WO2022148396A1 - 芯片采集方法和芯片定位方法 - Google Patents

芯片采集方法和芯片定位方法 Download PDF

Info

Publication number
WO2022148396A1
WO2022148396A1 PCT/CN2022/070496 CN2022070496W WO2022148396A1 WO 2022148396 A1 WO2022148396 A1 WO 2022148396A1 CN 2022070496 W CN2022070496 W CN 2022070496W WO 2022148396 A1 WO2022148396 A1 WO 2022148396A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
chip
code
detection area
encoded
Prior art date
Application number
PCT/CN2022/070496
Other languages
English (en)
French (fr)
Inventor
陈予郎
Original Assignee
长鑫存储技术有限公司
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 长鑫存储技术有限公司 filed Critical 长鑫存储技术有限公司
Publication of WO2022148396A1 publication Critical patent/WO2022148396A1/zh
Priority to US17/903,335 priority Critical patent/US11861451B2/en

Links

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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1439—Methods for optical code recognition including a method step for retrieval of the optical code
    • G06K7/1443—Methods for optical code recognition including a method step for retrieval of the optical code locating of the code in an image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
    • G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
    • G06K7/14—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation using light without selection of wavelength, e.g. sensing reflected white light
    • G06K7/1404—Methods for optical code recognition
    • G06K7/1408—Methods for optical code recognition the method being specifically adapted for the type of code
    • G06K7/1417—2D bar codes
    • 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
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20021—Dividing image into blocks, subimages or windows
    • 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
    • G06T2207/30148—Semiconductor; IC; Wafer
    • 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
    • G06T2207/30242—Counting objects in image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/06—Recognition of objects for industrial automation

