Endoscope camera module product quality detection method, system and device

Abstract

The application discloses a product quality detection method, system and equipment applied to an endoscope camera module, and relates to the technical field of camera module quality detection. The method comprises the following steps: clamping a target endoscope camera module to a camera module test tool, and electrifying the target endoscope camera module, while clamping an image test card directly above the target endoscope camera module; controlling the camera module test tool to perform imaging detection operation on the target endoscope camera module through an upper computer, and receiving camera module detection imaging information based on a decoding board; performing signal filtering to obtain a usable camera module detection image, and transmitting the camera module detection image to the upper computer; performing imaging defect analysis to obtain camera module defect feature data; performing quality evaluation and judgment on the camera module defect feature data to obtain a camera module quality detection result. The technical problem of low endoscope camera module detection efficiency in the prior art is solved, and the technical effect of improving detection efficiency is achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of camera module quality detection, and particularly relates to a product quality detection method, system and device applied to an endoscope camera module. BACKGROUND

[0002] With the wide application of endoscope technology, the endoscope camera module as an important component of the endoscope equipment directly affects the clarity and accuracy of endoscope imaging. However, in the prior art, the quality detection method for the endoscope camera module mainly relies on manual detection or simple automatic detection means. Such detection methods have the following problems: on the one hand, manual detection is low in efficiency and is easily affected by subjective factors, resulting in instability of the detection results; on the other hand, the existing automatic detection system can only identify obvious defects and has insufficient detection capability for complex image quality problems (such as blurring, distortion, color deviation, etc.). SUMMARY

[0003] The present application provides a product quality detection method, system and device applied to an endoscope camera module, which solves the technical problem of low detection efficiency of the endoscope camera module in the prior art.

[0004] In view of the above problems, the present application provides a product quality detection method, system and device applied to an endoscope camera module.

[0005] In a first aspect of the present application, a product quality detection method applied to an endoscope camera module is provided, which comprises:

[0006] An image test card is clamped above the target endoscope camera module, and the target endoscope camera module is powered on. An imaging detection operation is performed on the target endoscope camera module by a camera module test tool controlled by an upper computer, and imaging information of the camera module is received based on a decoding board. Signal filtering is performed on the imaging information of the camera module based on the decoding board to obtain a usable camera module detection image, and the usable camera module detection image signal is transmitted to the upper computer. An image defect detection algorithm network is obtained by the upper computer, and imaging defect analysis is performed on the usable camera module detection image based on the image defect detection algorithm network to obtain camera module defect feature data. A product quality determinator is built, and quality evaluation and determination are performed on the camera module defect feature data based on the product quality determinator to obtain a camera module quality detection result.

[0007] In a second aspect of the present application, a product quality detection system applied to an endoscope camera module is provided, which comprises:

[0008] The installation module: obtains a camera module test tool, clamps a target endoscope camera module to the camera module test tool in a preset direction, powers on the target endoscope camera module, and clamps an image test card directly above the target endoscope camera module; the imaging detection module: controls the camera module test tool to perform an imaging detection operation on the target endoscope camera module through a host computer, and receives camera module detection imaging information based on a decoding board; the signal filtering module: performs signal filtering on the camera module detection imaging information based on the decoding board, obtains a usable camera module detection image, and transmits the camera module detection image signal to the host computer; the imaging defect analysis module: obtains an image defect detection algorithm network through the host computer, performs imaging defect analysis on the usable camera module detection image based on the image defect detection algorithm network, and obtains camera module defect feature data; and the quality evaluation module: builds a product quality determinator, performs quality evaluation and determination on the camera module defect feature data based on the product quality determinator, and obtains a camera module quality detection result.

[0009] In a third aspect, the present application provides an electronic device, comprising: a memory for storing executable instructions; and a processor for executing the executable instructions stored in the memory to implement the product quality detection method for an endoscope camera module.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] First, a camera module test tool is obtained, a target endoscope camera module is clamped to the camera module test tool in a preset direction, the target endoscope camera module is powered on, and an image test card is clamped directly above the target endoscope camera module. Then, the camera module test tool is controlled to perform an imaging detection operation on the target endoscope camera module through a host computer, and camera module detection imaging information is received based on a decoding board. Further, signal filtering is performed on the camera module detection imaging information based on the decoding board, a usable camera module detection image is obtained, and the camera module detection image signal is transmitted to the host computer. Then, an image defect detection algorithm network is obtained through the host computer, imaging defect analysis is performed on the usable camera module detection image based on the image defect detection algorithm network, and camera module defect feature data is obtained. Finally, a product quality determinator is built, quality evaluation and determination are performed on the camera module defect feature data based on the product quality determinator, and a camera module quality detection result is obtained. The technical problem of low detection efficiency of an endoscope camera module in the prior art is solved, and the technical effect of improving detection efficiency is achieved. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0013] Figure 1 The application provides an endoscope camera module product quality detection method and a system.

