果;及若判斷數值在偏差閾值範圍內時,進入下一步驟S53。 In some embodiments, step S5 includes step S52: compare the center position coordinates of the ROI area of the detection label image with the same ROI_n identifier one by one and the center position coordinates of the ROI area of the reference label image, and determine whether the value is Within the deviation threshold range; if it is determined that the value is not within the deviation threshold range, the incomplete result of the detection tag is output; and if it is determined that the value is within the deviation threshold range, enter the next step S53.
在一些實施例中,步驟S5,包括步驟S53:將多個ROI_n標識相同的該檢測標籤圖像ROI區域與該基準標籤圖像ROI區域的寬度值、高度值和灰度值一一比對,判斷數值是否一致;若判斷任意一數值不一致時,輸出該檢測標籤不完整的結果;及 若判斷所有數值一致時,輸出該檢測標籤完整的結果。 In some embodiments, step S5 includes step S53: comparing the width value, height value and grayscale value of the detection label image ROI area with the same reference label image ROI area with multiple ROI_n identifiers one by one, Determine whether the values are consistent; if any value is determined to be inconsistent, output the incomplete result of the detection label; and If all values are judged to be consistent, the complete result of the detection label will be output.
一種標籤完整度自我調整檢測系統,包括拍照裝置和視覺處理軟體:當貼完標籤的料盤移動到該拍照裝置的視野區域時,該拍攝裝置對該料盤進行拍攝,以採集該料盤的完整圖像;及該拍照裝置將該料盤的完整圖像及時傳輸至該視覺處理軟體,該視覺處理軟體經過影像處理後,輸出標籤完整度的檢測結果。 A self-adjusting detection system for label integrity, including a camera device and visual processing software: when a labeled material tray moves to the field of view of the camera device, the camera device takes a picture of the material tray to collect information about the material tray The complete image; and the camera device transmits the complete image of the material tray to the visual processing software in a timely manner, and the visual processing software outputs the detection result of the label integrity after image processing.
在一些實施例中,該視覺處理軟體包括以下模組:一定位模組,用於對該料盤的完整圖像進行影像處理,自動定位標籤位置並提取標籤圖像;一矯正模組,用於自適應旋轉矯正該標籤圖像,以獲得處於目標水平位置的檢測標籤圖像;一識別模組,用於對處於目標水平位置的該檢測標籤圖像進行影像處理,以識別多個ROI區域,並對ROI區域進行框定,依次對該多個ROI區域標記ROI_n(n=1,2,3......),並讀取ROI_1的圖像資訊作為該檢測標籤圖像的唯一標識,獲取每一個ROI區域的中心座標、寬度值、高度值和灰度值;及一比對模組,用於將每一個ROI區域與預存於視覺處理軟體中的基準標籤圖像中的對應基準ROI區域進行一一比對,以判斷該標籤完整度,並輸出標籤是否完整的檢測結果。 In some embodiments, the visual processing software includes the following modules: a positioning module for image processing of the complete image of the material tray, automatically locating the label position and extracting the label image; a correction module for Correcting the label image with adaptive rotation to obtain a detection label image at a target horizontal position; a recognition module for performing image processing on the detection label image at a target horizontal position to identify multiple ROI areas , and frame the ROI area, mark the multiple ROI areas in sequence with ROI_n (n=1,2,3...), and read the image information of ROI_1 as the unique identifier of the detection label image , obtain the center coordinates, width value, height value and gray value of each ROI area; and a comparison module used to compare each ROI area with the corresponding benchmark in the benchmark label image pre-stored in the visual processing software The ROI areas are compared one by one to determine the completeness of the label, and the detection result of whether the label is complete is output.
與現有技術相比,本發明的一種標籤完整度自適應檢測方法及系統有益效果在於:本發明的檢測方法是自適應的(自我調整的),利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定,並以此ROI群為範本基準,用來判斷新的列印標籤品質是否合格,無需人工干預。 Compared with the existing technology, the beneficial effects of the label integrity adaptive detection method and system of the present invention are: the detection method of the present invention is adaptive (self-adjusting), and uses morphological operations and contour detection algorithms to The ROI is framed based on the printing information, and this ROI group is used as a template to determine whether the quality of the new printing label is qualified, without manual intervention.
本發明通過影像處理技術,快速且準確地定位並提取標籤圖像,然後通過圖像旋轉,將標籤圖像進行水平矯正,快速地對標籤上列印的所有資訊佈局進行完整度檢測,並輸出檢測結果,提高了產線效率,解決了人工作業易出現疏漏的問題,且檢測結果及時上傳至系統,即時可追溯。 This invention uses image processing technology to quickly and accurately locate and extract the label image, and then horizontally corrects the label image through image rotation, quickly detects the integrity of the layout of all information printed on the label, and outputs The test results improve the efficiency of the production line and solve the problem of omissions in manual operations. The test results are uploaded to the system in a timely manner and can be traced immediately.
本發明利用相機來代替掃碼器,相機用於拍攝列印出來的標籤,節省硬體費用。 The present invention uses a camera instead of a code scanner, and the camera is used to take pictures of printed labels, thereby saving hardware costs.
S1-S5:步驟 S1-S5: Steps
11:料盤 11: Material tray
13:貼標區 13: Labeling area
101:定位模組 101: Positioning module
102:矯正模組 102: Correction module
103:識別模組 103:Identification module
104:比對模組 104:Comparison module
下面將以明確易懂的方式,結合圖式說明較佳實施方式,對標籤完整度自適應檢測方法及方法的上述特性、技術特徵、優點及其實現方式予以進一步說明。 The following will describe the preferred implementation mode in a clear and easy-to-understand manner with reference to drawings, and further explain the above-mentioned characteristics, technical features, advantages and implementation methods of the tag integrity adaptive detection method and method.