Definitions

  • the embodiments of the present application relate to the field of semiconductor inspection, and in particular, to a chip collection method and a chip positioning method.
  • the calibration and identification of the chip on the chip tray is mainly by obtaining the code of the chip, and the code on the chip needs to be collected by an expensive laser camera.
  • the image shooting range of the laser camera is small, and a single acquisition only The code on a chip that can be collected.
  • the chips on the chip tray are mainly collected by manual control of the laser camera, and the number of chips on the chip tray is large. If the code of only one chip can be collected at a time, it will consume a lot of detection time, which is not conducive to the detection of chips. Batch production, and manual operation is prone to problems such as missing chips, repeated collection, and wrong position sequence collection. How to automate the collection of on-chip codes is an urgent problem to be solved in the semiconductor manufacturing process.
  • the embodiments of the present application provide a chip collection method and a chip positioning method, which can automatically realize the code acquisition of the chips on the chip tray, thereby saving the detection time of the chips and facilitating the mass production of the chips.
  • An embodiment of the present application provides a chip collection method, including: acquiring an image to be detected, where a chip coded image exists in the to-be-detected image, and the chip coded image is used to mark a semiconductor chip; acquiring a comparison image with the highest matching degree with the to-be-detected image in a database
  • the chip position information is used to indicate the position of the semiconductor chip in the comparison image; based on the chip position information, the position of the detection area in the image to be detected is obtained, and the detection area is used to mark the position of the chip coded image; If there is a chip code image in the image of the detection area, identify the chip code corresponding to the chip code image, and store the chip code in the database.
  • the image to be detected includes a plurality of chips, and the chip position information of the image to be detected is obtained through the chip position information of the comparison image with the highest matching degree of the image to be detected in the database, and the position of the detection area in the image to be detected is obtained. That is to obtain the chip position information of multiple chips in the image to be detected by comparing the chip position information in the image in the database, automatically realize the acquisition of the positions of multiple chips in the image to be detected, and then judge whether there is a chip code according to the image of the detection area. That is, the identification of multiple chip codes is realized at the same time, and the identification of multiple chips in the image to be inspected at the same time is realized through automation, which saves the inspection time of the chips and facilitates the mass production of chips.
  • judging whether there is a chip coded image in the image of the detection area includes the following steps: acquiring an image of the detection area, and the image of the detection area has a coding mark; based on the position of the coding mark and the signal strength of the coding mark, generating the position of the coding mark The relationship diagram with the signal strength of the coding mark; based on the difference between the relationship diagram and the signal strength of the coding mark at the preset position, it is determined whether the coding mark in the image of the detection area is a chip coding image.
  • generating a relationship diagram between the position of the coded mark and the signal strength of the coded mark comprising the steps of: setting a signal vector for analyzing the coded mark in the image of the detection area; obtaining The signal strength of the coded marker on the signal vector; based on the signal vector and the signal strength of the coded marker on the signal vector, a relationship diagram between the position of the coded marker and the signal strength of the coded marker is obtained.
  • the method further includes: judging whether there is a coding mark in the image of the detection area; if there is a coding mark in the image of the detection area, then executing judgment whether there is a chip in the image of the detection area.
  • identifying the chip code corresponding to the chip code image and storing the chip code in the database includes the following steps: binarizing the chip code image to obtain the chip code corresponding to the chip code image; storing the chip code in the database middle. Before the chip code is stored, the chip code is binarized, thereby improving the storage efficiency of the chip code.
  • the method further includes: performing code detection on the chip code, and if the chip code conforms to the code detection rule for code detection, executing the process of storing the chip code in the database. step.
  • the coding detection of the chip code includes the following steps: judging whether the length of the chip code belongs to a compliant length; judging whether each character of the chip code belongs to a compliant character.
  • the following steps are further included: acquiring an image of the detection area corresponding to the chip code image; enlarging the image in the detection area, and the magnification process is used to amplify the chip code image; Chip-encoded image.
  • the embodiment of the present application also provides a chip positioning method to obtain the chip position information in the above-mentioned chip acquisition method, including: obtaining an image to be positioned based on a positioning device; dividing the region of the image to be positioned to obtain a plurality of sub-positioning images, each There are chips in every sub-positioning image; the position of the chip in each sub-positioning image is obtained; based on the position of the chip in each sub-positioning image and the position of the sub-positioning image in the to-be-positioned image, the chip position information of the to-be-positioned image is obtained.
  • the positioning device divide the image to be positioned to obtain the chip position information in the image to be positioned, and then store the chip position information of the image to be positioned in the database as the chip position information of the comparison image, and then implement
  • the chip position information of the image to be positioned is mapped to the image to be detected according to the matching degree of the image to be detected and the comparison image, so as to automatically realize the code acquisition of the chip on the chip tray, thereby saving the detection time of the chip , which contributes to the mass production of chips.
  • dividing the area of the image to be positioned to obtain multiple sub-positioning images includes the following steps: obtaining a tray area based on the outer frame of the tray in the image to be positioned; dividing the tray area into equal areas to obtain multiple sub-positioning images with the same size Position the image.
  • dividing the tray area into equal areas includes the following steps: acquiring the number of vertical chips and the number of horizontal chips in the image to be positioned; Quantity, divide the tray area horizontally and equally.
  • the method further includes: obtaining a two-dimensional code image of each sub-positioning image based on the position of the chip in the sub-positioning image, and the two-dimensional code image only covers the position of the chip; Based on the position of the chip in each sub-positioning image and the position of the sub-positioning image in the image to be positioned, obtaining the chip position information of the image to be positioned includes: The information includes multiple two-dimensional code images and the positions of the multiple two-dimensional code images in the image to be positioned.
  • acquiring the two-dimensional code image of each sub-positioning image includes: performing size adjustment and position adjustment on the sub-positioning images at the same time, and obtaining an adjustment image; If there is a non-chip coded image, and the adjustment image covers all chip coded images, the adjustment image is set as the QR code image.
  • simultaneously performing size adjustment and position adjustment on the sub-positioning images including: based on the zoom-in and zoom-out instructions, simultaneously performing size adjustment on multiple sub-positioning images, so that there is no non-chip encoded image in the coverage area of the adjusted images;
  • the control instruction is used to adjust the positions of multiple sub-positioning images at the same time, so that the adjusted images cover all the chip-coded images.
  • FIG. 1 is a schematic flowchart of a chip collection method provided by an embodiment of the present application
  • FIG. 2 is a schematic flowchart of judging whether there is a chip-encoded image according to an embodiment of the present application
  • FIG. 3 is a schematic diagram of a signal vector provided by an embodiment of the present application.
  • FIG. 4 is a diagram of the relationship between the position of the encoded identifier and the signal strength of the encoded identifier provided by an embodiment of the present application;
  • FIG. 5 is a schematic flowchart of a chip collection method provided by another embodiment of the present application.
  • FIG. 6 is a schematic flowchart of a chip positioning method provided by another embodiment of the present application.
  • FIG. 7 is a schematic flowchart of obtaining a sub-location image provided by another embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a chip positioning method provided by still another embodiment of the present application.
  • FIG. 9 is a schematic diagram of an image to be positioned according to still another embodiment of the present application.
  • FIG. 10 is a schematic diagram of a sub-location image provided by still another embodiment of the present application.
  • FIG. 11 is a schematic diagram of a two-dimensional code image provided by still another embodiment of the present application.
  • the chips on the chip tray are mainly collected by manual control of the laser camera, and the number of chips on the chip tray is large. If the code of only one chip can be collected at a time, it will consume a lot of detection time, which is not conducive to the detection of chips. Batch production, and manual operation is prone to problems such as missing chip collection, repeated collection, and wrong position sequence collection.
  • An embodiment of the present application provides a chip collection method, which includes: acquiring an image to be detected, where a chip coded image exists in the to-be-detected image, and the chip coded image is used to mark a semiconductor chip; acquiring a comparison in a database with the highest matching degree with the to-be-detected image
  • the chip position information of the image, the chip position information is used to mark the position of the semiconductor chip in the contrast image; based on the chip position information, the position of the detection area in the image to be detected is obtained, and the detection area is used to mark the position of the chip coded image; based on the detection area If there is a chip code image in the image of the detection area, identify the chip code corresponding to the chip code image, and store the chip code in the database.
  • FIG. 1 is a schematic flowchart of a chip acquisition method provided by the embodiment
  • FIG. 2 is a schematic flowchart of judging whether there is a chip coded image provided by the embodiment
  • FIG. 3 is a schematic diagram of a signal vector provided by the embodiment
  • FIG. 4 is the embodiment. The following is a detailed description of the chip acquisition method provided by the embodiment of the present application in conjunction with the accompanying drawings, as follows:
  • the chip collection method includes the following steps:
  • Step 101 acquiring an image to be detected.
  • the to-be-detected image is acquired, and the to-be-detected image contains a chip coded image, and the chip coded image is used to mark the semiconductor chip.
  • the to-be-detected image is the acquired image of the chip tray, the to-be-detected image includes a plurality of chip code images, the chip code image contains a chip code, and the chip code is used for calibrating and identifying semiconductor chips.
  • the chip code Including a variety of general encoding formats in the form of Code-128, DataMatrix, QR-Code, etc.
  • Step 102 Obtain the chip position information of the comparison image with the highest matching degree with the image to be detected in the database.
  • the chip position information of the comparison image with the highest matching degree with the image to be detected in the database is acquired, and the chip position information is used to indicate the position of the semiconductor chip in the comparison image.
  • the chip position information of various comparison images is stored in the database; first, the matching degree between the image to be detected and the comparison image is obtained, and the matching degree is the similarity between the image to be detected and the comparison image; based on the matching degree, the matching degree between the image to be detected and the comparison image is obtained.
  • the chip position information of the comparison image with the highest matching degree is used to indicate the position of the semiconductor chip in the comparison image.
  • the size and size of the chip tray are not fixed, but the size and direction of the chips placed on the chip tray are fixed. Since the number of vertical chips and the number of horizontal chips on the chip tray are not fixed, it is necessary to pass the most similar chips. Compare the object to identify the chip position and identification sequence of the image to be detected.
  • Step 103 Acquire the position of the detection area in the image to be detected, and acquire an image of the detection area based on the position of the detection area.
  • the position of the detection area in the image to be detected is acquired, and the detection area is used to mark the position of the chip coded image; based on the position of the detection area, the image of the detection area is acquired.
  • the chip position information is mapped to the image to be detected, the position of the detection area indicated by the chip position information is obtained, and based on the position of the detection area and the to-be-detected image, the to-be-detected image is obtained. Detect the image of the detected area in the image.
  • Step 104 it is judged whether there is a chip coded image.
  • the method before judging whether there is a chip code image in the image of the detection area, the method further includes: judging whether there is a code mark in the image of the detection area; if there is a code mark in the image of the detection area, executing The step of judging whether a chip coded image exists in the image of the detection area; judging whether there is a chip coded image in the image of the detection area specifically includes: judging whether the coded mark is a chip coded image.
