WO2023185118A1 - 图像处理方法、装置、电子设备及存储介质 - Google Patents

图像处理方法、装置、电子设备及存储介质 Download PDF

Info

Publication number
WO2023185118A1
WO2023185118A1 PCT/CN2022/140357 CN2022140357W WO2023185118A1 WO 2023185118 A1 WO2023185118 A1 WO 2023185118A1 CN 2022140357 W CN2022140357 W CN 2022140357W WO 2023185118 A1 WO2023185118 A1 WO 2023185118A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
battery cell
cell
target subject
body image
Prior art date
Application number
PCT/CN2022/140357
Other languages
English (en)
French (fr)
Inventor
陈德
晏栋
林锡祥
Original Assignee
广东利元亨智能装备股份有限公司
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 广东利元亨智能装备股份有限公司 filed Critical 广东利元亨智能装备股份有限公司
Publication of WO2023185118A1 publication Critical patent/WO2023185118A1/zh

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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/13—Edge detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
    • 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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20152—Watershed segmentation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
    • Y02E60/10—Energy storage using batteries

Definitions

  • the present application relates to the field of image processing technology, specifically, to an image processing method, device, electronic equipment and storage medium.
  • lithium batteries have been widely used in various industries, such as mobile phones, tablets, notebooks, desktop computers, electric cars, electric buses, etc. Consumer demand for lithium batteries is very high, and the quality requirements for lithium batteries are getting higher and higher.
  • the image of the processed semi-finished battery core needs to be detected.
  • the existing detection method has low detection efficiency and cannot guarantee accuracy, and cannot meet the increasing high-precision requirements of battery core design.
  • the purpose of the embodiments of the present application is to provide an image processing method, device, electronic equipment and storage medium to solve the problem of inaccurate battery cell image positioning.
  • this application provides an image processing method, which method includes:
  • the edge image of the battery core body image in the preset direction is processed to obtain a second battery core image.
  • the image processing method provided by the embodiment of the present application extracts the battery cell main body image of the first battery cell image based on the contour external polygon function, and can obtain an accurate battery cell main body image, and then uses a perspective correction algorithm to process the battery cell main body image.
  • Obtaining the battery cell main body image in the preset direction can correct the angular deviation of the battery cell main body image, and process the edge image of the battery cell main body image to obtain a clear and accurate second battery cell image. This method can improve the accuracy of battery core image positioning and improve the efficiency of battery core detection.
  • the method further includes: removing the cell body image in the preset direction. The tabs in the main body image of the battery cell.
  • the impact of the tabs on the battery core detection can be reduced and the accuracy of the battery core detection can be improved.
  • the method before extracting the cell body image from the acquired first cell image based on the contour circumscribed polygon function, the method further includes:
  • the maximum outline of the target subject image is determined to obtain the first cell image.
  • an accurate first battery cell image can be extracted and the positioning of the first battery cell can be improved.
  • the accuracy of the core image is improved, and the efficiency of battery core detection is improved.
  • extracting a target subject image based on the original image includes:
  • the binary image is processed using a threshold segmentation method to extract the target subject image.
  • the threshold segmentation method is used to process the binary image, so that the target subject image can be quickly and effectively extracted.
  • the threshold segmentation method is used to process the binary image and extract the target subject image, including:
  • a segmentation threshold is determined based on a threshold segmentation method, and the binary image is processed according to the segmentation threshold to extract the target subject image.
  • the binary image is processed through the segmentation threshold and the target subject image is extracted.
  • the accurate first battery cell image can be extracted, which improves the accuracy of positioning the first battery cell image and improves the battery cell quality. Detection efficiency.
  • the method further includes:
  • the target subject image is processed using morphological operations; wherein the morphological operations include opening operations and closing operations.
  • morphological operations are used to process the target subject image, which can maintain the basic shape characteristics of the image and remove irrelevant structures.
  • processing the edge image of the cell body image in the preset direction to obtain a second cell image includes:
  • a watershed segmentation algorithm is used to restore the edge image in the cell body image in the preset direction to obtain a second cell image.
  • the watershed segmentation algorithm is used to restore the edge image of the main body image of the battery cell in the preset direction, thereby improving the clarity and accuracy of the battery core image.
  • an image processing device which includes:
  • An extraction module for extracting the main body image of the battery cell from the acquired first battery cell image based on the contour circumscribed polygon function
  • the first processing module is used to process the battery cell body image using a perspective correction algorithm to obtain a battery cell body image in a preset direction;
  • the second processing module is used to process the edge image of the cell body image in the preset direction to obtain a second cell image.
  • inventions of the present application also provide an electronic device.
  • the electronic device includes a memory and a processor.
  • Program instructions are stored in the memory.
  • the processor reads and runs the program instructions, it executes Steps in any of the above implementations.
  • embodiments of the present application also provide a computer-readable storage medium.
  • Computer program instructions are stored in the computer-readable storage medium. When the computer program instructions are read and run by a processor, they are executed. Steps in any of the above implementations.
  • Figure 1 is a flow chart of an image processing method provided by an embodiment of the present application.
  • Figure 2 is a flow chart before step 110 of the image processing method provided by the embodiment of the present application.
  • FIG. 3 is a schematic diagram of the functional modules of the image processing device provided by the embodiment of the present application.
  • FIG. 4 is a block diagram of an electronic device provided by an embodiment of the present application.
  • the existing detection method When inspecting the image of processed semi-finished battery cells, the existing detection method has low detection efficiency.
  • the battery core image is directly positioned. The accuracy of positioning cannot be guaranteed and cannot meet the increasing high-precision requirements of battery cell design.
  • the embodiment of the present application provides an image processing method, which extracts an accurate battery cell main body image based on the contour circumscribed polygon function, and then uses a perspective correction algorithm to correct the angular deviation of the battery cell main body image, and to correct the battery cell main body image.
  • the edge image is processed to obtain a clear and accurate second cell image.
  • This method can improve the accuracy of battery core image positioning and improve the efficiency of battery core detection.