[0014] Figure 2 The application provides an endoscope camera module product quality detection method and a system.

[0015] Figure 3 The application provides an endoscope camera module product quality detection method and a system.

[0016] Figure 4 The application provides an endoscope camera module product quality detection method and a system.

[0017] Figure 5 The application provides an endoscope camera module product quality detection method and a system.

[0018] Figure 6 The application provides an endoscope camera module product quality detection method and a system.

[0019] The application provides an endoscope camera module product quality detection method and a system. DETAILED DESCRIPTION

[0020] The application provides an endoscope camera module product quality detection method and a system.

[0021] The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0022] It is to be understood that the terms "including", "comprising", "having" and "with" are meant to be interpreted inclusively and non-exclusively, that is, "including", "comprising", "having" and "with" should be interpreted as specifying the presence of stated features or steps but not precluding the presence of one or more other features or steps.

[0023] In one embodiment, as shown in FIG. 1, the present application provides a product quality detection method for an endoscope camera module, wherein the method comprises: Figure 1

[0024] Obtaining a camera module test tool, clamping the target endoscope camera module to the camera module test tool according to a preset direction, and powering on the target endoscope camera module, while clamping an image test card directly above the target endoscope camera module.

[0025] The camera module test tool is a device for detecting camera modules, which is used to fix the camera module and provide a stable test environment. First, the target endoscope camera module to be detected is installed on the camera module test tool according to a preset direction, wherein the preset direction refers to a correct installation angle or position specified according to the working state and design characteristics of the camera module, to ensure the accuracy and consistency of the detection data; then, the target endoscope camera module is powered on to enter the working state; at the same time, the image test card is installed directly above the target endoscope camera module and kept parallel to the optical axis of the camera module, to ensure that the image captured by the module can completely cover the content of the test card, wherein the image test card is a board card with standardized patterns, used to detect the imaging quality of the camera module. Through this standardized clamping and test preparation, detection errors caused by installation deviation or non-standard operation can be effectively avoided.

[0026] Further, as shown in FIG. 2, Figure 2 , Figure 3 , Figure 4 The camera module test tool comprises a module test seat 31, a rotating platform 32, an X-axis adjusting knob 33, a Y-axis adjusting knob 34, a Z-axis adjusting handwheel 35, and a first interface 36, a second interface 37 and a third interface 38.

[0027] ​The camera module test tool includes a module test seat 31, a rotating platform 32, an X-axis adjustment knob 33, a Y-axis adjustment knob 34, a Z-axis adjustment handwheel 35, and a first interface 36, a second interface 37, and a third interface 38; the module test seat 31 is used to fix the target endoscope camera module, ensuring its stability and reliability during the test process; the rotating platform 32 supports multi-axis angle adjustment of the camera module, facilitating alignment with the test target; the X-axis adjustment knob 33 and the Y-axis adjustment knob 34 respectively realize accurate fine adjustment of the camera module in the left-right (X-axis direction) and up-down (Y-axis direction), to ensure alignment with the center position of the test card; the Z-axis adjustment handwheel 35 is used to adjust the distance between the camera module and the test card, ensuring imaging clarity; the first interface 36 is a USB Type A interface, used to connect external devices such as power supply or host computer; the second interface 37 is a Thunderbolt interface (connecting the module test seat), used for signal and power connection with the camera module; the third interface 38 is a USB Type C interface (connecting the computer), used to transmit the test signals of the camera module to the host computer for processing and analysis.

[0028] Further, the clamping of the target endoscope camera module to the camera module test tool in the preset direction includes:

[0029] The target endoscope camera module is clamped and fixed to the module test seat in the preset direction, and the X-axis adjustment knob, the Y-axis adjustment knob, and the Z-axis adjustment handwheel are used to adjust the position of the target endoscope camera module; based on the rotating platform, the angle of the target endoscope camera module is adjusted according to the camera module test scene, and the first interface, the second interface, and the third interface are connected to external devices in sequence.