  • judging whether there is a chip coded image in the image of the detection area includes the following steps:
  • this embodiment is described in detail by taking an image of the detection area with a coding mark as an example. Specifically, when the image of the detection area has a coding mark, the following steps are included:
  • Step 111 acquiring an image of the detection area.
  • An image of the detection area is acquired, and the image of the detection area has a coding mark.
  • Step 112 setting a signal vector for analyzing the encoded identifier and obtaining the signal strength of the encoded identifier on the signal vector.
  • a signal vector 120 for analyzing the encoded identifier is set in the image of the detection area, and the signal strength of the encoded identifier on the signal vector 120 is obtained.
  • Step 113 Obtain a relationship diagram between the position of the encoded identifier and the signal strength of the encoded identifier.
  • a relationship diagram between the position of the coded marker and the signal strength of the coded marker is generated.
  • the relationship between the position of the coding mark and the signal strength of the coding mark in this embodiment is a bar graph, which is only a distance description.
  • the signal strength relationship diagram of the coding mark no matter what form the position of the coding mark and the signal strength relationship diagram of the coding mark are displayed in, should belong to the protection scope of the present application.
  • step 114 it is judged whether the coded identifier is a chip coded image.
  • the encoded identifier in the image of the detection area is a chip encoded image.
  • Determining whether the code mark in the image of the detection area is a chip code image includes the following steps:
  • i is used to represent the sequential position index value
  • j is used to represent the current position index value
  • a n is used to represent the signal strength of the coding mark position n
  • A5 Determine whether
  • step 105 identify the chip code corresponding to the chip code image, and store the chip code in the database; if there is no chip code image in the image of the detection area, continue to detect the next The presence or absence of a chip-encoded image in the image of an inspection area.
  • Step 105 Identify the chip code corresponding to the chip code image, and store the chip code in the database.
  • the size of some chip codes may be extremely small.
  • the size of the code is 4mm*4mm, and the chip code is difficult to be recognized at this time.
  • the average brightness of the code and the background The difference is only 8 gray values, and the chip code is difficult to identify at this time.
  • the magnification processing is used to amplify the chip coded image, and obtain the enlarged chip coded image; in an example, the magnification of the magnification is 1 times. , 1.5 times method, 2 times magnification and other magnifications, specifically, the specific magnification is manually set for the system, and the identification rate of the code is improved by enlarging the chip coded image and then identifying it.
  • the image to be detected includes a plurality of chips
  • the chip position information of the image to be detected is obtained through the chip position information of the comparison image with the highest matching degree with the image to be detected in the database, and the detection area in the image to be detected is obtained. s position. That is to obtain the chip position information of multiple chips in the image to be detected by comparing the chip position information in the image in the database, automatically realize the acquisition of the positions of multiple chips in the image to be detected, and then judge whether there is a chip code according to the image of the detection area. That is, the identification of multiple chip codes is realized at the same time, and the identification of multiple chips in the image to be inspected at the same time is realized through automation, which saves the inspection time of the chips and facilitates the mass production of chips.
  • Another embodiment of the present application relates to a chip collection method. Different from the previous embodiment, in this embodiment, before the chip code is stored, the chip code is binarized, thereby improving the accuracy of the chip code. storage efficiency.
  • FIG. 5 is a schematic flowchart of the chip collection method provided by the present embodiment.
  • the chip collection method provided by the present embodiment will be described in detail below with reference to the accompanying drawings. The same or corresponding parts as the above-mentioned embodiments will not be described in detail below.
  • the chip collection method includes the following steps:
  • Step 201 acquiring an image to be detected.
  • Step 202 Obtain the chip position information of the comparison image with the highest matching degree with the image to be detected in the database.
  • Step 203 Acquire the position of the detection area in the image to be detected, and acquire an image of the detection area based on the position of the detection area.
  • Step 204 it is judged whether there is a chip coded image.
  • step 205 is executed to perform binarization processing on the chip code image to obtain the chip code; if there is no chip code image in the image of the detection area, continue to detect the next detection area. Whether the chip-encoded image is present in the image.
  • Step 205 perform binarization processing on the chip code image to obtain the chip code.
  • Binarization is performed on the chip coded image to obtain the chip code corresponding to the chip coded image.
  • the chip-encoded image is converted into a binarized image, the non-encoded area is effectively removed, and the information of 0 and 1 in the encoded image is effectively classified, thereby improving the success rate of chip acquisition.
  • binarizing the chip-encoded image includes the following steps:
  • the coding flags whose signal strength is greater than m are calibrated to 1, and the coding flags whose signal strength is not greater than m are calibrated to 0.
  • Step 206 code detection is performed on the chip code.
  • the method further includes: performing code detection on the chip code. If the chip code conforms to the code detection rule for code detection, step 207 is executed, Steps for storing the chip code in the database.
  • the code detection of the chip code includes the following steps: judging whether the length of the chip code belongs to a compliant length, and judging whether each character of the chip code belongs to a compliant character.
  • the chip code when the chip code is collected, it may happen that the collection is successful but the code is misjudged. Therefore, it is necessary to perform code detection on the obtained chip code. If the chip code meets the code detection rules of the database, the chip code belongs to the compliance code. , otherwise, the chip code is a non-compliant code.
  • the compliance length of the encoded string refers to a range, such as [13, 20, 22-25]: the range is between "13", "20” or “22 to 25” ” are all legal lengths; define the form of bits, such as English letters, decimal numbers, hexadecimal numbers, etc., such as [B-G, Z, h-k; 1-3, 7, 9; 0-F, 3-B] Representation:
  • the character rule is separated by ";”, which means that this rule is only applicable when the length of the encoded string is 4, and the compliance range of the first character is between uppercase letters B to G or Z or lowercase h to k between English letters, the second character is a decimal number between 1 and 3 or 7 or 9, and the third character is a hexadecimal number between 0 and 9 or A-F.
  • the fourth character is a hexadecimal number between 3 and 9 or between A-B.
  • Step 207 the chip code is stored in the database.
  • Yet another embodiment of the present application provides a chip positioning method, including: obtaining an image to be positioned based on a positioning device; dividing the image to be positioned to obtain a plurality of sub-positioning images, each sub-positioning image having a chip; obtaining each sub-positioning image The position of the chip in the image; based on the position of the chip in each sub-positioning image and the position of the sub-positioning image in the image to be positioned, the chip position information of the image to be positioned is obtained.
  • FIG. 6 is a schematic flowchart of a chip positioning method provided by this embodiment
  • FIG. 7 is a schematic flowchart of a sub-location image acquisition provided by this embodiment.
  • the chip positioning method includes the following steps:
  • step 301 an image to be positioned is obtained based on a positioning device.
  • Step 302 Acquire multiple sub-location images, and acquire the location of the chip in each sub-location image.
  • the image to be positioned is divided into regions to obtain a plurality of sub-positioning images, each sub-positioning image has a chip, and the position of the chip in each sub-positioning image is obtained.
  • the image to be positioned is divided into regions to obtain a plurality of sub-positioning images, including the following steps:
  • Step 311 acquiring the tray area.
  • the image of the chip tray acquired by the current camera device is acquired, and a user interface is presented, and the acquired image of the chip tray is rendered into a background.
  • the push plate area is divided into equal areas, a plurality of sub-positioning images of the same size are obtained, and the tray area is divided by lights, including the following steps:
  • Step 312 Acquire the number of vertical chips and the number of horizontal chips in the image to be positioned.
  • the tray area is equally divided vertically, and based on the number of horizontal chips, the tray area is equally divided horizontally.
  • Step 313 acquiring a sub-positioning image.
  • the outer frame of the tray can be selected on the user interface by means of the mouse; the number of vertical chips and the number of horizontal chips (v, c) in the tray can be entered; The outer frame is cut horizontally into c segments to obtain v*c sub-positioning images of the same area; the sub-positioning images are sequentially numbered from 1 to v*c according to the rules from upper left to lower right.
  • step 303 acquiring the chip position information of the image to be positioned. 25
  • the chip position information of the image to be positioned is acquired.
  • the image to be positioned is obtained by a positioning device, the region of the image to be positioned is divided to obtain the chip position information in the image to be positioned, and then the chip position information of the image to be positioned is stored in the database as the reference image of the comparison image.
  • Chip position information in the subsequent process of implementing the chip collection method, the chip position information of the to-be-located image is mapped to the to-be-detected image through the matching degree of the image to be detected and the comparison image, so as to automatically realize the code acquisition of the chip on the chip tray , thereby saving the detection time of the chip and helping the mass production of the chip.
  • Yet another embodiment of the present application provides a chip positioning method.
  • the sub-positioning image in the process of obtaining the chip position information of the to-be-positioned image from the sub-positioning image, the sub-positioning image first obtains the sub-positioning image. Locate the QR code image of the image, and then obtain the chip position information of the to-be-located image through the QR code image, which greatly reduces the scope of image analysis, effectively improves the processing speed and eliminates the interference of background factors, and effectively improves the accuracy to reduce the need for obtaining chip position information. Data processing volume.
  • FIG. 8 is a schematic flowchart of a chip positioning method provided by this embodiment
  • FIG. 9 is a schematic diagram of an image to be positioned provided by this embodiment
  • FIG. 10 is a schematic diagram of a sub-location image provided by this embodiment
  • FIG. 11 is provided by this embodiment.
  • a schematic diagram of a two-dimensional code image is shown below.
  • the chip positioning method provided in this embodiment will be described in detail below with reference to the accompanying drawings. The same or corresponding parts as in the above-mentioned embodiment will not be described in detail below.
  • the chip positioning method includes the following steps:
  • Step 401 Acquire an image to be positioned based on a positioning device.
  • a sub-positioning image 502 is acquired based on the image to be positioned 501 in FIG. 9 (refer to FIG. 10 ).
  • step 402 a plurality of sub-location images are acquired, and the position of the chip in each sub-location image is acquired.
  • Step 403 acquiring a two-dimensional code image of each sub-positioning image.
  • a two-dimensional code image 503 is acquired based on the sub-positioning image 502 in FIG. 10 (refer to FIG. 11 ).
  • a two-dimensional code image of each sub-location image is obtained, and the two-dimensional code image only covers the location of the chip.
  • the size adjustment and position adjustment are performed on the sub-positioning image at the same time, and the adjustment image is obtained. If there is no non-chip encoded image in the coverage area of the adjustment image, and the adjustment adjustment image covers all the chip encoded images, the adjustment image is set as QR code image.
  • the size of the multiple sub-positioning images is adjusted simultaneously, so that there is no non-chip coded image in the coverage area of the adjusted image; based on the direction control instruction, the position adjustment is performed on the multiple sub-positioning images at the same time. , so that the conditioning image covers all chip-encoded images.
  • Step 404 based on the two-dimensional code image, obtain the chip position information of the image to be positioned.
  • obtaining the chip position information of the image to be positioned includes: obtaining the chip position information of the image to be positioned based on the two-dimensional code image, the chip The location information includes multiple two-dimensional code images and the positions of the multiple two-dimensional code images in the image to be positioned.
  • the area of the sub-positioning image is modified into a square, and the side length of the square is the minimum value of the side length of the sub-positioning image.
  • the square area is the adjustment image, and the “+” key or the “-” key of the keyboard is used to adjust the image. Control and adjust the image, so that all the adjustment images can be reduced or reduced at the same time, and the QR code area is controlled by the direction keys of the keyboard, so that all the QR code areas can be moved at the same time until the adjustment image covers all the chip codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Toxicology (AREA)
  • Electromagnetism (AREA)
  • Multimedia (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)
  • Image Analysis (AREA)