圖1是本發明中標籤完整度自適應檢測方法一個實施例的示意圖;圖2是本發明中標籤完整度自適應檢測方法的應用示意圖;圖3是本發明中標籤完整度自適應檢測方法一個實施例的示意圖;圖4是本發明中貼完標籤的料盤圖像;圖5是本發明中基準標籤的示意圖;圖6是本發明中ROI區域數量缺失的示意圖;圖7是本發明中ROI區域數量缺失且字元缺失的示意圖;圖8是本發明中ROI區域字元缺失的示意圖;及圖9是本發明中標籤完整度自適應檢測系統的一個實施例的示意圖。 Figure 1 is a schematic diagram of an embodiment of the label integrity adaptive detection method in the present invention; Figure 2 is an application schematic diagram of the label integrity adaptive detection method in the present invention; Figure 3 is a label integrity adaptive detection method in the present invention Schematic diagram of the embodiment; Figure 4 is a schematic diagram of the labeled material tray in the present invention; Figure 5 is a schematic diagram of the reference label in the present invention; Figure 6 is a schematic diagram of the missing number of ROI areas in the present invention; Figure 7 is a schematic diagram of the missing ROI area in the present invention; FIG. 8 is a schematic diagram of the missing characters in the ROI area in the present invention; and FIG. 9 is a schematic diagram of an embodiment of the tag integrity adaptive detection system in the present invention.
為了更清楚地說明本發明實施例或現有技術中的技術方案,下面將對照附圖說明本發明的具體實施方式。顯而易見地,下面描述中的附圖僅僅是本發明的一些實施例,對於本領域普通技術人員來講,在不付出進步性勞動的前提下,還可以根據這些圖式獲得其他的圖式,並獲得其他的實施方式。 In order to explain the embodiments of the present invention or technical solutions in the prior art more clearly, the specific implementation modes of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without making any progressive efforts, and Get other implementations.
為使圖面簡潔,各圖中只示意性地表示出了與本發明相關的部分,它們並不代表其作為產品的實際結構。另外,以使圖面簡潔便於理解,在有些圖中具有相同結構或功能的部件,僅示意性地繪示了其中的一個,或僅標出了其中的一個。在本文中,“一個”不僅表示“僅此一個”,也可以表示“多於一個”的情形。 In order to keep the drawings concise, only the parts related to the present invention are schematically shown in each figure, and they do not represent the actual structure of the product. In addition, in order to make the drawings concise and easy to understand, in some drawings, only one of the components with the same structure or function is schematically illustrated or labeled. In this article, "a" not only means "only one", but can also mean "more than one".
在一個實施例中,本發明提供一種標籤完整度自適應檢測方法,如圖1至圖3所示,包括: In one embodiment, the present invention provides a label integrity adaptive detection method, as shown in Figures 1 to 3, including:
S1、對貼完標籤的料盤拍照,自動定位標籤位置並提取標籤圖像。 S1. Take a photo of the labeled material tray, automatically locate the label position and extract the label image.
如圖4所示,通過拍照裝置獲取貼完標籤的料盤圖像,以讓標籤完整度自適應檢測系統的視覺處理軟體自動定位標籤位置並提取標籤圖像。隨後步驟S2-S5都透過視覺處理軟體進行圖像處理。 As shown in Figure 4, the image of the labeled tray is obtained through the camera device, so that the visual processing software of the label integrity adaptive detection system can automatically locate the label position and extract the label image. Subsequent steps S2-S5 all perform image processing through visual processing software.
S2、自適應旋轉矯正該標籤圖像,以獲得處於目標水平位置的檢測標籤圖像。 S2. Adaptively rotate and correct the label image to obtain the detection label image at the target horizontal position.
如圖4所示的標籤圖像,與水平方向存在一定的旋轉角度,需要將標籤圖像進行旋轉矯正至水平。 The label image shown in Figure 4 has a certain rotation angle with the horizontal direction, and the label image needs to be rotated and corrected to be horizontal.
針對目前列印標籤印刷資訊的格式和佈局,本發明是通過影像處理技術,定位並提取標籤圖像,然後通過圖像旋轉,將標籤圖像進行水平矯正,最後對標籤上列印的所有資訊佈局進行完整度檢測。 In view of the current format and layout of label printing information, the present invention uses image processing technology to locate and extract the label image, then horizontally corrects the label image through image rotation, and finally corrects all the information printed on the label. Check the layout for completeness.
S3、對處於目標水平位置的檢測標籤圖像進行影像處理,以識別多個ROI區域並進行框定。ROI區域是感興趣區域(region of interest,ROI)。 S3. Perform image processing on the detection label image at the target horizontal position to identify and frame multiple ROI areas. The ROI region is the region of interest (ROI).
具體的,在檢測過程中,利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定,識別多個當前ROI區域。 Specifically, during the detection process, morphological operations and contour detection algorithms are used to frame the ROI of the printed information on the label and identify multiple current ROI areas.
S4、依次對多個ROI區域標記ROI_n(n=1,2,3......),並讀取ROI_1的圖像資訊作為檢測標籤圖像的唯一標識。 S4. Label multiple ROI areas ROI_n (n=1,2,3...) in sequence, and read the image information of ROI_1 as the unique identifier for detecting the label image.
具體地,自上而下、從左到右的順序對所有框定的ROI區域標記進行標記,標記符號為ROI_1、ROI_2、ROI_3......ROI_n。 Specifically, all framed ROI area markers are marked from top to bottom and from left to right, and the marking symbols are ROI_1, ROI_2, ROI_3...ROI_n.
S5、將每個ROI區域與基準標籤圖像中基準ROI區域進行一一比對,以判斷所述標籤完整度,並輸出標籤是否完整的檢測結果。 S5. Compare each ROI area one by one with the reference ROI area in the reference label image to determine the completeness of the label, and output a detection result of whether the label is complete.