  • the image processing method provided by this application is described below through several embodiments.
  • FIG. 1 is a flow chart of the image processing method provided by an embodiment of the present application, which may include steps 110 to 140 .
  • Step 110 Extract the main body image of the battery cell from the acquired first battery cell image based on the contour circumscribed polygon function.
  • the cell is a single electrochemical cell containing positive and negative electrodes, which together with the protective circuit board form a rechargeable battery.
  • Step 120 Use a perspective correction algorithm to process the battery cell main body image to obtain a battery cell main body image in a preset direction.
  • the four corner points of the minimum circumscribed rectangle of the battery cell main image are determined as the four corner points of the battery core main body image.
  • the order of the four corner points should be upper left, upper right, lower left and lower right, through getPerspectiveTransform
  • the function obtains the perspective transformation matrix, and then uses the warpPerspective function to perform perspective transformation to obtain the cell body image in the preset direction.
  • the preset direction may be the horizontal direction
  • the first cell image may have a deviation in the horizontal direction rotation angle.
  • the deviation can be adjusted through the perspective correction algorithm to make the cell positioning more accurate and improve the efficiency of cell detection.
  • Step 130 Process the edge image of the cell body image in the preset direction to obtain a second cell image.
  • the grabcut algorithm is used to process the edge image of the cell body image in the preset direction to obtain the second cell image.
  • the grabcut algorithm is an image segmentation method based on graph theory.
  • an energy function is defined.
  • the input of the energy function is the image and the marked foreground and background.
  • the output of the energy function is the segmented image, where,
  • the probability of labeling the foreground and background parts of the image can be estimated using a Gaussian model.
  • the image processing method may also include step 140.
  • Step 140 Remove the tabs from the cell body image in the preset direction.
  • the tabs are metal conductors that lead out the positive and negative electrodes from the battery core, and are the contact points for charging and discharging of the battery.
  • Figure 2 is a flow chart before step 110 of the image processing method provided by the embodiment of the present application.
  • steps 150 to 170 may be included before step 110 .
  • Step 150 Obtain the original image of the battery cell.
  • a camera device can be used to obtain the original image of the battery core.
  • Step 160 Extract the target subject image based on the original image.
  • RGB Red, G: Green, B: Blue
  • the values are divided into 0-255.
  • Pixel is the smallest image unit, and a picture is composed of multiple pixels.
  • the original image is then binarized, so that the gray value of each pixel in the original image is 0 (black) or 255 (white), and the target subject image is extracted.
  • the gray value range in the grayscale image is 0-255
  • the gray value range in the binarized image is 0 or 255.
  • Step 170 Determine the maximum outline of the target subject image to obtain the first cell image.
  • the contour points of all areas of the target subject image are searched, and the area with the largest area in the first battery cell image is determined, and this area is the first battery cell image.
  • step 160 may include steps 161 to 162.
  • Step 161 Suppress the highlight part of the original image to obtain a binary image.
  • Step 162 Use the threshold segmentation method to process the binary image and extract the target subject image.
  • the grayscale of the battery core in the binary image is relatively large.
  • Using the threshold segmentation method to segment according to the second preset threshold can quickly and effectively extract the target subject image.
  • step 162 may also include: determining a segmentation threshold based on a threshold segmentation method, processing the binary image according to the segmentation threshold, and extracting the target subject image.
  • the threshold segmentation method is an algorithm for determining the binary segmentation threshold of an image.
  • the threshold segmentation method divides the image into background and foreground parts according to the grayscale characteristics of the binary image.
  • the threshold segmentation method used is the Otsu threshold segmentation method.
  • the segmentation threshold of the foreground and background is marked as T
  • the proportion of the number of pixels belonging to the foreground to the entire image is marked as ⁇ 0
  • its average gray level is ⁇ 0
  • the pixels belonging to the background are The proportion of points in the entire image is denoted as ⁇ 1
  • its average gray level is ⁇ 1
  • the total average gray level of the image is denoted as ⁇
  • the inter-class variance is denoted as g.
  • N 0 +N 1 M*N
  • the traversal method is used to obtain the segmentation threshold T that maximizes the inter-class variance g.
  • step 170 may also be included after step 162.
  • Step 170 Use morphological operations to process the target subject image; where the morphological operations include opening operations and closing operations.
  • the basic idea of morphological operations is to use structural elements with certain shapes to measure and extract corresponding shapes in images to achieve the purpose of image analysis and recognition.
  • the application of morphological operations can simplify image data and preserve the image.
  • morphological operations in image processing may also include dilation, erosion, opening operations, closing operations, etc.
  • dilation refers to expanding the image
  • corrosion refers to shrinking the image.
  • the closing operation is to first expand and then erode, that is, the target subject image is first expanded and then reduced.
  • the closing operation can fill the holes in the target subject image.
  • the opening operation corrodes first and then expands, that is, the target subject image first shrinks and then expands.
  • the opening operation can disconnect the connection in the target subject image.
  • step 130 may also include: using a watershed segmentation algorithm to restore the edge image in the cell body image in the preset direction to obtain a second cell image.
  • Watershed is an image segmentation algorithm based on geographical morphological analysis, which imitates geographical structures (such as mountains, ravines, basins, etc.) to classify different objects.
  • the basic idea of the watershed segmentation algorithm is to regard the image (such as the main body image of the battery cell) as a geodesic topological landform.
  • the gray value of each pixel in the image represents the altitude of the point.
  • Each local minimum value and its The area of influence is called a catchment basin, and the boundaries of the catchment basin form the watershed.
  • the watershed segmentation algorithm is used to process the battery cell main body image.
  • the detected contour is closed, which facilitates subsequent operations, and the detection is highly efficient, which can improve the accuracy and clarity of the second battery cell image.
  • a geodesic distance threshold is set. Determine the pixel with the smallest grayscale value, and increase the grayscale value from the minimum value. During the growth process, you will encounter domain pixels. Measure the geodesic distance from the domain pixel to the lowest point of grayscale value. If it is less than the geodesic distance, If the distance threshold is set, the pixels in the field will be submerged, otherwise a dam will be set on the pixels in the field to complete the classification of the pixels in the field. Until the maximum gray value, all areas meet at the watershed line, and the dam partitions the entire edge image. The concave and convex curves of the edge image can be redisplayed, improving the clarity and accuracy of the cell image.