Abstract

一种芯片采集方法和芯片定位方法，其中，一种芯片采集方法包括：获取待检测图像，待检测图像中存在芯片编码图像，芯片编码图像用于标示半导体芯片；获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息，芯片位置信息用于标示对照图像中半导体芯片的位置；基于芯片位置信息，获取待检测图像中检测区域的位置，检测区域用于标示出芯片编码图像的位置；基于检测区域的位置，获取检测区域的图像；判断检测区域的图像中是否存在芯片编码图像；若检测区域的图像中存在芯片编码图像，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中。本申请自动化实现芯片托盘上芯片的编码获取。

Description

芯片采集方法和芯片定位方法
交叉引用
本申请基于申请号为202110026098.8、申请日为2021年01月08日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请实施例涉及半导体检测领域，特别涉及一种芯片采集方法和芯片定位方法。
背景技术
在半导体制程过程中，对芯片托盘(ChipTray)上芯片的标定和识别主要通过获取芯片的编码，而芯片上的编码需要使用高价的激光摄像机采集，激光摄像机的图像拍摄范围小，单次采集仅可采集到的一颗芯片上的编码。
目前，主要通过人工控制激光摄像机对芯片托盘上的芯片进行编码采集，而芯片托盘上的芯片数量多，若单次只能采集一颗芯片的编码，将耗费大量的检测时间，不利于芯片的批量产出，且人工操作容易出现芯片的遗漏采集、重复采集和错误位置顺序采集等问题，如何自动化实现芯片上编码的采集，是半导体制程过程中亟待解决的问题。
发明内容
本申请实施例提供一种芯片采集方法和芯片定位方法，自动化实现芯片托盘上芯片的编码获取，从而节省芯片的检测时间，有助于芯片的批量产出。
本申请实施例提供了一种芯片采集方法，包括：获取待检测图像，待检测图像中存在芯片编码图像，芯片编码图像用于标示半导体芯片；获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息，芯片位置信息用于标示对照图像中半导体芯片的位置；基于芯片位置信息，获取待检测图像中检测区域的位置，检测区域用于标示出芯片编码图像的位置；基于检测区域的位置，获取检测区域的图像；判断检测区域的图像中是否存在芯片编码图像；若检测区域的图像中存在芯片编码图像，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中。
待检测图像中包括多个芯片，通过数据库中与待检测图像匹配度最高的对照图像的芯片位置信息获取待检测图像的芯片位置信息，并 获取待检测图像中检测区域的位置。即通过数据库中对照图像中的芯片位置信息获取待检测图像中多个芯片的芯片位置信息，自动化实现待检测图像中多个芯片位置的获取，然后根据检测区域的图像判断其中是否存在芯片编码，即同时实现多个芯片编码的识别，通过自动化实现在待检测图像中同时对多个芯片的识别，节省芯片的检测时间，有助于芯片的批量产出。
另外，判断检测区域的图像中是否存在芯片编码图像，包括以下步骤：获取检测区域的图像，检测区域的图像中具有编码标识；基于编码标识的位置和编码标识的信号强度，生成编码标识的位置与编码标识的信号强度的关系图；基于关系图和预设位置的编码标识的信号强度差异，判断检测区域的图像中的编码标识是否为芯片编码图像。
另外，基于编码标识的位置和编码标识的信号强度，生成编码标识的位置与编码标识的信号强度的关系图，包括以下步骤：在检测区域的图像中设置用于分析编码标识的信号向量；获取信号向量上编码标识的信号强度；基于信号向量和信号向量上编码标识的信号强度，获取编码标识的位置与编码标识的信号强度的关系图。
另外，基于关系图和预设位置的编码标识的信号强度差异，判断检测区域的图像中的编码标识是否为芯片编码图像，包括以下步骤：设定当a i大于a j，则d i＝1，当a i不大于a j，则d i＝0，i用于表征循序位置索引值，j用于表征当前位置索引值，a n用于表征编码标识位置n的信号强度，d n用于表征编码标识位置n的判断值；A1：初始状态下，令i＝1，j＝1，并基于a 0和a 1获取b 1的值；A2：i递增1，获取d i的值；A3：判断d i与d j的值是否相同，d i＝d j则执行A4，d i≠d j则执行A5；A4：令j＝i，执行A2；A5：判断|a i-a j|是否大于t，|a i-a j|＞t则执行20A6，|a i-a j|≤t则执行A2，t用于表征容忍值；A6：令j＝i，s递增1，d i＝1-d i，执行A2，b用于表征标准振幅要求次数，s用于表征当前统计振幅次数；重复A1～A6，直至完成对所有编码标识位置n的判断，若检测区域的当前统计振幅次数不小于标准振幅要求次数，则判定检测区域中存在芯片编码图像。
另外，判断检测区域的图像中是否存在芯片编码图像之前，还包括：判断检测区域的图像中是否存在编码标识；若检测区域的图像中存在编码标识，则执行判断检测区域的图像中是否存在芯片编码图像的步骤；判断检测区域的图像中是否存在芯片编码图像，具体包括：判断编码标识是否为芯片编码图像。
另外，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中，包括以下步骤：对芯片编码图像进行二值化处理，获取对应于芯片编码图像的芯片编码；将芯片编码存储在数据库中。在对芯片编码进行存储之前，会对芯片编码进行二值化处理，从而提高芯片编码的存储效率。
另外，对芯片编码图像进行二值化处理，包括以下步骤：获取芯片编码图像所在的检测区域的图像，以获取x，x用于表征芯片编码图像所在检测区域的图像的像素总数；获取w和e，其中e＝w*x，e用于表征二值化评估值，w用于表征预设二值化评估百分比；获取芯片编码图像的信号强度由低到高的第一累加值，当第一累加值不小于e时，获取k 1，k 1用于表征获取二值化阈值的第一位置；获取芯片编码图像的信号强度由高到低的第二累加值，当第二累加值不小于e时，获取k 2，k 2用于表征获取二值化阈值的第二位置；获取m，其中，m＝(k 1+k 2)/2，m用于表征二值化处理阈值；将信号强度大于m的编码标识校订为1，将信号强度不大于m的编码标识校订为0。另外，识别芯片编码图像对应的芯片编码之后，且将芯片编码存储在数据库之前，还包括：对芯片编码进行编码检测，若芯片编码符合编码检测的编码检测规则，执行将芯片编码存储在数据库的步骤。
另外，对芯片编码进行编码检测，包括以下步骤：判断芯片编码的长度是否属于合规长度；判断芯片编码的每一个字符是否属于合规字符。
另外，识别芯片编码图像对应的芯片编码之前，还包括以下步骤：获取芯片编码图像对应的检测区域的图像；对检测区域的图像进行放大处理，放大处理用于放大芯片编码图像；获取放大后的芯片编码图像。
本申请实施例还提供了一种芯片定位方法，以获取上述芯片采集方法中的芯片位置信息，包括：基于定位设备获取待定位图像；对待定位图像进行区域划分，以获取多个子定位图像，每个子定位图像都存在芯片；获取每个子定位图像中芯片的所在位置；基于每个子定位图像中芯片的所在位置，以及子定位图像在待定位图像中的位置，获取待定位图像的芯片位置信息。
通过定位设备获取待定位图像，对待定位图像进行区域划分，以获取待定位图像中的芯片位置信息，然后将待定位图像的芯片位置信息存储在数据库中作为对照图像的芯片位置信息，后续在实现芯片采 集方法的过程中，通过待检测图像和对照图像的匹配度，将待定位图像的芯片位置信息映射到待检测图像中，从而自动化实现芯片托盘上芯片的编码获取，从而节省芯片的检测时间，有助于芯片的批量产出。
另外，对待定位图像进行区域划分，以获取多个子定位图像，包括以下步骤：基于待定位图像中的托盘外框，获取托盘区域；对托盘区域进行等量区域划分，获取多个大小一致的子定位图像。
另外，对托盘区域进行等量区域划分，包括以下步骤：获取待定位图像中的纵向芯片数和横向芯片数；基于纵向芯片数的数量，对托盘区域进行纵向等量划分；基于横向芯片数的数量，对托盘区域进行横向等量划分。
另外，获取每个子定位图像中芯片的所在位置之后，还包括：基于子定位图像中的芯片的所在位置，获取每个子定位图像的二维码图像，二维码图像仅覆盖芯片的所在位置；基于每个子定位图像中芯片的所在位置，以及子定位图像在待定位图像的位置，获取待定位图像的芯片位置信息，包括：基于二维码图像，获取待定位图像的芯片位置信息，芯片位置信息包括多个二维码图像，以及多个二维码图像在待定位图像中的位置。
另外，基于子定位图像中的芯片的所在位置，获取每个子定位图像的二维码图像，包括：对子定位图像同时进行大小调整和位置调整，获取调节图像；若调节图像的覆盖区域中不存在非芯片编码图像，且调节图像覆盖所有芯片编码图像，则将调节图像设定为二维码图像。
另外，对子定位图像同时进行大小调整和位置调整，包括：基于放大指令和缩小指令，对多个子定位图像同时进行大小调整，以使调节图像的覆盖区域中不存在非芯片编码图像；基于方向控制指令，对多个子定位图像同时进行位置调整，以使调节图像覆盖所有芯片编码图像。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，除非有特别申明，附图中的图不构成比例限制。