具體的,將多個ROI區域組成的佈局,即ROI區域的數量、每個ROI區域的位置、長度、寬度和基準標籤圖像的基準ROI區域進行對比,當任意一個數值不一致時,該列印標籤就為不完整的標籤。 Specifically, the layout composed of multiple ROI areas, that is, the number of ROI areas, the position, length, and width of each ROI area is compared with the reference ROI area of the reference label image. When any value is inconsistent, the print The label is an incomplete label.
在本實施例中,本發明的檢測方法是自適應的,利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定,並以此ROI群為範本基準,用來判斷新的列印標籤品質是否合格,無需人工干預。 In this embodiment, the detection method of the present invention is adaptive. It uses morphological operations and contour detection algorithms to frame the ROI of the printed information on the label, and uses this ROI group as a template to determine new Check whether the printed label quality is up to standard without manual intervention.
在一個實施例中,在步驟S1之前,還包括如下步驟: In one embodiment, before step S1, the following steps are also included:
S0、採集基準標籤圖像,並將基準標籤圖像旋轉至目標水平位置,對基準標籤圖像進行影像處理,以識別多個ROI區域並進行框定,並依次對多個ROI區域標記ROI_n(n=1,2,3......),獲取所有ROI區域的數量、灰度值和位置資訊並預存。 S0. Collect the benchmark label image, rotate the benchmark label image to the target horizontal position, perform image processing on the benchmark label image to identify and frame multiple ROI areas, and mark multiple ROI areas in sequence ROI_n(n =1,2,3...), obtain the quantity, gray value and position information of all ROI areas and pre-store them.
實施例中,將完整度為100%的列印標籤的圖像進行影像處理,識別出ROI區域和對應的資訊,並對所有識別的ROI區域進行標記,標記為ROI_n (n=1,2,3......),以及獲取所有標記的ROI區域的灰度值和位置資訊,並預存。以此作為基準標籤的ROI區域基準參數。 In the embodiment, the image of the printed label with a completeness of 100% is image processed, the ROI area and the corresponding information are identified, and all the identified ROI areas are marked as ROI_n. (n=1,2,3...), and obtain the grayscale value and position information of all marked ROI areas and pre-save them. Use this as the ROI area benchmark parameter for the benchmark label.
在後續判斷過程中,可以將新的標籤與基準標籤進行比較,當新的標籤與基準標籤參數相同時,輸出貼標料盤的標籤完整結果。當新的標籤與基準標籤基準參數不相同時,輸出貼標料盤的標籤不完整結果。 In the subsequent judgment process, the new label can be compared with the reference label. When the parameters of the new label and the reference label are the same, the complete label result of the labeling material tray will be output. When the new label is different from the reference label reference parameters, the incomplete label result of the labeling tray is output.
在一個實施例中,S3、對處於目標水平位置的檢測標籤圖像進行影像處理,以識別所有ROI區域並進行框定,包括:對處於目標水平位置的檢測標籤圖像進行影像處理,獲取檢測標籤圖像中每個ROI區域的數量、灰度值和位置資訊。 In one embodiment, S3. Perform image processing on the detection label image at the target horizontal position to identify and frame all ROI areas, including: performing image processing on the detection label image at the target horizontal position to obtain the detection label. The number, gray value and location information of each ROI area in the image.
在一個實施例中,位置資訊包括:標籤圖像的外接矩形的中心座標、寬度(Width)值和高度(Height)值。 In one embodiment, the position information includes: center coordinates, width (Width) value, and height (Height) value of the enclosing rectangle of the label image.
具體的,在識別框定ROI區域時,會獲取每個ROI區域的中心位置座標、長度、寬度和面積。 Specifically, when identifying the framed ROI area, the center position coordinates, length, width and area of each ROI area will be obtained.
同時,會統計ROI區域的數量,並且會同步採集每個ROI區域的灰度值。具體包括以下:
在一個實施例中,S2、自適應旋轉矯正標籤圖像,以獲得處於目標水平位置的檢測標籤圖像,包括:
根據標籤圖像的外接矩形的中心座標、旋轉角度、旋轉矩陣,將標籤圖像自適應旋轉至目標水平位置,公式如下:
其中,M為旋轉矩陣,θ為旋轉角度,(x,y)為標籤圖像中的點座標,(tx,ty)為標籤圖像的外接矩形的中心座標,(x',y')為點(x,y)經旋轉矩陣M旋轉後的點座標。 Among them, M is the rotation matrix, θ is the rotation angle, (x, y) is the point coordinates in the label image, (t x , t y ) is the center coordinate of the circumscribing rectangle of the label image, (x ' , y ' ) is the point coordinate of point (x, y) rotated by rotation matrix M.
具體地,如圖4所示,在提取列印標籤時,由於標籤不在水平位置,即標籤的底部與料盤11的貼標區13的底部不平行。在採集貼完標籤的料盤圖像時,拍照裝置是位於料盤11的正上方,提取列印標籤時會存在一定的旋轉角度,在自動框定識別區域時將標籤圖像旋轉至水平位置,這樣才能自適應框定識別區域,否則在框定識別區域時會存在框定殘缺的問題。 Specifically, as shown in FIG. 4 , when the printed label is extracted, since the label is not in a horizontal position, that is, the bottom of the label is not parallel to the bottom of the labeling area 13 of the material tray 11 . When collecting the image of the labeled tray, the camera is located directly above the tray 11. There will be a certain rotation angle when extracting the printed label. When automatically framing the recognition area, the label image is rotated to a horizontal position. In this way, the recognition area can be adaptively framed. Otherwise, there will be a problem of incomplete framing when framing the recognition area.