  • the embodiments of the present application also provide an image processing device corresponding to the image processing method. Since the problem-solving principle of the device in the embodiments of the present application is similar to that of the aforementioned image processing method embodiments, in this embodiment
  • For the implementation of the device please refer to the description in the embodiments of the above method, and repeated details will not be described again.
  • FIG. 3 is a schematic diagram of the functional modules of the image processing device provided by an embodiment of the present application.
  • the embodiment of the present application provides an image processing device 200.
  • the image processing device 200 includes an extraction module 210, a first processing module 220 and a second processing module 230.
  • the extraction module 210 is configured to extract the cell body image from the acquired first cell image based on the contour circumscribed polygon function.
  • the first processing module 220 is used to process the battery cell main body image using a perspective correction algorithm to obtain a battery cell main body image in a preset direction.
  • the second processing module 230 is used to process the edge image of the cell body image in the preset direction to obtain a second cell image.
  • the image processing device 200 further includes a removal module 240.
  • the removal module 240 is used to remove the tabs in the cell body image in the preset direction.
  • the image processing device 200 may also include an image extraction module 250, and the image extraction module 250 is used for:
  • the maximum outline of the target subject image is determined to obtain the first cell image.
  • the image extraction module 250 is also used to:
  • the threshold segmentation method is used to process the binary image and extract the target subject image.
  • the image extraction module 250 is also used to:
  • the segmentation threshold is determined based on the threshold segmentation method, and the binary image is processed according to the segmentation threshold to extract the target subject image.
  • the image extraction module 250 is also used to:
  • Morphological operations are used to process the target subject image; morphological operations include opening operations and closing operations.
  • the second processing module 230 is also configured to use a watershed segmentation algorithm to restore the edge image in the cell body image in the preset direction to obtain a second cell image.
  • FIG. 4 is a block diagram of an electronic device provided by an embodiment of the present application.
  • the embodiment of this application introduces the electronic device for running the image processing method.
  • Electronic device 300 may include processor 310 and memory 320.
  • Persons of ordinary skill in the art can understand that the structure shown in FIG. 4 is only illustrative and does not limit the structure of the electronic device 300 .
  • electronic device 300 may also include more or fewer components than shown in FIG. 4 , or have a different configuration than shown in FIG. 4 .
  • the electronic device 300 may be a smartphone, a personal computer (PC), a tablet, a personal digital assistant (PDA), a mobile Internet device (MID), etc.
  • PC personal computer
  • PDA personal digital assistant
  • MID mobile Internet device
  • the above-mentioned processor 310 and memory 320 are directly or indirectly electrically connected to each other to realize data transmission or interaction. For example, these components may be electrically connected to each other through one or more communication buses or signal lines.
  • the above-mentioned processor 310 is used to execute executable modules stored in the memory.
  • the memory 320 can be, but is not limited to, random access memory (Random Access Memory, referred to as RAM), read-only memory (Read Only Memory, referred to as ROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM) ), Erasable Programmable Read-Only Memory (EPROM for short), Electrically Erasable Programmable Read-Only Memory (EEPROM for short), etc.
  • RAM Random Access Memory
  • ROM Read Only Memory
  • PROM programmable read-only memory
  • EPROM Erasable Programmable Read-Only Memory
  • EEPROM Electrically Erasable Programmable Read-Only Memory
  • the above-mentioned processor 310 may be an integrated circuit chip with signal processing capabilities.
  • the above-mentioned processor 310 can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (digital signal processor, referred to as DSP) ), Application Specific Integrated Circuit (ASIC for short), Field Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP digital signal processor
  • ASIC Application Specific Integrated Circuit
  • FPGA Field Programmable Gate Array
  • a general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
  • the electronic device 300 in this embodiment can be used to perform each step in each method provided by the embodiment of this application.
  • embodiments of the present application also provide a computer-readable storage medium.
  • the computer-readable storage medium stores a computer program. When the computer program is run by a processor, the steps of any of the above methods are executed.
  • the computer program product of the image processing method provided by the embodiment of the present application includes a computer-readable storage medium storing program code.
  • the instructions included in the program code can be used to execute the steps of the image processing method described in the above method embodiment. , please refer to the above method embodiments for details, and will not be described again here.
  • each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more components for implementing the specified logical function(s). Executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures.
  • each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or acts. , or can be implemented using a combination of specialized hardware and computer instructions.
  • each functional module in each embodiment of the present application can be integrated together to form an independent part, each module can exist alone, or two or more modules can be integrated to form an independent part.
  • the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the technical solution of the present application is essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product.
  • the computer software product is stored in a storage medium, including Several instructions are used to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program code.
  • ROM read-only memory
  • RAM random access memory
  • magnetic disk or optical disk and other media that can store program code.
  • relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply that these entities or operations are mutually exclusive. any such actual relationship or sequence exists between them.
  • the terms “comprises,” “comprises,” or any other variations thereof are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that includes a list of elements includes not only those elements, but also those not expressly listed other elements, or elements inherent to the process, method, article or equipment.
  • an element defined by the statement "comprising" does not exclude the presence of additional identical elements in a process, method, article, or device that includes the stated element.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Quality & Reliability (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本申请提供一种图像处理方法、装置、电子设备及存储介质，涉及图像处理技术领域。所述方法包括：基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像；采用透视校正算法对电芯主体图像进行处理，得到预设方向的电芯主体图像；以及对预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。采用本申请实施例提供的图像处理方法可以解决电芯图像定位不准确的问题。