图1为本申请一实施例提供的芯片采集方法的流程示意图；
图2为本申请一实施例提供的判断是否存在芯片编码图像的流程示意图；
图3为本申请一实施例提供的信号向量的示意图；
图4为本申请一实施例提供的编码标识的位置与编码标识的信号强度关系图；
图5为本申请另一实施例提供的芯片采集方法的流程示意图；
图6为本申请又一实施例提供的芯片定位方法的流程示意图；
图7为本申请又一实施例提供的获取子定位图像的流程示意图；
图8为本申请再一实施例提供的芯片定位方法的流程示意图；
图9为本申请再一实施例提供的待定位图像的示意图；
图10为本申请再一实施例提供的子定位图像的示意图；
图11为本申请再一实施例提供的二维码图像的示意图。
具体实施方式
目前，主要通过人工控制激光摄像机对芯片托盘上的芯片进行编码采集，而芯片托盘上的芯片数量多，若单次只能采集一颗芯片的编码，将耗费大量的检测时间，不利于芯片的批量产出，且人工操作容易出现芯片的遗漏采集、重复采集和错误位置顺序采集等问题。
本申请一实施例提供了一种芯片采集方法，包括：获取待检测图像，待检测图像中存在芯片编码图像，芯片编码图像用于标示半导体芯片；获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息，芯片位置信息用于标示对照图像中半导体芯片的位置；基于芯片位置信息，获取待检测图像中检测区域的位置，检测区域用于标示出芯片编码图像的位置；基于检测区域的位置，获取检测区域的图像；判断检测区域的图像中是否存在芯片编码图像；若检测区域的图像中存在芯片编码图像，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中。
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合附图对本申请的各实施例进行详细的阐述。然而，本领域的普通技术人员可以理解，在本申请各实施例中，为了使读者更好地理解本申请而提出了许多技术细节。但是，即使没有这些技术细节和基于以下各实施例的种种变化和修改，也可以实现本申请所要求保护的技术方案。以下各个实施例的划分是为了描述方便，不应对本申请的具体实现方式构成任何限定，各个实施例在不矛盾的前提下可以相互结合，相互引用。
图1为实施例提供的芯片采集方法的流程示意图，图2为本实施例提供的判断是否存在芯片编码图像的流程示意图，图3为本实施例提供的信号向量的示意图，图4为本实施例提供的编码标识的位置与 编码标识的信号强度关系图，下面结合附图对本申请实施例提供的芯片采集方法进行详细说明，具体如下：
参考图1，芯片采集方法，包括以下步骤：
步骤101，获取待检测图像。
获取待检测图像，待检测图像中存在芯片编码图像，芯片编码图像用于标示半导体芯片。
具体地，待检测图像即获取的芯片托盘的图像，待检测图像中包括多个芯片编码图像，芯片编码图像中存在芯片编码，芯片编码用于标定和识别半导体芯片，在一个例子中，芯片编码包括例如Code-128,DataMatrix,QR-Code等形式的多种通用编码格式。
步骤102，获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息。
获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息，芯片位置信息用于标示对照图像中半导体芯片的位置。
具体地，数据库中存储有多种对照图像的芯片位置信息；首先，获取待检测图像与对照图像的匹配度，匹配度即待检测图像和对照图像相似度；基于匹配度，获取与待检测图像匹配度最高的对照图像的芯片位置信息，芯片位置信息用于标示对照图像中半导体芯片的位置。
在一个例子中，芯片托盘的尺寸和大小非固定，但是摆放在芯片托盘上芯片的尺寸和芯片方向是固定的，由于芯片托盘纵向芯片数量与横向芯片数量非固定，需要通过相似度最高的对照对象，对待检测图像的芯片位置与识别顺序进行识别。
步骤103，获取待检测图像中检测区域的位置，基于检测区域的位置，获取检测区域的图像。
基于芯片位置信息，获取待检测图像中检测区域的位置，检测区域用于标示出芯片编码图像的位置；基于检测区域的位置，获取检测区域的图像。
具体地，基于相似度最高的对照图像的芯片位置信息，将芯片位置信息映射到待检测图像中，获取芯片位置信息标示的检测区域的位置，并基于检测区域的位置和待检测图像，获取待检测图像中检测区域的图像。
步骤104，判断是否存在芯片编码图像。
需要说明的是，在其他实施例中，判断检测区域的图像中是否存 在芯片编码图像之前，还包括：判断检测区域的图像中是否存在编码标识；若检测区域的图像中存在编码标识，则执行判断检测区域的图像中是否存在芯片编码图像的步骤；判断检测区域的图像中是否存在芯片编码图像，具体包括：判断编码标识是否为芯片编码图像。通过判断检测区域中是否存在编码标识，再对编码标识是否为芯片编码图像进行判断，减少系统对检测区域的图像进行判断的数据处理量，从而加快芯片识别的进程。
具体地，判断检测区域的图像中是否存在芯片编码图像，包括以下步骤：
参考图2，本实施例以检测区域的图像中具有编码标识为例进行详细说明，具体地，当检测区域的图像中具有编码标识时，包括以下步骤：
步骤111，获取检测区域图像。
获取检测区域的图像，检测区域的图像中具有编码标识。
步骤112，设置用于分析编码标识的信号向量并获取信号向量上编码标识的信号强度。
具体地，参考图3，在检测区域的图像中设置用于分析所述编码标识的信号向量120，并获取信号向量120上编码标识的信号强度。
步骤113，获取编码标识的位置与编码标识的信号强度的关系图。
具体地，参考图4，基于信号向量和信号向量上编码标识的信号强度，生成编码标识的位置与编码标识的信号强度关系图。
需要说明的是，本实施例中的编码标识的位置与编码标识的信号强度关系图为柱状图仅为距离说明，在其他实施例中，可以采用折线图或表格等形式体现编码标识的位置与编码标识的信号强度关系图，本领域技术人员可知，无论编码标识的位置与编码标识的信号强度关系图以何种形式展现，都应属于本申请的保护范围。
继续参考图3，步骤114，判断编码标识是否为芯片编码图像。
具体地，基于关系图和预设位置的编码标识的信号强度差异，判断检测区域的图像中的编码标识是否为芯片编码图像。
判断检测区域的图像中的编码标识是否为芯片编码图像，包括以下步骤：
i用于表征循序位置索引值，j用于表征当前位置索引值，a n用于表征编码标识位置n的信号强度，d n用于表征编码标识位置n的判断值，设定当a i大于a j，则d i＝1，当a i不大于a j，则d i＝0。
A1：初始状态下，令i＝1，j＝1，并基于a 0和a 1获取b 1的值。
A2：i递增1，获取d i的值。
A3：判断d i与d j的值是否相同，d i＝d j则执行A4，d i≠d j则执行A5。
A4：令j＝i，执行A2。
A5：判断|a i-a j|是否大于t，|a i-a j|＞t则执行A6，|a i-a j|≤t则执行A2，t用于表征容忍值。
A6：令j＝i，s递增1，d i＝1-d i，执行A2，b用于表征标准振幅要求次数，s用于表征当前统计振幅次数。
重复A1～A6，直至完成对所有编码标识位置n的判断，若检测区域的当前统计振幅次数不小于标准振幅要求次数，则判定检测区域中存在芯片编码图像。
信号强度存在足够大的振幅落差，即标准振幅，当检测区域的图像中存在足够多的标准振幅，则检测区域的图像中存在芯片编码图像。
若检测区域的图像中存在芯片编码图像，则执行步骤105，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中；若检测区域的图像中不存在芯片编码图像，则继续检测下一个检测区域的图像中是否存在芯片编码图像。
步骤105，识别芯片编码图像对应的芯片编码，并将芯片编码存储在数据库中。
需要说明的是，部分芯片编码的尺寸可能极小，如编码尺寸的规格为4mm*4mm，此时芯片编码难以被识别；另外，在灰阶(gray level)图像中，编码与背景的平均亮度差异仅为8个灰度值，此时芯片编码难以被识别。
在本实施例中，识别芯片编码图像对应的芯片编码之前，还包括以下步骤：
获取芯片编码图像对应的检测区域的图像，对检测区域的图像进行放大处理，放大处理用于放大芯片编码图像，获取放大后的芯片编码图像；在一个例子中，放大处理的倍数为1倍放大、1.5倍方法、2倍放大等倍率，具体地，具体放大倍率通过人工为系统进行设置，通过对芯片编码图像进行放大处理之后进行识别，从而提高编码的辨识率。
相对于相关技术而言，待检测图像中包括多个芯片，通过数据库 中与待检测图像匹配度最高的对照图像的芯片位置信息获取待检测图像的芯片位置信息，并获取待检测图像中检测区域的位置。即通过数据库中对照图像中的芯片位置信息获取待检测图像中多个芯片的芯片位置信息，自动化实现待检测图像中多个芯片位置的获取，然后根据检测区域的图像判断其中是否存在芯片编码，即同时实现多个芯片编码的识别，通过自动化实现在待检测图像中同时对多个芯片的识别，节省芯片的检测时间，有助于芯片的批量产出。
上面各种步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其流程的核心设计都在该专利的保护范围内。