在一個實施例中,步驟S1、對貼完標籤的料盤拍照,自動定位標籤位置並提取標籤圖像還包括:當貼完標籤的料盤移動到拍照裝置的對準區域時,控制拍照裝置對貼完標籤的料盤進行拍攝,以採集貼完標籤的料盤圖像。 In one embodiment, step S1, taking a picture of the labeled material tray, automatically locating the label position and extracting the label image also includes: when the labeled material tray moves to the alignment area of the camera device, controlling the camera device Take a picture of the labeled material tray to collect the image of the labeled material tray.
具體的,將貼完列印標籤的料盤移動到拍照裝置(相機)正下方區域,通過軟體通信方式給出觸發信號至相機,控制相機進行拍照,得到貼完標籤的料盤圖像。 Specifically, the material tray with printed labels is moved to the area directly below the camera device (camera), a trigger signal is given to the camera through software communication, and the camera is controlled to take pictures to obtain an image of the labeled material tray.
在具體應用過程中,需要通過識別標籤的唯一標識來與其他檢測標籤進行區別,同時根據唯一標識確定該標籤的基準標籤,並調取基準標籤作為驗證該標籤完整度的對比準則。 In the specific application process, it is necessary to distinguish the tag from other detection tags by identifying the unique ID. At the same time, the benchmark tag of the tag is determined based on the unique ID, and the benchmark tag is retrieved as a comparison criterion to verify the integrity of the tag.
本實施例中,以標記ROI_1區域的條碼內容需要進行讀取,並將條碼內容作為該檢測標籤的唯一標識。 In this embodiment, the barcode content marking the ROI_1 area needs to be read, and the barcode content is used as the unique identifier of the detection tag.
在一個實施例中,S5、將每個所述ROI區域與基準標籤圖像中對應ROI區域進行一一比對,以判斷標籤完整度,並輸出標籤是否完整的檢測結果,包括步驟S51:比對基準標籤的ROI區域數量與檢測標籤圖像ROI區域的數量,判斷數量是否一致;若判斷數量不一致時,輸出檢測標籤不完整結果;及若判斷數量一致時,進入下一步驟S52。 In one embodiment, S5, compare each ROI area with the corresponding ROI area in the reference label image one by one to determine the completeness of the label, and output the detection result of whether the label is complete, including step S51: comparison For the number of ROI areas of the reference label and the number of ROI areas of the detection label image, determine whether the numbers are consistent; if the determined numbers are inconsistent, output the incomplete result of the detected label; and if the determined numbers are consistent, proceed to the next step S52.
具體的,例如圖5是基準標籤,有6個基準ROI區域,如圖6、7所示的檢測標籤,只能檢測出4個ROI區域,與圖5比較,ROI_5和ROI_6均缺失。因此,圖6和圖7與基準標籤的ROI區域數量比較,檢測標籤存在ROI區域數量缺少,輸出標籤不完整結果。 Specifically, for example, Figure 5 is a benchmark label with 6 baseline ROI areas. The detection labels shown in Figures 6 and 7 can only detect 4 ROI areas. Compared with Figure 5, both ROI_5 and ROI_6 are missing. Therefore, compared with the number of ROI areas of the benchmark label in Figures 6 and 7, the detection label has a missing number of ROI areas, and the output label result is incomplete.
在一個實施例中,步驟S5將每個ROI區域與基準標籤圖像中基準ROI區域進行一一比對,以判斷標籤完整度,並輸出標籤是否完整的檢測結果,包括步驟S52: 將所有ROI_n標識相同的檢測標籤圖像的ROI區域的中心位置座標與基準標籤圖像的ROI區域中心位置座標一一比對,判斷數值是否在偏差閾值範圍內;若判斷數值不在偏差閾值範圍內時,輸出檢測標籤不完整結果;及若判斷數值在偏差閾值範圍內時,進入下一步驟S53。 In one embodiment, step S5 compares each ROI area one by one with the reference ROI area in the reference label image to determine the completeness of the label, and outputs the detection result of whether the label is complete, including step S52: Compare the center position coordinates of the ROI area of all detection label images with the same ROI_n identifier with the center position coordinates of the ROI area of the reference label image one by one to determine whether the value is within the deviation threshold range; if it is determined that the value is not within the deviation threshold range When, the incomplete result of detecting the label is output; and if the value is judged to be within the deviation threshold range, the next step S53 is entered.
具體地,獲取的檢測標籤的所有ROI區域ROI_1、ROI_2......ROI_n的中心座標分別為(x1,y1)、(x2,y2)......(xn,yn),與基準標籤圖像對應ROI區域中心位置座標(X1,Y1)、(X2,Y2)......(Xn,Yn)一一比對,判斷數值是否在偏差閾值範圍內。本實施例中設計偏差閾值為k1、k2,若滿足如以下條件,則進入下一步驟S53:an=|xn-Xn|k1,bn=|yn-Yn|k2。 Specifically, the center coordinates of all ROI areas ROI_1, ROI_2...ROI_n of the acquired detection tags are (x1, y1), (x2, y2)... (xn, yn) respectively, and The benchmark label image corresponds to the ROI area center position coordinates (X1, Y1), (X2, Y2)...(Xn, Yn) and is compared one by one to determine whether the value is within the deviation threshold range. In this embodiment, the design deviation thresholds are k1 and k2. If the following conditions are met, proceed to the next step S53: an=|xn-Xn| k1,bn=|yn-Yn| k2.