[0030] Specifically, first, the target endoscope camera module is clamped and fixed to the module test seat in the preset direction, ensuring the stable and reliable position of the camera module; then, the X-axis adjustment knob, the Y-axis adjustment knob, and the Z-axis adjustment handwheel are used to accurately adjust the position of the target endoscope camera module, to ensure that the center of the camera module is aligned with the test card or other target position in the test scene; after completing the position adjustment, the angle of the camera module is adjusted based on the test scene requirements of the camera module through the rotating platform, to ensure that the viewing angle of the camera module matches the requirements of the test scene; at the same time, the first interface (USB Type A interface), the second interface (Thunderbolt interface), and the third interface (USB Type C interface) are connected to external devices in sequence, to realize power supply, signal transmission, and data processing support of the host computer for the camera module. Through this clamping and adjustment process, the test accuracy and stability of the endoscope camera module are ensured, laying a foundation for subsequent quality detection.

[0031] The imaging detection operation of the target endoscope camera module is performed by the camera module test tool controlled by the host computer, and the camera module detection imaging information is received based on the decoding board.

[0032] The host computer is a computer or a master control device, which is the control core of the entire test process; the decoding board is used to receive and process the raw imaging information transmitted by the camera module. The imaging data captured by the camera module (usually transmitted in the form of digital signals) is transmitted to the decoding board through the interface.

[0033] The imaging detection operation of the target endoscope camera module is performed by the camera module test tool controlled by the host computer, and the camera module detection imaging information is received based on the decoding board.

[0034] The imaging detection operation of the target endoscope camera module is performed by the camera module test tool controlled by the host computer, and the camera module detection imaging information is received based on the decoding board.

[0035] The decoding board extracts signals from the camera module detection imaging information, and applies various filtering algorithms (such as low-pass filtering, Gaussian filtering, or median filtering) to process the data in terms of noise, interference, and other factors affecting imaging quality, in order to remove high-frequency noise in the imaging signal, reduce background interference, and enhance the edge details of the image, thereby ensuring the clarity and accuracy of the signal. After filtering, the obtained image signal is converted into a usable camera module detection image, which has a good signal-to-noise ratio and high-quality imaging effect, and can reflect the real imaging performance of the camera module. Subsequently, the decoding board sends these usable detection image signals to the host computer through a standardized transmission interface (such as USB Type A or USB TypeC), ensuring the integrity and stability of the signal.

[0036] Further, the obtained usable camera module detection image includes:

[0037] The decoding board performs signal type recognition and signal decoding conversion on the camera module detection imaging information to obtain a camera module decoding detection image; performs color channel conversion and signal enhancement on the camera module decoding detection image to obtain a camera module enhanced detection image; performs noise recognition on the camera module enhanced detection image to obtain image multi-scale noise information; and performs filter processing on the camera module enhanced detection image based on the image multi-scale noise information to obtain a usable camera module detection image.

[0038] Specifically, the decoding board performs signal type recognition on the camera module detection imaging information, determines whether the signal is an analog signal or a digital signal by analyzing the transmission format of the signal, and decodes and converts the format of the signal based on the recognition result to convert the original imaging signal into a standardized image data format, thereby obtaining a camera module decoding detection image. Then, color channel conversion is performed on the decoded camera module detection image to convert the color space of the image from RGB format to YCbCr or HSV format suitable for subsequent processing, so as to optimize the color restoration effect of the image. At the same time, signal enhancement processing is performed on the image by adjusting parameters such as brightness, contrast and color saturation to obtain a camera module enhanced detection image. Next, noise information in the camera module enhanced detection image is recognized, and multi-scale noise features such as high-frequency noise, low-frequency interference and random noise in the image are extracted using a multi-scale analysis method to form image multi-scale noise information. Finally, filter processing is performed on the camera module enhanced detection image based on the extracted image multi-scale noise information, and algorithms such as Gaussian filter, adaptive median filter or bilateral filter are combined to gradually perform denoising operations on different types and scales of noise while retaining key details and edge information in the image, so as to finally obtain a usable camera module detection image with high signal-to-noise ratio and complete details, thereby providing high-quality data support for subsequent image defect detection and camera module quality evaluation.

[0039] Further, the obtaining of the usable camera module detection image comprises:

[0040] obtaining a filter algorithm list, matching the type characteristics of the image multi-scale noise information with the filter algorithm list respectively to obtain a multi-scale noise matching algorithm set, performing filter parameter analysis on the image multi-scale noise information based on the multi-scale noise matching algorithm set to obtain a multi-scale noise filter, and performing filter processing on the camera module enhanced detection image using the multi-scale noise filter to obtain the usable camera module detection image.