本申请另一实施例涉及一种芯片采集方法，与前一实施例不同的是，在本实施例中在对芯片编码进行存储之前，会对芯片编码进行二值化处理，从而提高芯片编码的存储效率。
图5为本实施例提供的芯片采集方法的流程示意图，下面结合附图对本实施例提供的芯片采集方法进行详细说明，与上述实施例相同或相应的部分，以下将不做详细赘述。
参考图5，芯片采集方法，包括以下步骤：
步骤201，获取待检测图像。
步骤202，获取数据库中与待检测图像匹配度最高的对照图像的芯片位置信息。
步骤203，获取待检测图像中检测区域的位置，并基于检测区域的位置，获取检测区域的图像。
步骤204，判断是否存在芯片编码图像。
若检测区域的图像中存在芯片编码图像，则执行步骤205，对芯片编码图像进行二值化处理，获取芯片编码；若检测区域的图像中不存在芯片编码图像，则继续检测下一个检测区域的图像中是否存在芯片编码图像。
步骤205，对芯片编码图像进行二值化处理，获取芯片编码。
对芯片编码图像进行二值化处理，获取对应于芯片编码图像的芯片编码。通过寻找一个最佳阈值，将芯片编码图像转化为二值化图像，有效去除非编码区域，并有效归类编码图像中0与1的信息，从而提高芯片采集的成功率。
具体地，对芯片编码图像进行二值化处理，包括以下步骤：
获取芯片编码图像所在的检测区域的图像，以获取x，x用于表征芯片编码图像所在检测区域的图像的像素总数。
获取w和e，其中e＝w*x，e用于表征二值化评估值，w用于表征预设二值化评估百分比。
获取芯片编码图像的信号强度由低到高的第一累加值，当第一累加值不小于e时，获取k 1，k 1用于表征获取二值化阈值的第一位置。
获取芯片编码图像的信号强度由高到低的第二累加值，当第二累加值不小于e时，获取k 2，k 2用于表征获取二值化阈值的第二位置。
获取m，其中，m＝(k 1+k 2)/2，m用于表征二值化处理阈值。
将信号强度大于m的所述编码标识校订为1，将信号强度不大于m的所述编码标识校订为0。
步骤206，对芯片编码进行编码检测。
在本实施例中，识别芯片编码图像对应的芯片编码之后，且将芯片编码存储在数据库之前，还包括：对芯片编码进行编码检测，若芯片编码符合编码检测的编码检测规则，执行步骤207，将芯片编码存储在数据库的步骤。
具体地，对芯片编码进行编码检测，包括以下步骤：判断芯片编码的长度是否属于合规长度，判断芯片编码的每一个字符是否属于合规字符。
在一个例子中，芯片编码采集时，可能会发生采集成功但编码误判的情况，因此需要对获取的芯片编码进行编码检测，若芯片编码满足数据库的编码检测规则，芯片编码则属于合规编码，否则，芯片编码属于非合规编码。
具体地，定义编码字符串的合规长度，这里的合规长度指代一个范围，如[13，20，22-25]表示：范围于“13”、“20”或者“22至25之间”皆为合规长度；定义位元形态，如英文字母、十进制数字、十六进制数字等，如[B-G，Z，h-k；1-3，7，9；0-F，3-B]表示：以“；”为字元规则的分隔，表示此规则仅适用于编码字串长度为4时使用，第一个字元合规范围为大写字母B至G之间或Z或小写h至k之间的英文字母，第二个字元合规范围为1至3之间或7或9的十进位数字，第三个字元合规范围为0至9之间或A-F之间的十六进位数字，第四个字元合规范围为3至9之间或A-B之间的十六进位数字。
步骤207，将芯片编码存储在数据库中。
上面各种步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其流程的核心设计都在该专利的保护范围内。
由于上述实施例与本实施例相互对应，因此本实施例可与上述实施例互相配合实施。上述实施例中提到的相关技术细节在本实施例中依然有效，在上述实施例中所能达到的技术效果在本实施例中也同样可以实现，为了减少重复，这里不再赘述。相应地，本实施例中提到的相关技术细节也可应用在上述实施例中。
本申请又一实施例提供了一种芯片定位方法，包括：基于定位设备获取待定位图像；对待定位图像进行区域划分，以获取多个子定位图像，每个子定位图像都存在芯片；获取每个子定位图像中芯片的所在位置；基于每个子定位图像中芯片的所在位置，以及子定位图像在待定位图像中的位置，获取待定位图像的芯片位置信息。
图6为本实施例提供的芯片定位方法的流程示意图，图7为本实施例提供的获取子定位图像的流程示意图，下面结合附图对本申请实施例提供的芯片定位方法进行详细说明，具体如下：
参考图6，芯片定位方法，包括以下步骤：
步骤301，基于定位设备获取待定位图像。
步骤302，获取多个子定位图像，并获取每个子定位图像中芯片的所在位置。
对待定位图像进行区域划分，以获取多个子定位图像，每个子定位图像都存在芯片，获取每个子定位图像中芯片的所在位置。
参考图7，对待定位图像进行区域划分，以获取多个子定位图像，包括以下步骤：
步骤311，获取托盘区域。
基于待定位图像中的托盘外框，获取托盘区域。
在一个例子中，获取当前摄像设备所获取的托盘芯片图像，并呈现一个使用界面，将获取的托盘芯片图像渲染成背景。
对所述推盘区域进行等量区域划分，获取多个大小一致的子定位图像，对托盘区域进行灯亮划分，包括以下步骤：
步骤312，获取待定位图像中的纵向芯片数和横向芯片数。
具体地，获取待定位图像中的纵向芯片数和横向芯片数，基于纵 向芯片数的数量，对托盘区域进行纵向等量划分，基于横向芯片数的数量，对托盘区域进行横向等量划分。
步骤313，获取子定位图像。
在一个例子中，可借由鼠标于使用界面上选中托盘外框；键入托盘的纵向芯片数和横向芯片数(v，c)；将托盘外框纵向等量切割成v个片段，并将托盘外框横向等量切割成c个片段，获取v*c个同等面积的子定位图像；将子定位图像依左上至右下的规则，循序将芯片区域有1至v*c编号。
继续参考图6，步骤303，获取待定位图像的芯片位置信息。25
基于每个子定位图像中芯片的所在位置，以及子定位图像在待定位图像中的位置，获取待定位图像的芯片位置信息。
相对于相关技术而言，通过定位设备获取待定位图像，对待定位图像进行区域划分，以获取待定位图像中的芯片位置信息，然后将待定位图像的芯片位置信息存储在数据库中作为对照图像的芯片位置信息，后续在实现芯片采集方法的过程中，通过待检测图像和对照图像的匹配度，将待定位图像的芯片位置信息映射到待检测图像中，从而自动化实现芯片托盘上芯片的编码获取，从而节省芯片的检测时间，有助于芯片的批量产出。
上面各种步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其流程的核心设计都在该专利的保护范围内。
本申请再一实施例提供了一种芯片定位方法，与前一实施例不同的是，在本实施例中由子定位图像获取待定位图像的芯片位置信息的过程中，会先由子定位图像获取子定位图像的二维码图像，然后通过二维码图像获取待定位图像的芯片位置信息，大幅缩小图像分析范围，有效提升处理速度且排除背景因素干扰，有效提升准确率以减少获取芯片位置信息的数据处理量。
图8为本实施例提供的芯片定位方法的流程示意图，图9为本实施例提供的待定位图像的示意图，图10为本实施例提供的子定位图像的示意图，图11为本实施例提供的二维码图像的示意图，下面结合附图对本实施例提供的芯片定位方法进行详细说明，与上述实施例相同或相应的部分，以下将不做详细赘述。
参考图8，芯片定位方法，包括以下步骤：
步骤401，基于定位设备获取待定位图像。
基于图9中的待定位图像501获取子定位图像502(参考图10)。
继续参考图8，步骤402，获取多个子定位图像，并获取每个子定位图像中芯片的所在位置。
步骤403，获取每个子定位图像的二维码图像。
基于图10中的子定位图像502获取二维码图像503(参考图11)。
具体地，基于子定位图像中的芯片的所在位置，获取每个子定位图像的二维码图像，所述二维码图像仅覆盖芯片的所在位置。
具体地，对子定位图像同时进行大小调整和位置调整，获取调节图像，若调节图像的覆盖区域中不存在非芯片编码图像，且调节调节图像覆盖所有芯片编码图像，则将调节图像设定为二维码图像。
更具体地，基于放大指令和缩小指令，对多个子定位图像同时进行大小调整，以使调节图像的覆盖区域中不存在非芯片编码图像；基于方向控制指令，对多个子定位图像同时进行位置调整，以使调节图像覆盖所有芯片编码图像。
步骤404，基于二维码图像，获取待定位图像的芯片位置信息。
基于每个字定位图像中芯片的所在位置，以及子定位图像在待定位图像的位置，获取待定位图像的芯片位置信息，包括：基于二维码图像，获取待定位图像的芯片位置信息，芯片位置信息包括多个二维码图像，以及多个二维码图像在待定位图像中的位置。
在一个例子中，将子定位图像的区域修改为正方形，正方形的边长为子定位图像边长的最小值，此时正方形区域为调节图像，借由键盘的“+”键或“-”键控制调节图像，使全部调节图像同时方法或缩小，借由键盘的方向键控制二维码区域，使全部二维码区域同时进行位置移动，直至调节图像覆盖所有芯片编码。
上面各种步骤划分，只是为了描述清楚，实现时可以合并为一个步骤或者对某些步骤进行拆分，分解为多个步骤，只要包括相同的逻辑关系，都在本专利的保护范围内；对流程中添加无关紧要的修改或者引入无关紧要的设计，但不改变其流程的核心设计都在该专利的保护范围内。
本领域的普通技术人员可以理解，上述各实施例是实现本申请的具体实施例，而在实际应用中，可以在形式上和细节上对其作各种改变，而不偏离本申请的精神和范围。