Description

图像处理方法、装置、电子设备及存储介质 技术领域
本申请涉及图像处理技术领域，具体而言，涉及一种图像处理方法、装置、电子设备及存储介质。
背景技术
目前，锂电池已经广泛地运用于各个行业，如手机、平板、笔记本、台式电脑、电动轿车、电动公交车等。消费者对锂电池的需求量非常大，而且对锂电池的质量要求越来越高。现有技术中，需要对加工后的半成品电芯的图像进行检测，而现有的检测方式其检测效率低，且准确性无法保证，无法满足日益增进的电芯设计高精度要求。
发明内容
本申请实施例的目的在于提供一种图像处理方法、装置、电子设备及存储介质，用以解决电芯图像定位不准确的问题。
主要包括以下几个方面：
第一方面，本申请提供一种图像处理方法，所述方法包括：
基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像；
采用透视校正算法对所述电芯主体图像进行处理，得到预设方向的电芯主体图像；以及
对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
本申请实施例提供的图像处理方法，基于轮廓外接多边形函数提取出第一电芯图像的电芯主体图像，可以得到准确的电芯主体图像，再采用透视校正算法对电芯主体图像进行处理，得到预设方向的电芯主体图像，可以校正电芯主体图像的角度偏差，以及对电芯主体图像的边缘图像进行处理，可以得到清晰和准确的第二电芯图像。通过该方法可以提高电芯图像定位的准确性，提高了电芯检测的效率。
在一些可选的实施方式中，所述采用透视校正算法对所述电芯主体图像进行处理，得到预设方向的电芯主体图像之后，所述方法还包括：移除所述预设方向的电芯主体图像中的极耳。
在上述实施方式中，通过移除预设方向的电芯主体图像中的极耳，可以降低极耳对 电芯检测时的影响，提高电芯检测的准确性。
在一些可选的实施方式中，所述基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像之前，所述方法还包括：
获取电芯的原始图像；
基于所述原始图像，提取出目标主体图像；以及
确定出所述目标主体图像的最大轮廓，得到第一电芯图像。
在上述实施方式中，通过基于原始图像提取出目标主体图像，并确定出目标主体图像的最大轮廓，得到第一电芯图像，可以提取出准确的第一电芯图像，提高了定位第一电芯图像的准确性，以及提高了电芯检测的效率。
在一些可选的实施方式中，所述基于所述原始图像，提取出目标主体图像，包括：
抑制所述原始图像的高光部分，获得二值图像；
采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像。
在上述实施方式中，通过抑制原始图像的高光部分，获得二值图像，并采用阈值分割法对二值图像进行处理，可快速有效地提取出目标主体图像。
在一些可选的实施方式中，所述采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像，包括：
基于阈值分割法确定出分割阈值，并根据所述分割阈值进行对所述二值图像进行处理，提取出所述目标主体图像。
在上述实施方式中，通过分割阈值对二值图像进行处理，提取出目标主体图像，可以提取出准确的第一电芯图像，提高了定位第一电芯图像的准确性，以及提高了电芯检测的效率。
在一些可选的实施方式中，在所述采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像之后，所述方法还包括：
采用形态学操作对所述目标主体图像进行处理；其中，所述形态学操作包括开操作和闭操作。
在上述实施方式中，采用形态学操作答对目标主体图像进行处理，可以保持图像基本的形状特性，并除去不相干的结构。
在一些可选的实施方式中，所述对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像，包括：
采用分水岭分割算法对所述预设方向的电芯主体图像中的边缘图像进行还原处理， 得到第二电芯图像。
在上述实施方式中，通过分水岭分割算法对预设方向的电芯主体图像的边缘图像进行还原处理，提高了电芯图像的清晰度和准确度。
第二方面，本申请实施例提供一种图像处理装置，所述装置包括：
提取模块，用于基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像；
第一处理模块，用于采用透视校正算法对所述电芯主体图像进行处理，获得预设方向的电芯主体图像；以及
第二处理模块，用于对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
第三方面，本申请实施例还提供了一种电子设备，所述电子设备包括存储器和处理器，所述存储器中存储有程序指令，所述处理器读取并运行所述程序指令时，执行上述任一实现方式中的步骤。
第四方面，本申请实施例还提供了一种计算机可读存储介质，所述计算机可读取存储介质中存储有计算机程序指令，所述计算机程序指令被一处理器读取并运行时，执行上述任一实现方式中的步骤。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本申请的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。
图1为本申请实施例提供的图像处理方法的流程图；
图2为本申请实施例提供的图像处理方法的步骤110之前的流程图；
图3为本申请实施例提供的图像处理装置的功能模块示意图；
图4为本申请实施例提供的电子设备的方框示意图。
具体实施方式
为使本申请实施例的目的、技术方案和优点更加清楚，下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。以下对本申请的实施例的详细描述并非旨在限制要求保护的本申请的范围，而是仅仅表示本申请的选定实施例。基于本申 请的实施例，本领域技术人员在没有做出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。
对加工后的半成品电芯的图像检测的时候，现有的检测方式其检测效率低，直接对电芯图像进行定位，定位的准确性无法保证，无法满足日益增进的电芯设计高精度要求。
有基于此，本申请实施例提供一种图像处理方法，基于轮廓外接多边形函数提取出准确的电芯主体图像，再采用透视校正算法校正电芯主体图像的角度偏差，以及对电芯主体图像的边缘图像进行处理，由此得到清晰和准确的第二电芯图像。通过该方法可以提高电芯图像定位的准确性，提高了电芯检测的效率。下面通过几个实施例描述本申请提供的图像处理方法。
本申请实施例提供一种图像处理方法，请参看图1，图1为本申请实施例提供的图像处理方法的流程图，可以包括步骤110至步骤140。