[0041] Specifically, a filter algorithm list containing multiple filter algorithms is obtained, the filter algorithm list contains filter algorithms designed for different types of noise, such as Gaussian filtering, adaptive median filtering, bilateral filtering, etc., for processing various noise types such as high-frequency noise, low-frequency interference, and random noise; based on the extracted image multi-scale noise information, the type characteristics of each noise (such as the spatial distribution, intensity, and frequency range of the noise) are analyzed, and these characteristics are matched one by one with the algorithms in the filter algorithm list, thereby generating a multi-scale noise matching algorithm set, in which each noise type corresponds to one or more suitable filter algorithms; based on the multi-scale noise matching algorithm set, the image multi-scale noise information is filtered and analyzed, specifically including determining the key filter parameters of each matching algorithm, such as filter window size, smoothing coefficient, or edge preservation intensity, to meet the processing needs of different noise characteristics, and through this process, multiple multi-scale noise filters are generated, each of which is optimized and configured for a specific noise type and characteristic; the generated multi-scale noise filters are used to filter and process the camera module enhanced detection image layer by layer, and in the processing process, each multi-scale noise filter only takes effect on its corresponding noise type, thereby achieving the hierarchical removal of high-frequency noise, low-frequency interference, and random noise, while trying to preserve the key details and edge information in the image, avoiding excessive smoothing or detail loss. Through the above process, the final available camera module detection image is obtained, which has a high signal-to-noise ratio and complete detail quality, providing high-reliability data support for subsequent defect detection and quality evaluation.

[0042] The host computer obtains an image defect detection algorithm network based on the image defect detection algorithm network, and analyzes the imaging defects of the available camera module detection image to obtain camera module defect feature data.

[0043] The host computer calls an image defect detection algorithm network from pre-loaded or external storage, which is usually based on deep learning or machine learning techniques, such as convolutional neural networks (CNN) or target detection-based algorithm models (such as YOLO, Faster R-CNN), and is specifically used to analyze the imaging defects of the camera module. The host computer inputs the available camera module detection image transmitted from the decoding board into the image defect detection algorithm network, which extracts features and analyzes patterns of the available camera module detection image to identify possible imaging defects, and outputs camera module defect feature data after the analysis, which includes defect types (such as blur, distortion, or color restoration abnormalities, etc.), defect locations (specific coordinates or area ranges of defects in the image), and defect degrees (severity of defects).

[0044] Further, the host computer obtains an image defect detection algorithm network, including:

[0045] According to the endoscope camera module application standard, an imaging defect label library of the camera module is constructed; a camera module defect image dataset is collected and acquired, type labeling is performed on the camera module defect image dataset based on the imaging defect label library of the camera module, and a camera module defect image sample set is obtained; an image defect detection requirement is acquired, and an image detection algorithm network structure is determined according to the image defect detection requirement; the image detection algorithm network structure is used to train and optimize the camera module defect image sample set, an image defect detection algorithm network is obtained, and the image defect detection algorithm network is stored to the upper computer.

[0046] Specifically, according to the endoscope camera module application standard (for example, an industry standard or an imaging quality requirement in a specific application scenario), an imaging defect label library of the camera module is constructed, which is used to define various imaging defect types that may exist in the camera module and their standardized descriptions, such as blur, color cast, distortion, dark corner, noise, or pixel dead point, and set standardized descriptions and classification rules for each defect type, including feature parameters, position markers, and severity classification; a large number of image datasets containing camera module defects are acquired through the collection of actual shooting images, the generation of simulated defect images, and the like; based on the constructed imaging defect label library of the camera module, type labeling is performed on the defect image dataset, and label information of defect types, defect region coordinates, and severity is added to each image, thereby forming a camera module defect image sample set and providing high-quality data support for subsequent algorithm training; according to the image defect detection requirement of the camera module, the defect types to be detected, the detection accuracy requirement, and the detection speed and other actual application scenario requirements are analyzed, and a suitable image detection algorithm network structure is selected or designed, which can adopt a mature deep learning model architecture (such as YOLO, Faster R-CNN, or a self-defined model based on a convolutional neural network) or be adjusted and optimized in combination with actual requirements; after the network structure is determined, the camera module defect image sample set is input into the network for multiple rounds of training and optimization. In the training stage, the weights of the network are optimized through large-scale image data in the sample set, and the recognition ability of the network for various imaging defects is improved; in the optimization stage, the learning rate is adjusted, the loss function is optimized, and data enhancement techniques are introduced, so as to further improve the detection accuracy and robustness of the network, and reduce the false positive rate and the false negative rate. Finally, the image defect detection algorithm network that has completed training and optimization is saved to the upper computer as a core tool for subsequent camera module defect detection tasks. Through the process, the obtained algorithm network has the ability to accurately detect imaging defects of the camera module, can quickly identify the defect types in the image, locate the defect region, and evaluate the defect degree, thereby providing efficient and reliable technical support for quality evaluation of the endoscope camera module.