Claims (16)

  1. 一种芯片采集方法，包括：
    获取待检测图像，所述待检测图像中存在芯片编码图像，所述芯片编码图像用于标示半导体芯片；
    获取数据库中与所述待检测图像匹配度最高的对照图像的芯片位置信息，所述芯片位置信息用于标示所述对照图像中半导体芯片的位置；
    基于所述芯片位置信息，获取所述待检测图像中检测区域的位置，所述检测区域用于标示出所述芯片编码图像的位置；
    基于所述检测区域的位置，获取所述检测区域的图像；
    判断所述检测区域的图像中是否存在所述芯片编码图像；
    若所述检测区域的图像中存在所述芯片编码图像，识别所述芯片编码图像对应的芯片编码，并将所述芯片编码存储在所述数据库中。
  2. 根据权利要求1所述的芯片采集方法，其中，所述判断所述检测区域的图像中是否存在所述芯片编码图像，包括以下步骤：
    获取所述检测区域的图像，所述检测区域的图像中具有编码标识；
    基于所述编码标识的位置和所述编码标识的信号强度，生成所述编码标识的位置与所述编码标识的信号强度的关系图；
    基于所述关系图和预设位置的所述编码标识的信号强度差异，判断所述检测区域的图像中的所述编码标识是否为所述芯片编码图像。
  3. 根据权利要求2所述的芯片采集方法，其中，所述基于所述编码标识的位置和所述编码标识的信号强度，生成所述编码标识的位置与所述编码标识的信号强度的关系图，包括以下步骤：
    在所述检测区域的图像中设置用于分析所述编码标识的信号向量；
    获取所述信号向量上所述编码标识的信号强度；
    基于所述信号向量和所述信号向量上所述编码标识的信号强度，获取所述编码标识的位置与所述编码标识的信号强度的关系图。
  4. 根据权利要求2所述的芯片采集方法，其中，所述基于所述关系图和预设位置的所述编码标识的信号强度差异，判断所述检测区域的图像中的所述编码标识是否为所述芯片编码图像，包括以下步骤：
    设定当a i大于a j，则d i＝1，当a i不大于a j，则d i＝0，i用于表征 循序位置索引值，j用于表征当前位置索引值，a n用于表征编码标识位置n的信号强度，d n用于表征编码标识位置n的判断值；
    A1：初始状态下，令i＝1，j＝1，并基于a 0和a 1获取b 1的值；
    A2：i递增1，获取d i的值；
    A3：判断d i与d j的值是否相同，d i＝d j则执行A4，d i≠d j则执行A5；
    A4：令j＝i，执行A2；
    A5：判断|a i-a j|是否大于t，|a i-a j|＞t则执行A6，|a i-a j|≤t则执行A2，t用于表征容忍值；
    A6：令j＝i，s递增1，d i＝1-d i，执行A2，b用于表征标准振幅要求次数，s用于表征当前统计振幅次数；
    重复A1～A6，直至完成对所有编码标识位置n的判断，若所述检测区域的当前统计振幅次数不小于所述标准振幅要求次数，则判定所述检测区域中存在芯片编码图像。
  5. 根据权利要求1所述的芯片采集方法，其中，包括：
    所述判断所述检测区域的图像中是否存在所述芯片编码图像之前，还包括：判断所述检测区域的图像中是否存在编码标识；
    若所述检测区域的图像中存在所述编码标识，则执行所述判断所述检测区域的图像中是否存在所述芯片编码图像的步骤；
    所述判断所述检测区域的图像中是否存在所述芯片编码图像，具体包括：判断所述编码标识是否为所述芯片编码图像。
  6. 根据权利要求1所述的芯片采集方法，其中，所述识别所述芯片编码图像对应的芯片编码，并将所述芯片编码存储在所述数据库中，包括以下步骤：
    对所述芯片编码图像进行二值化处理，获取对应于所述芯片编码图像的芯片编码；
    将所述芯片编码存储在所述数据库中。
  7. 根据权利要求6所述的芯片采集方法，其中，所述对所述芯片编码图像进行二值化处理，包括以下步骤：
    获取所述芯片编码图像所在的所述检测区域的图像，以获取x，x用于表征芯片编码图像所在检测区域的图像的像素总数；
    获取w和e，其中e＝w*x，e用于表征二值化评估值，w用于表征预设二值化评估百分比；
    获取所述芯片编码图像的信号强度由低到高的第一累加值，当第 一累加值不小于e时，获取k 1，k 1用于表征获取二值化阈值的第一位置；
    获取所述芯片编码图像的信号强度由高到低的第二累加值，当第二累加值不小于e时，获取k 2，k 2用于表征获取二值化阈值的第二位置；
    获取m，其中，m＝(k 1+k 2)/2，m用于表征二值化处理阈值；
    将信号强度大于m的所述编码标识校订为1，将信号强度不大于m的所述编码标识校订为0。
  8. 根据权利要求1所述的芯片采集方法，其中，所述识别所述芯片编码图像对应的芯片编码之后，且所述将所述芯片编码存储在数据库之前，还包括：对所述芯片编码进行编码检测，若所述芯片编码符合所述编码检测的编码检测规则，执行所述将所述芯片编码存储在所述数据库的步骤。
  9. 根据权利要求8所述的芯片采集方法，其中，所述对所述芯片编码进行编码检测，包括以下步骤：
    判断所述芯片编码的长度是否属于合规长度；
    判断所述芯片编码的每一个字符是否属于合规字符。
  10. 根据权利要求1所述的芯片采集方法，其中，所述识别所述芯片编码图像对应的芯片编码之前，还包括以下步骤：
    获取所述芯片编码图像对应的所述检测区域的图像；
    对所述检测区域的图像进行放大处理，所述放大处理用于放大所述芯片编码图像；
    获取放大后的所述芯片编码图像。
  11. 一种芯片定位方法，以获取权利要求1～10任一项所述的芯片采集方法中所述的芯片位置信息，包括：
    基于定位设备获取待定位图像；
    对所述待定位图像进行区域划分，以获取多个子定位图像，每个所述子定位图像都存在芯片；
    获取每个所述子定位图像中芯片的所在位置；
    基于每个所述子定位图像中芯片的所在位置，以及所述子定位图像在所述待定位图像中的位置，获取所述待定位图像的所述芯片位置信息。
  12. 根据权利要求11所述的芯片定位方法，其中，所述对所述待定位图像进行区域划分，以获取多个子定位图像，包括以下步骤：
    基于所述待定位图像中的托盘外框，获取托盘区域；
    对所述托盘区域进行等量区域划分，获取多个大小一致的所述子定位图像。
  13. 根据权利要求12所述的芯片定位方法，其中，所述对所述托盘区域进行等量区域划分，包括以下步骤：
    获取所述待定位图像中的纵向芯片数和横向芯片数；
    基于所述纵向芯片数的数量，对所述托盘区域进行纵向等量划分；
    基于所述横向芯片数的数量，对所述托盘区域进行横向等量划分。
  14. 根据权利要求11所述的芯片定位方法，其中，包括：
    所述获取每个所述子定位图像中芯片的所在位置之后，还包括：
    基于所述子定位图像中的芯片的所在位置，获取每个所述子定位图像的二维码图像，所述二维码图像仅覆盖所述芯片的所在位置；
    所述基于每个所述子定位图像中芯片的所在位置，以及所述子定位图像在所述待定位图像的位置，获取所述待定位图像的所述芯片位置信息，包括：
    基于所述二维码图像，获取所述待定位图像的所述芯片位置信息，所述芯片位置信息包括多个所述二维码图像，以及多个所述二维码图像在所述待定位图像中的位置。
  15. 根据权利要求14所述的芯片定位方法，其中，所述基于所述子定位图像中的芯片的所在位置，获取每个所述子定位图像的二维码图像，包括：
    对所述子定位图像同时进行大小调整和位置调整，获取调节图像；
    若所述调节图像的覆盖区域中不存在非芯片编码图像，且所述调节图像覆盖所有芯片编码图像，则将所述调节图像设定为所述二维码图像。
  16. 根据权利要求15所述的芯片定位方法，其中，对所述子定位图像同时进行大小调整和位置调整，包括：
    基于放大指令和缩小指令，对多个所述子定位图像同时进行大小调整，以使所述调节图像的覆盖区域中不存在非芯片编码图像；
    基于方向控制指令，对多个所述子定位图像同时进行位置调整，以使所述调节图像覆盖所有所述芯片编码图像。
PCT/CN2022/070496 2021-01-08 2022-01-06 芯片采集方法和芯片定位方法 WO2022148396A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US17/903,335 US11861451B2 (en) 2021-01-08 2022-09-06 Method for chip collection and method for chip positioning