特別地,檢測標籤的所有被標記的ROI_n區域可存在同時沿X方向或沿Y方向偏移的情況,在一定的偏差閾值範圍內是被允許的,例如偏差閾值範圍為k1、k2。反之,如檢測到所有被標記的ROI_n區域的偏差不在設定的閾值範圍內,或者並未同時沿X方向或沿Y方向發生相同的偏移量,即a1、a2......an不相等或者b1、b2......bn不相等,則輸出檢測標籤不完整結果。 In particular, all marked ROI_n areas of the detection tag may be shifted along the X direction or along the Y direction at the same time, which is allowed within a certain deviation threshold range, for example, the deviation threshold range is k1, k2. On the contrary, if it is detected that the deviations of all marked ROI_n areas are not within the set threshold range, or the same offset does not occur along the X direction or along the Y direction at the same time, that is, a1, a2...an do not If they are equal or b1, b2...bn are not equal, the incomplete result of the detection label will be output.
具體地,本發明中檢測標籤所有ROI_n區域中心位置座標的xn(n=1,2......n)與基準標籤的ROI_n區域中心位置座標的Xn(n=1,2......n)的實際偏差應相同,這裡以a表示,即a=|xn-Xn|,判斷a是否小於或等於偏差閾值k1。同時,本案中檢測標籤所有ROI_n區域中心位置座標的yn(n=1,2......n)與基準標籤的ROI_n區域中心位置座標的Yn(n=1,2......n)的實際偏差應相同,這裡以b表示,即b=|yn-Yn|,判斷b是否小於或等於偏差閾值k2。若同時滿足ak1和bk2,則進入下一步驟S53;如a>k1或b>k2,則輸出檢測標籤不完整結果。 Specifically, in the present invention, xn (n=1,2...n) of the center position coordinates of all ROI_n regions of the detection tag and Xn (n=1,2...n) of the center position coordinates of the ROI_n region of the reference tag ...n) should be the same, here represented by a, that is, a=|xn-Xn|, determine whether a is less than or equal to the deviation threshold k1. At the same time, in this case, yn(n=1,2...n) of the center position coordinates of all ROI_n areas of the detection tag and Yn(n=1,2...n) of the center position coordinates of the ROI_n area of the reference tag The actual deviation of .n) should be the same, represented by b here, that is, b=|yn-Yn|, determine whether b is less than or equal to the deviation threshold k2. If a is satisfied at the same time k1 and b k2, then enter the next step S53; if a>k1 or b>k2, then output the incomplete result of detecting the label.
例如,圖8所示的檢測標籤,在列印時存在位移,導致ROI_1區域不完整,在檢測時,獲取ROI_n區域的中心位置座標(xn,yn)與圖5的基準標籤的對應ROI_n區域的中心位置座標(Xn,Yn)比較,計算出偏差值an=|xn-Xn|,bn=|yn-Yn|,然後比較an、bn是否小於或等於預先設定的偏差閾值。本實施例中,an或者bn應是大於預先設定的偏差閾值了,輸出檢測標籤不完整結果。 For example, the detection label shown in Figure 8 is displaced during printing, resulting in the incomplete ROI_1 area. During detection, the center position coordinates (xn, yn) of the ROI_n area and the corresponding ROI_n area of the reference label in Figure 5 are obtained. Compare the center position coordinates (Xn, Yn), calculate the deviation values an=|xn-Xn|, bn=|yn-Yn|, and then compare whether an and bn are less than or equal to the preset deviation threshold. In this embodiment, if an or bn should be greater than the preset deviation threshold, the incomplete detection label result will be output.
在一個實施例中,步驟S5將每個ROI區域與基準標籤圖像中對應ROI區域進行一一比對,以判斷所述標籤完整度,並輸出標籤是否完整的檢測結果,包括步驟S53:將所有ROI_n標識相同的檢測標籤圖像ROI區域與基準標籤圖像ROI區域的寬度值、高度值和灰度值一一比對,判斷數值是否一致;若判斷任意一數值不一致時,輸出檢測標籤不完整的結果;及若判斷所有數值一致時,輸出檢測標籤完整的結果。 In one embodiment, step S5 compares each ROI area one by one with the corresponding ROI area in the reference label image to determine the completeness of the label, and outputs a detection result of whether the label is complete, including step S53: Compare the width, height and grayscale values of all detection label image ROI areas with the same ROI_n identifier with the reference label image ROI area one by one to determine whether the values are consistent; if any value is determined to be inconsistent, the output detection label is incorrect. Complete results; and if all values are judged to be consistent, output the complete results of the detection label.
在具體場景中,如圖7所示,出現ROI區域缺失的情況,在步驟S51時,就可檢測到ROI區域數量缺少,輸出標籤不完整的結果。如圖8所示,在步驟S52時,如偏差閥值設置不當,造成在此步驟時未被檢測出標籤不完整,則會進入步驟S53。 In a specific scenario, as shown in Figure 7, the ROI area is missing. In step S51, it is detected that the number of ROI areas is missing, and the result of incomplete labels is output. As shown in Figure 8, in step S52, if the deviation threshold is set improperly, resulting in incomplete tags not being detected at this step, step S53 will be entered.
具體地,將獲取的此檢測標籤所有ROI_n區域的寬度值w_n、高度值h_n和灰度值g_n,並分別與基準標籤對應標記的ROI_n區域的寬度值w_n、高度值h_n和灰度值g_n進行一一比較,若有任意數值不一致,則表示該檢測標籤的ROI_n區域的字符缺失,輸出檢測標籤不完整結果。 Specifically, the obtained width value w_n, height value h_n and gray value g_n of all ROI_n areas of this detection tag are compared with the width value w_n, height value h_n and gray value g_n of the ROI_n area corresponding to the reference label. Compare one by one, if any values are inconsistent, it means that the characters in the ROI_n area of the detection label are missing, and the incomplete result of the detection label is output.
如圖8所示的檢測標籤,很明顯ROI_1區域的高度值h_1與圖5所示的基準標籤的ROI_1區域的高度值H_1相比,h_1≠H_1,因此輸出檢測標籤不完整結果。 For the detection label shown in Figure 8, it is obvious that the height value h_1 of the ROI_1 area is compared with the height value H_1 of the ROI_1 area of the reference label shown in Figure 5, h_1≠H_1, so the output detection label is incomplete.