[0047] Further, the obtained camera module defect feature data includes:

[0048] Based on the image defect detection algorithm network, the available camera module detection image is marked for defect recognition, the image defect detection algorithm network accurately identifies the defect types (such as blur, color deviation, distortion, dark corner, noise, etc.) in the image through feature analysis of the pixels in the image, and generates corresponding marked areas for each defect, forming a camera module defect area set and a camera module defect type set. The camera module defect area set defines the boundary range of all detected defects in the image, and the camera module defect type set classifies these defects; then, edge segmentation and integral calculation are performed on each defect area in the camera module defect area set. The purpose of edge segmentation is to extract the boundary line of each defect area through an algorithm (such as Canny edge detection or Sobel operator), to ensure the accurate outline of the defect area; integral calculation sums the areas of the pixel points in the defect area to obtain the defect area set of each defect, and the camera module defect area set contains the area sizes of all defect areas, which are used for subsequent quality evaluation; then, an image positioning coordinate system is constructed, taking the top left corner of the image as the origin to define a two-dimensional coordinate system of X and Y axes; based on the image positioning coordinate system, each defect area in the camera module defect area set is positioned, i.e. the center point coordinates, boundary vertex coordinates and other spatial position data of the defect area are calculated, forming a camera module defect area position set, which is used to determine the specific distribution position of each defect in the image; the camera module defect type set, the camera module defect area set and the camera module defect area position set obtained above are integrated to generate complete camera module defect feature data, which includes detailed information such as the type, area and position of each defect, providing comprehensive data support for the quality detection of the camera module, and can be used for subsequent quality judgment and optimization analysis.

[0049] Specifically, based on the image defect detection algorithm network, the available camera module detection image is marked for defect recognition, the image defect detection algorithm network accurately identifies the defect types (such as blur, color deviation, distortion, dark corner, noise, etc.) in the image through feature analysis of the pixels in the image, and generates corresponding marked areas for each defect, forming a camera module defect area set and a camera module defect type set. The camera module defect area set defines the boundary range of all detected defects in the image, and the camera module defect type set classifies these defects; then, edge segmentation and integral calculation are performed on each defect area in the camera module defect area set. The purpose of edge segmentation is to extract the boundary line of each defect area through an algorithm (such as Canny edge detection or Sobel operator), to ensure the accurate outline of the defect area; integral calculation sums the areas of the pixel points in the defect area to obtain the defect area set of each defect, and the camera module defect area set contains the area sizes of all defect areas, which are used for subsequent quality evaluation; then, an image positioning coordinate system is constructed, taking the top left corner of the image as the origin to define a two-dimensional coordinate system of X and Y axes; based on the image positioning coordinate system, each defect area in the camera module defect area set is positioned, i.e. the center point coordinates, boundary vertex coordinates and other spatial position data of the defect area are calculated, forming a camera module defect area position set, which is used to determine the specific distribution position of each defect in the image; the camera module defect type set, the camera module defect area set and the camera module defect area position set obtained above are integrated to generate complete camera module defect feature data, which includes detailed information such as the type, area and position of each defect, providing comprehensive data support for the quality detection of the camera module, and can be used for subsequent quality judgment and optimization analysis.

[0050] A product quality determinator is built, and the camera module defect feature data is evaluated and determined for quality based on the product quality determinator to obtain a camera module quality detection result.

[0051] The product quality determinator is a rule-based evaluation tool for analyzing defect feature data; the camera module defect feature data is input into the product quality determinator for quality evaluation and determination, so as to determine whether the camera module meets the quality standard, and finally output the camera module quality detection result.

[0052] Further, the product quality determinator is built, comprising:

[0053] The product quality determination elements are obtained, including the camera module defect type set, the defect area, and the defect area position; a product quality determination coordinate system is constructed according to the product quality determination elements; the product quality determination coordinate system is divided into a qualified area based on the product qualification standard of the target endoscope camera module, and a qualified area logical line is obtained; and the product quality determinator is built based on the product quality determination coordinate system and the qualified area logical line.