步骤110、基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像。
示例性地，电芯为单个含有正、负极的电化学电芯，其与保护电路板组成充电电池。
示例性地，首先查找第一电芯图像的所有区域的轮廓点，确定出第一电芯图像中面积最大的区域，此区域即为电芯主体图像的区域。然后遍历所有轮廓点，由轮廓点集确定出最小外接矩形，对该电芯主体图像的区域通过外接矩形获得电芯主体图像。
步骤120、采用透视校正算法对电芯主体图像进行处理，得到预设方向的电芯主体图像。
示例性地，确定出电芯主体图像的最小外接矩形的四个角点，作为电芯主体图像的四个角点，四个角点的顺序应为左上、右上、左下以及右下，通过getPerspectiveTransform函数得到透视变换矩阵，再通过warpPerspective函数进行透视变换得到预设方向的电芯主体图像。
示例性地，预设方向可以是水平方向，第一电芯图像可能存在水平方向旋转角度的偏差，通过透视校正算法可以调整该偏差，使电芯定位更加的准确，提高了电芯检测的效率。
步骤130、对预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
示例性地，采用grabcut算法对预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
示例性地，grabcut算法是一种基于图论的图像分割方法，首先定义一个能量函数，能量函数的输入为图像和被标记好的前景、背景，能量函数的输出为分割后的图像，其 中，对图像的前景部分和背景部分的标记可以采用高斯模型估算概率。采用grabcut算法对边缘图像进行处理，可以得到清晰和准确的第二电芯图像。
可选地，图像处理方法还可以包括步骤140。
步骤140、移除预设方向的电芯主体图像中的极耳。
示例性地，极耳是从电芯中将正负极引出来的金属导电体，是电池进行充放电的接触点。通过移除电芯主体图像中的极耳，可以降低极耳对电芯检测时的影响，提高电芯检测的准确性。
如图2所示，图2为本申请实施例提供的图像处理方法的步骤110之前的流程图。
可选地，步骤110之前可以包括步骤150至步骤170。
步骤150、获取电芯的原始图像。
示例性地，可以采用摄像头装置获取电芯的原始图像，摄像装置可以是一个，摄像装置也可以是多个，获取电芯的原始图像。
步骤160、基于原始图像，提取出目标主体图像。
示例性地，在图像处理中，用RGB(R：Red，G：Green，B：Blue)三个分量，即红、绿和蓝三原色来表示真彩色，R分量、G分量以及B分量的取值分为均为0-255，比如电脑屏幕上的一个红色的像素点的三个分量的值分别为：255，0，0。像素点是最小的图像单元，一张图片由多个像素点构成。
示例性地，对原始图像进行灰度化处理，让原始图像中的每一个像素点都满足：R＝G＝B，即红色变量、绿色变量以及蓝色变量的值相等，此时这个值为灰度值。
示例性地，再对原始图像进行二值化处理，让原始图像中的每个像素点的灰度值为0(黑色)或者255(白色)，提取出目标主体图像。在灰度化的图像中灰度值的范围为0-255，在二值化后的图像中的灰度值范围是0或者255。
步骤170、确定出目标主体图像的最大轮廓，得到第一电芯图像。
示例性地，查找目标主体图像的所有区域的轮廓点，确定出第一电芯图像中面积最大的区域，此区域即为第一电芯图像。
可选地，步骤160可以包括步骤161至步骤162。
步骤161、抑制所述原始图像的高光部分，获得二值图像。
示例性地，由于拍摄原始图像时的光源问题，原始图像的周围会有白色高光的部分，通过抑制原始图像的高光部分，即将灰度值大于预设值的像素点的灰度值设置为0，将图像中灰度大于第一预设阈值的像素提取出来，由此获得二值图像。
步骤162、采用阈值分割法对二值图像进行处理，提取出目标主体图像。
示例性地，电芯在二值图像中的灰度相对较大，采用阈值分割法按照第二预设阈值进行分割，可快速有效地提取出目标主体图像。
可选地，步骤162还可以包括：基于阈值分割法确定出分割阈值，并根据分割阈值进行对二值图像进行处理，提取出目标主体图像。
示例性地，阈值分割法是一种确定图像二值化分割阈值的算法。阈值分割法按二值图像的灰度特性，将图像分成背景和前景两部分。
示例性地，采用的阈值分割法为大津阈值分割法。具体地，对于图像I(x，y)，前景和背景的分割阈值记为T，属于前景的像素点数占整幅图像的比例记为ω 0，其平均灰度为μ 0，属于背景的像素点数占整幅图像的比例记为ω 1，其平均灰度为μ 1，图像的总平均灰度记为μ，类间方差记为g。
假设图像的背景较暗，并且图像的大小为M*N，图像中像素的灰度值小于分割阈值T的像素个数记为N 0，像素灰度大于分割阈值T的像素个数记为N 1，则有：
Figure PCTCN2022140357-appb-000001
Figure PCTCN2022140357-appb-000002
N 0+N 1＝M*N
ω 0+ω 1＝1
μ＝ω 0*μ 0+ω 1*μ 1
g＝ω 0(μ_0-μ) 2+ω 1(μ 0-μ) 2
由以上公式可得：
g＝ω 0ω 1(μ 0-μ) 2
采用遍历的方法得到是类间方差g最大的分割阈值T。
可选地，步骤162后还可以包括步骤170。
步骤170、采用形态学操作对目标主体图像进行处理；其中，形态学操作包括开操作和闭操作。
示例性地，形态学操作的基本思想是用具有一定形态的结构元素去度量和提取图像中的对应形状以达到对图像分析和识别的目的，形态学操作处理的应用可以简化图像数据，保持图像基本的形状特性，并除去不相干的结构。
示例性地，图像处理中的形态学操作还可以包括膨胀、腐蚀、开操作以及闭操作 等。其中，膨胀是指使图像扩大，腐蚀是指使图像缩小。
示例性地，闭操作是先膨胀后腐蚀，即将目标主体图像先扩大后缩小，闭操作可以填充目标主体图像中的空洞。而开操作是先腐蚀后膨胀，即将目标主体图像先缩小后扩大，开操作可以将目标主体图像中的连接断开。
可选地，步骤130还可以包括：采用分水岭分割算法对预设方向的电芯主体图像中的边缘图像进行还原处理，得到第二电芯图像。
示例性地，分水岭(Watershed)是基于地理形态分析的图像分割算法，模仿地理结构(比如山川、沟壑、盆地等)来实现对不同物体的分类。分水岭分割算法的基本思想是把图像(例如电芯主体图像)看作是测地学上的拓扑地貌，图像中每一点像素的灰度值表示该点的海拔高度，每一个局部极小值及其影响区域称为集水盆，而集水盆的边界则形成分水岭。
示例性地，采用分水岭分割算法对电芯主体图像进行处理，其检测到的轮廓具有封闭性，方便后续操作，且检测具有高效率，可以提高第二电芯图像的准确度和清晰度。