在一個實施例中,本發明還提供一種標籤完整度自適應檢測系統,如圖9所示,包括拍照裝置和視覺處理軟體:當貼完標籤的料盤移動到拍照裝置的視野區域時,拍照裝置對料盤進行拍攝,以採集料盤的完整圖像。 In one embodiment, the present invention also provides a label integrity adaptive detection system, as shown in Figure 9, including a camera device and visual processing software: when the labeled material tray moves to the field of view of the camera device, the system takes a picture The device takes a picture of the material tray to collect a complete image of the material tray.
拍照裝置將料盤的完整圖像及時傳輸至視覺處理軟體,視覺處理軟體經過影像處理後,輸出標籤完整度的檢測結果。 The camera device transmits the complete image of the material tray to the visual processing software in a timely manner. After image processing, the visual processing software outputs the detection results of the label integrity.
在一個實施例中,視覺處理軟體包括以下模組: In one embodiment, the visual processing software includes the following modules:
定位模組101,用於對貼完標籤的料盤拍照,自動定位標籤位置並提取標籤圖像。
The
示例性的,在獲取貼完標籤的料盤圖像後,如圖4所示的貼完標籤的料盤圖像,自動定位標籤位置並提取標籤圖像。 For example, after acquiring the image of the labeled material tray, as shown in Figure 4, the label position is automatically located and the label image is extracted.
矯正模組102,用於自我調整旋轉矯正所述標籤圖像,以獲得處於目標水平位置的檢測標籤圖像。
The
示例性的,如圖4所示的標籤圖像,與拍攝裝置的正拍攝區域的水平方向存在一定的旋轉角度,需要將存在一定旋轉角度的標籤圖像進行旋轉矯正至水平。 For example, the label image shown in Figure 4 has a certain rotation angle with the horizontal direction of the shooting area of the shooting device. The label image with a certain rotation angle needs to be rotated and corrected to be horizontal.
針對目前列印標籤印刷資訊的格式和佈局,本發明是通過影像處理技術,定位並提取標籤圖像,然後通過圖像旋轉,將標籤圖像進行水平矯正,最後對標籤上列印的所有資訊佈局進行完整度檢測。 In view of the current format and layout of label printing information, the present invention uses image processing technology to locate and extract the label image, then horizontally corrects the label image through image rotation, and finally corrects all the information printed on the label. Check the layout for completeness.
識別模組103,用於識別模組,用於對處於目標水平位置的檢測標籤圖像進行影像處理,以識別多個ROI區域,並對ROI區域進行框定,依次對所述ROI區域標記ROI_n(n=1,2,3......),並讀取ROI_1的圖像資訊作為檢測標籤圖像的唯一標識,獲取每個ROI區域的中心座標、寬度值、高度值和灰度值。
The
同時,檢測方法是自適應或稱自我調整的,利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定。 At the same time, the detection method is adaptive or self-adjusting, using morphological operations and contour detection algorithms to frame the ROI of the printed information on the label.
比對模組104,用於將每個ROI區域與基準標籤圖像中基準ROI區域進行一一比對,以判斷標籤完整度,並輸出標籤是否完整的檢測結果。
The
具體的,將多個ROI區域組成的佈局,即每個ROI區域的位置和面積、長度、數量和基準標籤圖像的基準ROI區域進行對比,當任意一個數量不一致時,該列印標籤就為不完整的標籤。 Specifically, the layout composed of multiple ROI areas, that is, the position, area, length, and quantity of each ROI area is compared with the reference ROI area of the reference label image. When any number is inconsistent, the print label is Incomplete label.
在本實施例中,本發明的檢測方法是自適應的,利用形態學操作和輪廓檢測演算法,對標籤上列印資訊進行ROI框定,並以此ROI群為範本基準,用來判斷新的列印標籤品質是否合格,無需人工干涉。 In this embodiment, the detection method of the present invention is adaptive. It uses morphological operations and contour detection algorithms to frame the ROI of the printed information on the label, and uses this ROI group as a template to determine new Check whether the printed label quality is up to standard without manual intervention.
在一個實施例中,識別模組,還用於:對處於目標水平位置的標籤圖像進行影像處理,獲取標籤圖像的條碼位置和條碼位置對應的條碼內容,標籤圖像的字符位置和字符位置對應的字符內容。 In one embodiment, the recognition module is also used to: perform image processing on the label image at the target horizontal position, obtain the barcode position of the label image and the barcode content corresponding to the barcode position, and the character position and character of the label image. The character content corresponding to the position.
基於條碼位置和條碼位置對應的條碼內容,字符位置和字符位置對應的字符內容,得到多個當前ROI區域。 Based on the barcode position and the barcode content corresponding to the barcode position, the character position and the character content corresponding to the character position, multiple current ROI areas are obtained.
示例性的,識別模組,具體用於:對處於目標水平位置的標籤圖像進行影像處理,獲取標籤圖像中每個當前ROI區域的數量、灰度值和位置資訊。 Exemplary, the recognition module is specifically used to: perform image processing on the label image at the target horizontal position, and obtain the number, gray value and position information of each current ROI area in the label image.
具體地,在識別框定ROI區域時,會獲取每個ROI區域的中心位置座標、長度、寬度和面積以確定ROI區域的位置資訊。 Specifically, when identifying and framing the ROI area, the center position coordinates, length, width and area of each ROI area are obtained to determine the location information of the ROI area.
同時,會統計ROI區域的數量,並且會同步採集每個ROI區域的灰度值。具體包括以下:
在一個實施例中,如圖2及3所示,還包括拍照裝置,用於:當貼完標籤的料盤移動到拍照裝置的拍攝區域時,控制拍照裝置對貼完標籤的料盤進行拍攝,以採集貼完標籤的料盤圖像。 In one embodiment, as shown in Figures 2 and 3, a photographing device is also included, which is used to: when the labeled material tray moves to the shooting area of the photographing device, control the photographing device to photograph the labeled material tray. , to collect images of labeled trays.