[0054] Specifically, the product quality determination elements are obtained, including the defect type set, the defect area, and the defect area position of the camera module, which respectively describe the nature, size, and spatial distribution of the defects, and are the core indicators for quality determination; a product quality determination coordinate system is constructed according to the product quality determination elements, wherein the defect type is used as a classification dimension to distinguish different defect categories (such as blur, color deviation, distortion, etc.); the defect area is used as a size dimension to quantify the influence range of the defect; and the defect area position is used as a spatial dimension to describe the distribution position of the defect in the image; through the combination of the three-dimensional data, a product quality determination coordinate system is established which can comprehensively describe the defect feature of the camera module.

[0055] According to the product qualification standard of the target endoscope camera module, the product quality determination coordinate system is divided into a qualified area. Specifically, the allowed defect types, the maximum threshold of the defect area, and the limitation conditions of the defect position in the qualification standard are analyzed, and the qualified area logical line in the coordinate system is drawn using these standards to divide the coordinate system into a qualified area and an unqualified area. For example, some minor defects (such as edge noise) may fall into the qualified area, while serious defects (such as blur or color deviation in the center area of the image) will fall into the unqualified area. Finally, based on the product quality determination coordinate system and the qualified area logical line, the product quality determinator is built, which can automatically analyze the defect feature data of the camera module. In specific implementation, the defect feature data (defect type, area, and position) is mapped into the product quality determination coordinate system, and the determination result is quickly obtained by judging whether the data point is located in the qualified area. At the same time, the determinator can output the determination basis, including the defect exceeding type, the unqualified position, and other information, to realize efficient evaluation and intuitive feedback of the camera module product quality.

[0056] To sum up, the embodiments of the present application have at least the following technical effects:

[0057] First, the camera module test tool is obtained, the target endoscope camera module is clamped to the camera module test tool in a preset direction, the target endoscope camera module is powered on, and an image test card is clamped directly above the target endoscope camera module. Then, the camera module test tool is controlled by the upper computer to perform imaging detection on the target endoscope camera module, and the camera module detection imaging information is received based on the decoding board. Further, the camera module detection imaging information is signal filtered based on the decoding board to obtain a usable camera module detection image, and the usable camera module detection image signal is transmitted to the upper computer. Then, the image defect detection algorithm network is obtained by the upper computer, the imaging defect analysis of the usable camera module detection image is performed based on the image defect detection algorithm network, and camera module defect feature data is obtained. Finally, a product quality determinator is built, the quality evaluation and determination of the camera module defect feature data are performed based on the product quality determinator, and a camera module quality detection result is obtained. The technical problem of low detection efficiency of the endoscope camera module in the prior art is solved, and the technical effect of improving the detection efficiency is achieved.

[0058] Embodiment two, based on the same inventive concept as the product quality detection method applied to the endoscope camera module in the foregoing embodiments, as shown in Figure 5 The present application provides a product quality detection system applied to an endoscope camera module, wherein the system comprises:

[0059] The installation module 11 obtains a camera module test tool, clamps a target endoscope camera module to the camera module test tool in a preset direction, and powers on the target endoscope camera module, while clamping an image test card directly above the target endoscope camera module. The imaging detection module 12 controls the camera module test tool to perform imaging detection on the target endoscope camera module by the upper computer, and receives camera module detection imaging information based on the decoding board. The signal filtering module 13 performs signal filtering on the camera module detection imaging information based on the decoding board to obtain a usable camera module detection image, and transmits the usable camera module detection image signal to the upper computer. The imaging defect analysis module 14 obtains an image defect detection algorithm network by the upper computer, performs imaging defect analysis on the usable camera module detection image based on the image defect detection algorithm network, and obtains camera module defect feature data. The quality evaluation module 15 builds a product quality determinator, performs quality evaluation and determination on the camera module defect feature data based on the product quality determinator, and obtains a camera module quality detection result.

[0060] Further, the signal filtering module 13 is used to execute the following method:

[0061] The decoding board is used for signal type recognition and signal decoding conversion on the imaging information detected by the camera module to obtain a camera module decoding detection image; color channel conversion and signal enhancement are performed on the camera module decoding detection image to obtain a camera module enhanced detection image; noise recognition is performed on the camera module enhanced detection image to obtain image multi-scale noise information; and the camera module enhanced detection image is filtered based on the image multi-scale noise information to obtain a usable camera module detection image.

[0062] Further, the signal filtering module 13 is used to perform the following method:

[0063] A filtering algorithm list is obtained, the type characteristics of the image multi-scale noise information are matched with the filtering algorithm list respectively to obtain a multi-scale noise matching algorithm set; the image multi-scale noise information is filtered based on the multi-scale noise matching algorithm set respectively to obtain a multi-scale noise filter; and the camera module enhanced detection image is filtered using the multi-scale noise filter to obtain the usable camera module detection image.