示例性地，分水岭分割算法中，将电芯主体图像中的边缘图像的所有像素按照灰度值进行分类，并设定一个测地距离阈值。确定出其中灰度值最小的像素点，将灰度值从最小值开始增长，在增长的过程中，会碰到领域像素，测量领域像素到灰度值最低点的测地距离，如果小于测地距离阈值，则将该领域像素淹没，否则在该领域像素上设置大坝，完成对领域像素的分类。直到灰度值的最大值，所有区域都在分水岭线上相遇，大坝就对整个边缘图像进行了分区。可以使边缘图像的凹凸的曲线重新显示出来，提高电芯图像的清晰度和准确度。
基于同一申请构思，本申请实施例中还提供了与图像处理方法对应的图像处理装置，由于本申请实施例中的装置解决问题的原理与前述的图像处理方法实施例相似，因此本实施例中的装置的实施可以参见上述方法的实施例中的描述，重复之处不再赘述。
请参看图3，图3为本申请实施例提供的图像处理装置的功能模块示意图。本申请实施例提供一种图像处理装置200，图像处理装置200包括提取模块210、第一处理模块220和第二处理模块230。
提取模块210，用于基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像。
第一处理模块220，用于采用透视校正算法对电芯主体图像进行处理，获得预设方向的电芯主体图像。
第二处理模块230，用于对预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
可选地，图像处理装置200还包括移除模块240。
移除模块240，用于移除预设方向的电芯主体图像中的极耳。
可选地，图像处理装置200还可以包括图像提取模块250，图像提取模块250用于：
获取电芯的原始图像；
基于原始图像，提取出目标主体图像；以及
确定出目标主体图像的最大轮廓，得到第一电芯图像。
可选地，图像提取模块250还用于：
抑制原始图像的高光部分，获得二值图像；
采用阈值分割法对二值图像进行处理，提取出目标主体图像。
可选地，图像提取模块250还用于：
基于阈值分割法确定出分割阈值，并根据分割阈值进行对二值图像进行处理，提取出目标主体图像。
可选地，图像提取模块250还用于：
采用形态学操作对目标主体图像进行处理；其中，形态学操作包括开操作和闭操作。
可选地，第二处理模块230还用于：采用分水岭分割算法对预设方向的电芯主体图像中的边缘图像进行还原处理，得到第二电芯图像。
请参看图4，图4为本申请实施例提供的电子设备的方框示意图。本申请实施例对图像处理方法运行的电子设备进行介绍。电子设备300可以包括处理器310和存储器320。本领域普通技术人员可以理解，图4所示的结构仅为示意，其并不对电子设备300的结构造成限定。例如，电子设备300还可包括比图4中所示更多或者更少的组件，或者具有与图4所示不同的配置。
可选地，电子设备300可以是智能手机、个人电脑(personal computer，PC)、平板电脑、个人数字助理(personal digital assistant，PDA)、移动上网设备(mobile Internet device，MID)等。
上述的处理器310和存储器320相互之间直接或间接地电性连接，以实现数据的传输或交互。例如，这些元件相互之间可通过一条或多条通讯总线或信号线实现电性连接。上述的处理器310用于执行存储器中存储的可执行模块。
其中，存储器320可以是，但不限于，随机存取存储器(Random Access Memory，简称RAM)，只读存储器(Read Only Memory，简称ROM)，可编程只读存储器(Programmable Read-Only Memory，简称PROM)，可擦除只读存储器(Erasable Programmable Read-Only Memory，简称EPROM)，电可擦除只读存储器(Electric Erasable Programmable Read-Only Memory，简称EEPROM)等。其中，存储器320用于存储程序，所述处理器310在接收到执行指令后，执行所述程序，本申请实施例任一实施例揭示的过程定义的电子设备300所执行的方法可以应用于处理器310中，或者由处理器310实现。
上述的处理器310可能是一种集成电路芯片，具有信号的处理能力。上述的处理器310可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(digital signal processor，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
本实施例中的电子设备300可以用于执行本申请实施例提供的各个方法中的各个步骤。
此外，本申请实施例还提供一种计算机可读存储介质，该计算机可读存储介质上存储有计算机程序，该计算机程序被处理器运行时执行上述方法任一方法的步骤。
本申请实施例所提供的图像处理方法的计算机程序产品，包括存储了程序代码的计算机可读存储介质，所述程序代码包括的指令可用于执行上述方法实施例中所述的图像处理方法的步骤，具体可参见上述方法实施例，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的装置和方法，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和框图显示了根据本申请的多个实施例的装置、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，所述模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是， 框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
另外，在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。
所述功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。需要说明的是，在本文中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括……”限定的要素，并不排除在包括所述要素的过程、方法、物品或者设备中还存在另外的相同要素。
以上所述仅为本申请的优选实施例而已，并不用于限制本申请，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。应注意到：相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。
以上所述仅为本申请的实施例而已，并不用于限制本申请的保护范围，对于本领域的技术人员来说，本申请可以有各种更改和变化。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (10)