具體地,將貼完列印標籤的料盤移動到相機正下方的拍攝區域,通過軟體通信方式給出觸發信號至相機,控制相機進行抓拍,得到貼完標籤的料盤圖像。 Specifically, the tray with printed labels is moved to the shooting area directly below the camera, a trigger signal is given to the camera through software communication, and the camera is controlled to capture a picture to obtain an image of the tray with labels.
在一個實施例中,矯正模組,用於:根據標籤圖像的外接矩形的座標、旋轉角度、旋轉矩陣,將標籤圖像自適應旋轉至目標水平位置,公式如下:
其中,M為旋轉矩陣,θ為旋轉角度,(x,y)為標籤圖像中的點座標,(tx,ty)為標籤圖像的外接矩形的中心座標,(x',y')為旋轉後的標籤圖像的中點座標。 Among them, M is the rotation matrix, θ is the rotation angle, (x, y) is the point coordinates in the label image, (t x , t y ) is the center coordinate of the circumscribing rectangle of the label image, (x ' , y ' ) is the midpoint coordinate of the rotated label image.
具體的,如圖4所示,在提取列印標籤時,由於標籤貼的位置不在同一水平位置,即標籤的底部與料盤11的貼標區13的底部不平行。在採集貼完標籤的料盤圖像時,拍照裝置是位於料盤的正上方,提取列印標籤時會存在一定的旋轉角度,在自動框定識別區域前將標籤圖像旋轉至0度即水平位置,這樣才能自適應框定識別區域,否則在框定識別區域時會存在框定殘缺的問題。 Specifically, as shown in FIG. 4 , when the printed label is extracted, since the position of the label is not at the same horizontal position, that is, the bottom of the label is not parallel to the bottom of the labeling area 13 of the material tray 11 . When collecting the image of the labeled material tray, the camera device is located directly above the material tray. There will be a certain rotation angle when extracting the printed label. Before automatically framing the recognition area, the label image is rotated to 0 degrees, which is horizontal. position, so that the recognition area can be adaptively framed. Otherwise, there will be a problem of incomplete framing when framing the recognition area.
在具體應用過程中,需要通過識別標籤的唯一標識確定該標籤的基準標籤,並調取基準標籤作為驗證該標籤完整度的對比準則。本案中,ROI_1區域的條碼內容需要進行檢測,並將條碼內容作為標籤的唯一標識。在一個實施例中,比對模組,用於:對比檢測標籤的所有ROI區域與基準標籤的對應ROI區域的數據,數據包括ROI區域數量、灰度值、位置資訊,判斷是否一致。 In the specific application process, it is necessary to determine the benchmark tag of the tag through the unique identifier of the tag, and retrieve the benchmark tag as a comparison criterion to verify the integrity of the tag. In this case, the barcode content in the ROI_1 area needs to be detected and used as the unique identifier of the label. In one embodiment, the comparison module is used to compare all ROI areas of the detection tag with the data of the corresponding ROI area of the reference tag. The data includes the number of ROI areas, grayscale values, and location information, and determine whether they are consistent.
當任一數據不一致時,輸出標籤不完整結果。 When any data is inconsistent, incomplete label results are output.
當數據一致時,輸出標籤完整結果。 When the data is consistent, complete label results are output.
具體地,每一個ROI區域的位置資訊包括ROI區域外接矩形的中心位置座標、ROI區域外接矩形的寬度值、高度值和面積。 Specifically, the position information of each ROI region includes the center position coordinates of the circumscribed rectangle of the ROI region, the width value, the height value and the area of the circumscribed rectangle of the ROI region.
具體的,如圖6、7所示,當ROI區域數量缺少時,輸出標籤不完整結果。如圖7、8所示,當檢測到ROI區域的字符缺失時,輸出標籤不完整結果。在具體場景中,如圖7所示,可能出現字符缺失且ROI缺失的情況,可以輸出標籤不完整的結論。 Specifically, as shown in Figures 6 and 7, when the number of ROI areas is missing, incomplete label results are output. As shown in Figures 7 and 8, when missing characters in the ROI area are detected, incomplete label results are output. In specific scenarios, as shown in Figure 7, characters may be missing and ROIs may be missing, and a conclusion that the labels are incomplete may be output.
應當說明的是,上述實施例均可根據需要自由組合。以上僅是本發明的較佳實施方式,應當指出,對於本技術領域的具有通常知識者來說,在不脫離本發明原理的前提下,還可以做出若干改進和潤飾,這些改進和潤飾也應視為本發明的保護範圍。 It should be noted that the above embodiments can be freely combined as needed. The above are only the preferred embodiments of the present invention. It should be pointed out that those with ordinary knowledge in this technical field can also make several improvements and modifications without departing from the principles of the present invention. These improvements and modifications can also be made. should be regarded as the protection scope of the present invention.