[0064] Further, the imaging defect analysis module 14 is used to perform the following method:

[0065] An imaging defect label library of the camera module is constructed according to an endoscope camera module application standard; a camera module defect image data set is collected, the camera module defect image data set is type-labeled based on the imaging defect label library of the camera module to obtain a camera module defect image sample set; an image defect detection requirement is obtained, an image detection algorithm network structure is determined according to the image defect detection requirement; the camera module defect image sample set is trained and optimized using the image detection algorithm network structure to obtain an image defect detection algorithm network and store the image defect detection algorithm network to the upper computer.

[0066] Further, the imaging defect analysis module 14 is used to perform the following method:

[0067] Defect recognition marking is performed on the usable camera module detection image based on the image defect detection algorithm network to obtain a camera module defect region set and a camera module defect type set; edge segmentation and integral calculation are performed on the camera module defect region set respectively to obtain a camera module defect region area set; an image positioning coordinate system is constructed, and the camera module defect region set is sequentially positioned based on the image positioning coordinate system to obtain a camera module defect region position set; and the camera module defect feature data is obtained based on the camera module defect type set, the camera module defect region area set and the camera module defect region position set.

[0068] Further, the quality evaluation module 15 is configured to execute the following method:

[0069] Obtaining product quality judgment elements, the product quality judgment elements including a set of camera module defect types, defect area size, and defect area position; constructing a product quality judgment coordinate system according to the product quality judgment elements; performing qualified product area division on the product quality judgment coordinate system based on product qualification standards of the target endoscope camera module to obtain a qualified product area logical line; and building the product quality judgment device based on the product quality judgment coordinate system and the qualified product area logical line.

[0070] Further, the installation module 11 is configured to execute the following method:

[0071] The camera module test tool includes a module test seat, a rotating platform, X-axis adjustment knobs, Y-axis adjustment knobs, a Z-axis adjustment hand wheel, and a first interface, a second interface, and a third interface.

[0072] Further, the installation module 11 is configured to execute the following method:

[0073] The target endoscope camera module is clamped and fixed to the module test seat in the preset direction, and the X-axis adjustment knobs, the Y-axis adjustment knobs, and the Z-axis adjustment hand wheel are used to adjust the position of the target endoscope camera module; the rotating platform is used to adjust the angle of the target endoscope camera module according to a camera module test scene, and the first interface, the second interface, and the third interface are sequentially connected with external devices.

[0074] Embodiment Three, Figure 6 The structure of the electronic device provided in Embodiment Three of the present application is shown in a block diagram of an exemplary electronic device suitable for implementing the embodiments of the present application. Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functions and use range of the embodiments of the present application. As Figure 6 As shown, the electronic device includes a processor 21, a memory 22, an input device 23, and an output device 24; the number of processors 21 in the electronic device can be one or more, Figure 6 For example, the processor 21 in the electronic device, the memory 22, the input device 23, and the output device 24 can be connected through a bus or other means, Figure 6 For example, the connection through a bus.