  1. 一种图像处理方法，其特征在于，所述方法包括：
    基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像；
    采用透视校正算法对所述电芯主体图像进行处理，得到预设方向的电芯主体图像；以及
    对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
  2. 根据权利要求1所述的方法，其特征在于，所述采用透视校正算法对所述电芯主体图像进行处理，得到预设方向的电芯主体图像之后，所述方法还包括：移除所述预设方向的电芯主体图像中的极耳。
  3. 根据权利要求1所述的方法，其特征在于，所述基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像之前，所述方法还包括：
    获取电芯的原始图像；
    基于所述原始图像，提取出目标主体图像；以及
    确定出所述目标主体图像的最大轮廓，得到第一电芯图像。
  4. 根据权利要求3所述的方法，其特征在于，所述基于所述原始图像，提取出目标主体图像，包括：
    抑制所述原始图像的高光部分，获得二值图像；
    采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像。
  5. 根据权利要求4所述的方法，其特征在于，所述采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像，包括：
    基于阈值分割法确定出分割阈值，并根据所述分割阈值进行对所述二值图像进行处理，提取出所述目标主体图像。
  6. 根据权利要求4所述的方法，其特征在于，在所述采用阈值分割法对所述二值图像进行处理，提取出所述目标主体图像之后，所述方法还包括：
    采用形态学操作对所述目标主体图像进行处理；其中，所述形态学操作包括开操作和闭操作。
  7. 根据权利要求1所述的方法，其特征在于，所述对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像，包括：
    采用分水岭分割算法对所述预设方向的电芯主体图像中的边缘图像进行还原处理， 得到第二电芯图像。
  8. 一种图像处理装置，其特征在于，所述装置包括：
    提取模块，用于基于轮廓外接多边形函数对所获取的第一电芯图像提取电芯主体图像；
    第一处理模块，用于采用透视校正算法对所述电芯主体图像进行处理，获得预设方向的电芯主体图像；以及
    第二处理模块，用于对所述预设方向的电芯主体图像的边缘图像进行处理，得到第二电芯图像。
  9. 一种电子设备，其特征在于，所述电子设备包括存储器和处理器，所述存储器中存储有程序指令，所述处理器运行所述程序指令时，执行权利要求1-7中任一项所述方法中的步骤。
  10. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质中存储有计算机程序指令，所述计算机程序指令被一处理器运行时，执行权利要求1-7任一项所述方法中的步骤。
PCT/CN2022/140357 2022-03-29 2022-12-20 图像处理方法、装置、电子设备及存储介质 WO2023185118A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210323147.9A CN114638818B (zh) 2022-03-29 2022-03-29 图像处理方法、装置、电子设备及存储介质
CN202210323147.9 2022-03-29