S1-S5:步驟 S1-S5: Steps
Claims (9)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210093558.3 | 2022-01-26 | ||
CN202210093558.3A CN114549423A (en) | 2022-01-26 | 2022-01-26 | Label integrity self-adaptive detection method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
TW202331655A TW202331655A (en) | 2023-08-01 |
TWI823463B true TWI823463B (en) | 2023-11-21 |
Family
ID=81673898
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
TW111125555A TWI823463B (en) | 2022-01-26 | 2022-07-07 | Label integrity adaptive detection method and system |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN114549423A (en) |
TW (1) | TWI823463B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117227336B (en) * | 2023-08-16 | 2024-04-16 | 门杜美昊(廊坊)医药科技有限公司 | Ultrasonic diagnosis report printing device |
CN118068026A (en) * | 2024-03-15 | 2024-05-24 | 江苏远升生物科技有限公司 | Biological sample processing device and biological detection system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW507169B (en) * | 2001-04-27 | 2002-10-21 | Hon Hai Prec Ind Co Ltd | Automatic bar code detection system |
TW200943192A (en) * | 2008-02-22 | 2009-10-16 | Qualcomm Inc | Image capture device with integrated barcode scanning |
TW201019229A (en) * | 2008-10-02 | 2010-05-16 | Silverbrook Res Pty Ltd | Method of imaging position-coding pattern having tag coordinates encoded by successive subsequences of cyclic position code |
CN102708351A (en) * | 2012-05-24 | 2012-10-03 | 江南大学 | Method for fast identifying Data Matrix two-dimensional bar code under complicated working condition background |
CN103034831B (en) * | 2011-09-30 | 2015-05-27 | 无锡爱丁阁信息科技有限公司 | Method and system for identifying linear bar code |
TWI571803B (en) * | 2015-12-28 | 2017-02-21 | 元智大學 | Generation? method? of? color? qr? code |
CN111539236A (en) * | 2020-04-13 | 2020-08-14 | 苏州摩比信通智能系统有限公司 | Method for reading multiple bar codes at one time |
CN112149440A (en) * | 2020-08-27 | 2020-12-29 | 深圳长城开发精密技术有限公司 | Quick positioning and identifying method for multi-dimensional multi-bar code |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR100498763B1 (en) * | 2002-12-24 | 2005-07-01 | 한국전자통신연구원 | The bar code reader and high-speed extraction system of bar code locating, the control method of this system |
CN106971390A (en) * | 2017-02-23 | 2017-07-21 | 国网上海市电力公司 | A kind of detection method for labelling quality |
CN109018591A (en) * | 2018-08-09 | 2018-12-18 | 沈阳建筑大学 | A kind of automatic labeling localization method based on computer vision |
CN109934809A (en) * | 2019-03-08 | 2019-06-25 | 深慧视(深圳)科技有限公司 | A kind of paper labels character defect inspection method |
CN112488099B (en) * | 2020-11-25 | 2022-12-16 | 上海电力大学 | Digital detection extraction element on electric power liquid crystal instrument based on video |
-
2022
- 2022-01-26 CN CN202210093558.3A patent/CN114549423A/en active Pending
- 2022-07-07 TW TW111125555A patent/TWI823463B/en active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TW507169B (en) * | 2001-04-27 | 2002-10-21 | Hon Hai Prec Ind Co Ltd | Automatic bar code detection system |
TW200943192A (en) * | 2008-02-22 | 2009-10-16 | Qualcomm Inc | Image capture device with integrated barcode scanning |
TW201019229A (en) * | 2008-10-02 | 2010-05-16 | Silverbrook Res Pty Ltd | Method of imaging position-coding pattern having tag coordinates encoded by successive subsequences of cyclic position code |
CN103034831B (en) * | 2011-09-30 | 2015-05-27 | 无锡爱丁阁信息科技有限公司 | Method and system for identifying linear bar code |
CN102708351A (en) * | 2012-05-24 | 2012-10-03 | 江南大学 | Method for fast identifying Data Matrix two-dimensional bar code under complicated working condition background |
TWI571803B (en) * | 2015-12-28 | 2017-02-21 | 元智大學 | Generation? method? of? color? qr? code |
CN111539236A (en) * | 2020-04-13 | 2020-08-14 | 苏州摩比信通智能系统有限公司 | Method for reading multiple bar codes at one time |
CN112149440A (en) * | 2020-08-27 | 2020-12-29 | 深圳长城开发精密技术有限公司 | Quick positioning and identifying method for multi-dimensional multi-bar code |
Also Published As
Publication number | Publication date |
---|---|
CN114549423A (en) | 2022-05-27 |
TW202331655A (en) | 2023-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI823463B (en) | Label integrity adaptive detection method and system | |
CN112949564B (en) | Pointer type instrument automatic reading method based on deep learning | |
CN109785316B (en) | Method for detecting apparent defects of chip | |
CN111474184B (en) | AOI character defect detection method and device based on industrial machine vision | |
CN111476109A (en) | Bill processing method, bill processing apparatus, and computer-readable storage medium | |
CN109426814B (en) | Method, system and equipment for positioning and identifying specific plate of invoice picture | |
CN107633239A (en) | Bill classification and bill field extracting method based on deep learning and OCR | |
CN106971406B (en) | Object pose detection method and device | |
CN111126391B (en) | Printed character defect positioning method | |
CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
CN113903024A (en) | Handwritten bill numerical value information identification method, system, medium and device | |
CN116309573B (en) | Defect detection method for printed characters of milk packaging box | |
WO2022227103A1 (en) | Intelligent detection and mark system and method for parts | |
CN114266764A (en) | Character integrity detection method and device for printed label | |
CN113063802A (en) | Printed label defect detection method and device | |
CN113838144A (en) | Method for positioning object on UV printer based on machine vision and deep learning | |
CN114187253A (en) | Circuit board part installation detection method | |
CN111259184B (en) | Image automatic labeling system and method for new retail | |
CN112488099A (en) | Digital detection extraction element on electric power liquid crystal instrument based on video | |
CN111223081A (en) | Part hole opening recognition and detection method and system based on deep learning | |
CN116563876A (en) | Invoice identification method | |
CN114955152A (en) | Intelligent labeling robot labeling error-proofing control system for electrolytic aluminum casting finished product aluminum ingot | |
CN106648171B (en) | A kind of interactive system and method based on lettering pen | |
CN114037822A (en) | Method and system for detecting driving license | |
CN114898083A (en) | Method, device and equipment for intelligently aligning circular red official seal |