[0075] It should be noted that the above-mentioned embodiment sequences of the present application are merely for description only, but not for representing the advantages and disadvantages of the embodiments. And the above-mentioned embodiments of the present specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0076] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0077] The specification and drawings are merely exemplary of the present application, and any and all modifications, variations, combinations or equivalents that are within the scope of the present application should be included. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A method for product quality detection applied to an endoscope camera module, characterized in that, The method comprises: An image pickup module test tool is acquired, a target endoscope image pickup module is clamped to the image pickup module test tool in a preset direction, the preset direction is a specified mounting angle or position according to the working state and design characteristics of the image pickup module, the target endoscope image pickup module is powered on, and an image test card is clamped directly above the target endoscope image pickup module; An imaging detection operation is performed on the target endoscope image pickup module by the image pickup module test tool under the control of a host computer, and image pickup module detection imaging information is received based on a decoding board; Signal filtering is performed on the image pickup module detection imaging information based on the decoding board to obtain a usable image pickup module detection image, and the usable image pickup module detection image signal is transmitted to the host computer; An image defect detection algorithm network is acquired by the host computer, imaging defect analysis is performed on the usable image pickup module detection image based on the image defect detection algorithm network, and image pickup module defect feature data is obtained; A product quality determinator is built, quality evaluation and determination are performed on the image pickup module defect feature data based on the product quality determinator, and image pickup module quality detection results are obtained; The usable image pickup module detection image is obtained by: Signal type recognition and signal decoding conversion are performed on the image pickup module detection imaging information based on the decoding board to obtain an image pickup module decoding detection image; Color channel conversion and signal enhancement are performed on the image pickup module decoding detection image to obtain an image pickup module enhanced detection image; Noise recognition is performed on the image pickup module enhanced detection image to obtain image multi-scale noise information; Filtering processing is performed on the image pickup module enhanced detection image based on the image multi-scale noise information to obtain a usable image pickup module detection image; The product quality determinator is built by: Product quality determination elements are acquired, the product quality determination elements comprise an image pickup module defect type set, a defect area size, and a defect area position; A product quality determination coordinate system is constructed according to the product quality determination elements; The product quality determination coordinate system is divided into a qualified product area based on a product qualification standard of the target endoscope image pickup module to obtain a qualified product area logical line; The product quality determinator is built based on the product quality determination coordinate system and the qualified product area logical line; The image pickup module test tool comprises a module test seat, a rotating platform, an X-axis adjusting knob, a Y-axis adjusting knob, a Z-axis adjusting handwheel, and a first interface, a second interface, and a third interface; The image pickup module defect feature data is obtained by: Defect recognition marking is performed on the usable image pickup module detection image based on the image defect detection algorithm network to obtain an image pickup module defect area set and an image pickup module defect type set; Edge segmentation and integral calculation are performed on the image pickup module defect area set respectively to obtain an image pickup module defect area size set; An image positioning coordinate system is constructed, and the image pickup module defect area set is sequentially positioned based on the image positioning coordinate system to obtain an image pickup module defect area position set; Obtain the camera module defect feature data based on the camera module defect type set, the camera module defect area set and the camera module defect area position set.

2. The method for detecting product quality applied to an endoscope camera module according to claim 1, wherein The available camera module detection image can be obtained by: Obtaining a filter algorithm list, and matching the type characteristics of the image multi-scale noise information with the filter algorithm list respectively to obtain a multi-scale noise matching algorithm set; Based on the multi-scale noise matching algorithm set, the image multi-scale noise information is filtered to obtain a multi-scale noise filter; The multi-scale noise filter is used to filter the camera module enhanced detection image to obtain the available camera module detection image. 3.The method for detecting product quality applied to an endoscope camera module according to claim 2, wherein, The image defect detection algorithm network is obtained by the host computer, including: According to the endoscope camera module application standard, a camera module imaging defect label library is constructed; A camera module defect image data set is collected, and the camera module defect image data set is type labeled based on the camera module imaging defect label library to obtain a camera module defect image sample set; An image defect detection requirement is obtained, and an image detection algorithm network structure is determined according to the image defect detection requirement; The camera module defect image sample set is trained and optimized using the image detection algorithm network structure to obtain an image defect detection algorithm network and store it to the host computer. 4.The method for detecting product quality applied to an endoscope camera module according to claim 1, wherein, The target endoscope camera module is clamped to the camera module test tool in a preset direction, including: The target endoscope camera module is clamped and fixed to the module test seat in the preset direction, and the position of the target endoscope camera module is adjusted using the X-axis adjusting knob, Y-axis adjusting knob and Z-axis adjusting hand wheel; Based on the rotating platform, the angle of the target endoscope camera module is adjusted according to the camera module test scene, and the first interface, second interface and third interface are connected with external devices in turn.

5. A product quality detection system applied to an endoscope camera module, characterized in that, The system for implementing the product quality detection method for the endoscope camera module according to any one of claims 1-4, the system comprising: An installation module: a camera module test tool is obtained, a target endoscope camera module is clamped to the camera module test tool in a preset direction, and the target endoscope camera module is powered on, and an image test card is clamped above the target endoscope camera module; An imaging detection module: the camera module test tool is controlled by the host computer to perform imaging detection operation on the target endoscope camera module, and the camera module detection imaging information is received based on the decoding board; A signal filtering module: based on the decoding board, the camera module detection imaging information is signal filtered to obtain an available camera module detection image, and the available camera module detection image signal is transmitted to the host computer; An imaging defect analysis module: an image defect detection algorithm network is obtained by the host computer, and imaging defect analysis is performed on the available camera module detection image based on the image defect detection algorithm network to obtain camera module defect feature data; The quality evaluation module is configured to build a product quality determinator, perform quality evaluation and determination on the camera module defect feature data based on the product quality determinator, and obtain a camera module quality detection result.

6. An electronic device, comprising: The electronic device includes: a memory configured to store executable instructions; a processor configured to execute the executable instructions stored in the memory to implement the product quality detection method for the endoscope camera module according to any one of claims 1-4.

Images