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110026098.8A CN114757872A (zh) 2021-01-08 2021-01-08 芯片采集方法和芯片定位方法
CN202110026098.8 2021-01-08

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/903,335 Continuation US11861451B2 (en) 2021-01-08 2022-09-06 Method for chip collection and method for chip positioning

Publications (1)

Publication Number Publication Date
WO2022148396A1 true WO2022148396A1 (zh) 2022-07-14

Family

ID=82325759

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/070496 WO2022148396A1 (zh) 2021-01-08 2022-01-06 芯片采集方法和芯片定位方法

Country Status (3)

Country Link
US (1) US11861451B2 (zh)
CN (1) CN114757872A (zh)
WO (1) WO2022148396A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116320248B (zh) * 2023-05-18 2023-08-29 深圳曦华科技有限公司 存储芯片共享系统、方法、相关装置及存储介质
CN117457536B (zh) * 2023-11-01 2024-03-26 江苏新智达新能源设备有限公司 一种基于图像处理的芯片智能拾取方法

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140050401A1 (en) * 2012-08-15 2014-02-20 Augmented Reality Lab LLC Fast Image Processing for Recognition Objectives System
CN104881665A (zh) * 2015-04-29 2015-09-02 华中科技大学 一种芯片字符识别与校验方法及装置
CN105046271A (zh) * 2015-06-25 2015-11-11 哈尔滨工业大学 基于模板匹配的melf元件定位与检测方法
CN105404900A (zh) * 2015-12-22 2016-03-16 广州视源电子科技股份有限公司 一种并排二极管的定位方法及装置
CN111274961A (zh) * 2020-01-20 2020-06-12 华南理工大学 一种柔性ic基板字符识别和信息解析方法
CN112101060A (zh) * 2020-10-28 2020-12-18 大连海事大学 基于平移不变性和小区域模板匹配的二维码定位方法

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202632312U (zh) 2012-03-07 2012-12-26 河南李烨包装科技有限公司 基于图像识别技术同时采集处理多个条形码信息的系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140050401A1 (en) * 2012-08-15 2014-02-20 Augmented Reality Lab LLC Fast Image Processing for Recognition Objectives System
CN104881665A (zh) * 2015-04-29 2015-09-02 华中科技大学 一种芯片字符识别与校验方法及装置
CN105046271A (zh) * 2015-06-25 2015-11-11 哈尔滨工业大学 基于模板匹配的melf元件定位与检测方法
CN105404900A (zh) * 2015-12-22 2016-03-16 广州视源电子科技股份有限公司 一种并排二极管的定位方法及装置
CN111274961A (zh) * 2020-01-20 2020-06-12 华南理工大学 一种柔性ic基板字符识别和信息解析方法
CN112101060A (zh) * 2020-10-28 2020-12-18 大连海事大学 基于平移不变性和小区域模板匹配的二维码定位方法

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
GUO XIAOFENG, ET AL.: "IC Chip Character Segmentation and Recognition Method Based on Geometric Features", CAAI TRANSACTIONS ON INTELLIGENT SYSTEMS, vol. 15, no. 1, 31 January 2020 (2020-01-31), pages 144 - 151, XP055949707, ISSN: 1673-4785, DOI: 10.11992/tis.201904028 *
WANG WENPING: "Halcon-Based Chip Character Recognition", MASTER THESIS, TIANJIN POLYTECHNIC UNIVERSITY, CN, no. 4, 15 April 2019 (2019-04-15), CN , XP055949705, ISSN: 1674-0246 *

Also Published As

Publication number Publication date
US11861451B2 (en) 2024-01-02
CN114757872A (zh) 2022-07-15
US20220414360A1 (en) 2022-12-29

Similar Documents

Publication Publication Date Title
CN105426530B (zh) 一种商标检索方法、装置和系统
WO2022148396A1 (zh) 芯片采集方法和芯片定位方法
CN110909732B (zh) 一种图中数据的自动提取方法
US8620094B2 (en) Pattern recognition apparatus, pattern recogntion method, image processing apparatus, and image processing method
CN109886928B (zh) 一种目标细胞标记方法、装置、存储介质及终端设备
CN106295498B (zh) 光学遥感图像目标区域检测装置与方法
WO2017101225A1 (zh) 一种商标图形要素识别方法、装置、系统以及计算机存储介质
WO2017041600A1 (zh) 一种汉信码特征图形检测方法及系统
CN112016481B (zh) 基于ocr的财务报表信息检测和识别方法
CN111274961B (zh) 一种柔性ic基板字符识别和信息解析方法
CN114005126A (zh) 表格重构方法、装置、计算机设备及可读存储介质
CN114037672A (zh) 一种图像缺陷的检测方法、装置及计算机可读介质
CN108734849B (zh) 一种自动化发票验真方法及系统
CN115240213A (zh) 表格图像识别方法、装置、电子设备及存储介质
CN117474929A (zh) 基于机器视觉的托盘外形尺寸检测方法及系统
CN108596115A (zh) 一种基于卷积神经网络的车辆检测方法、装置及系统
CN117037185B (zh) 一种基于光学字符识别技术的导线线号识别方法及装置
CN113569677A (zh) 一种基于扫描件的纸质试验报告生成方法
EP3477547A1 (en) Optical character recognition systems and methods
CN111428534B (zh) 一种基于点阵隐写信息编码的解密识别方法
KR101849933B1 (ko) 공분산 기술자와 퍼지 모델을 이용한 심볼 인식장치
CN114972274A (zh) 一种基于裂缝连通域的区域搜索连接方法
JP2008276311A (ja) 文字認識装置、外観検査装置及び文字認識方法
Peng et al. Document image matching based on component blocks
JP2005250786A (ja) 画像認識方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22736558

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22736558

Country of ref document: EP

Kind code of ref document: A1