Publications (1)

Publication Number Publication Date
WO2023185118A1 true WO2023185118A1 (zh) 2023-10-05

Family

ID=81952430

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/140357 WO2023185118A1 (zh) 2022-03-29 2022-12-20 图像处理方法、装置、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN114638818B (zh)
WO (1) WO2023185118A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117911419A (zh) * 2024-03-20 2024-04-19 东北大学 中厚板转钢角度增强检测方法及装置、介质、设备
CN118231739A (zh) * 2024-05-14 2024-06-21 苏州时代华景新能源有限公司 一种电芯包膜工艺控制方法及系统

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114638818B (zh) * 2022-03-29 2023-11-03 广东利元亨智能装备股份有限公司 图像处理方法、装置、电子设备及存储介质
CN116912188B (zh) * 2023-07-06 2024-07-09 钛玛科（北京）工业科技有限公司 锂电池边界帽孔的提取方法、装置、设备及存储介质
CN118229675A (zh) * 2024-05-21 2024-06-21 宁德时代新能源科技股份有限公司 电芯检测方法及系统

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110414502A (zh) * 2019-08-02 2019-11-05 泰康保险集团股份有限公司 图像处理方法及装置、电子设备和计算机可读介质
CN111986159A (zh) * 2020-07-24 2020-11-24 苏州威华智能装备有限公司 太阳能电池片的电极缺陷检测方法、设备及存储介质
CN113313677A (zh) * 2021-05-17 2021-08-27 武汉工程大学 一种卷绕锂电池x光图像的质量检测方法
US20220027657A1 (en) * 2020-07-24 2022-01-27 Beihang University Image object detection method, device, electronic device and computer readable medium
CN114638818A (zh) * 2022-03-29 2022-06-17 广东利元亨智能装备股份有限公司 图像处理方法、装置、电子设备及存储介质

Family Cites Families (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110570442A (zh) * 2019-09-19 2019-12-13 厦门市美亚柏科信息股份有限公司 一种复杂背景下轮廓检测方法、终端设备及存储介质
CN110827308A (zh) * 2019-11-05 2020-02-21 中国医学科学院肿瘤医院 图像处理方法，装置，电子设备及存储介质
CN110827301B (zh) * 2019-11-11 2023-09-26 京东科技控股股份有限公司 用于处理图像的方法和装置
CN111402264B (zh) * 2020-03-11 2024-05-24 南京三百云信息科技有限公司 图像区域分割方法、装置及其模型训练方法及计算机设备
CN113160257B (zh) * 2021-04-23 2024-01-16 深圳市优必选科技股份有限公司 图像数据标注方法、装置、电子设备及存储介质
CN113376177A (zh) * 2021-06-21 2021-09-10 上海商汤科技开发有限公司 极耳检测方法、装置及电子设备
CN113390351B (zh) * 2021-08-17 2021-12-14 苏州高视半导体技术有限公司 电芯顶侧封封装质量检测方法、电子设备及存储介质
CN113393463B (zh) * 2021-08-18 2021-12-14 苏州高视半导体技术有限公司 软包电池卷芯检测入壳方法
CN113989232B (zh) * 2021-10-28 2022-12-16 广东利元亨智能装备股份有限公司 电芯缺陷检测方法、装置、电子设备和存储介质
CN114219770A (zh) * 2021-11-26 2022-03-22 深圳市优必选科技股份有限公司 地面检测方法、装置、电子设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110414502A (zh) * 2019-08-02 2019-11-05 泰康保险集团股份有限公司 图像处理方法及装置、电子设备和计算机可读介质
CN111986159A (zh) * 2020-07-24 2020-11-24 苏州威华智能装备有限公司 太阳能电池片的电极缺陷检测方法、设备及存储介质
US20220027657A1 (en) * 2020-07-24 2022-01-27 Beihang University Image object detection method, device, electronic device and computer readable medium
CN113313677A (zh) * 2021-05-17 2021-08-27 武汉工程大学 一种卷绕锂电池x光图像的质量检测方法
CN114638818A (zh) * 2022-03-29 2022-06-17 广东利元亨智能装备股份有限公司 图像处理方法、装置、电子设备及存储介质

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117911419A (zh) * 2024-03-20 2024-04-19 东北大学 中厚板转钢角度增强检测方法及装置、介质、设备
CN118231739A (zh) * 2024-05-14 2024-06-21 苏州时代华景新能源有限公司 一种电芯包膜工艺控制方法及系统

Also Published As

Publication number Publication date
CN114638818B (zh) 2023-11-03
CN114638818A (zh) 2022-06-17

Similar Documents

Publication Publication Date Title
WO2023185118A1 (zh) 图像处理方法、装置、电子设备及存储介质
US10970844B2 (en) Image segmentation method and device, computer device and non-volatile storage medium
CN112800915B (zh) 建筑物变化检测方法、装置、电子设备以及存储介质
WO2021212913A1 (zh) 一种图像分割方法、装置、设备及介质
Bai et al. Splitting touching cells based on concave points and ellipse fitting
CN109919002B (zh) 黄色禁停线识别方法、装置、计算机设备及存储介质
CN114359932B (zh) 文本检测方法、文本识别方法及装置
CN114677565B (zh) 特征提取网络的训练方法和图像处理方法、装置
CN112989995B (zh) 文本检测方法、装置及电子设备
CN111680690A (zh) 一种文字识别方法及装置
US9269017B2 (en) Cascaded object detection
CN111310759A (zh) 双模式协作的目标检测抑制优化方法及设备
CN110148136A (zh) 一种绝缘子图像分割方法、装置与计算机可读存储介质
CN111368865B (zh) 遥感影像储油罐检测方法、装置、可读存储介质及设备
CN110751156A (zh) 用于表格线大块干扰去除方法、系统、设备及介质
CN113012088A (zh) 一种电路板故障检测及孪生网络的训练方法、装置和设备
CN113902899A (zh) 训练方法、目标检测方法、装置、电子设备以及存储介质
CN117557777A (zh) 一种样本图像确定方法、装置、电子设备以及存储介质
Jerripothula et al. QCCE: Quality constrained co-saliency estimation for common object detection
Li et al. Transition region-based single-object image segmentation
CN115482436B (zh) 图像筛选模型的训练方法、装置以及图像筛选方法
CN111382760B (zh) 图片类别的识别方法、装置及计算机可读存储介质
CN116385415A (zh) 一种边缘缺陷检测方法、装置、设备及存储介质
CN114511862B (zh) 表格识别方法、装置及电子设备
CN114298992B (zh) 一种视频帧去重方法、装置、电子设备及存储介质

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: 22934934

Country of ref document: EP

Kind code of ref document: A1