AOI automatic optical inspection instrument calibration method and system

Abstract

The present invention relates to the field of optical inspection technology, specifically to an AOI automatic optical inspection instrument calibration method and system, comprising the following steps: obtaining a standard color plate RGB reflectance reference, collecting measured values to calculate offset comparisons, extracting image brightness to generate correction ratios, converting grayscale to extract mutations and filter anomalies, analyzing brightness trends to generate trimming records, and formulating rule-matching correction output comparison tables. In the present invention, the accuracy and reliability of image detection are enhanced by detailed analysis and precise correction of color offsets and brightness differences. The solution combines real-time light source data with image information to effectively identify subtle changes and reduce the error rate. By comprehensively analyzing light intensity offsets and regional brightness trends, the accuracy of grayscale and color correction is improved, ensuring the efficiency and quality of high-density circuit detection. This meticulous calibration mechanism significantly reduces detection errors, especially in high-precision environments, and optimizes product quality control and the stability of the production process.

Description

Technical Field

[0001] The present invention relates to the field of optical detection technology, and in particular to an AOI automatic optical inspection instrument calibration method and system. Background Art

[0002] The field of optical inspection technology involves using optical equipment to analyze and determine the conformity of inspected objects. This field is widely used in multiple industries, including integrated circuits, electronic components, and printed circuit boards. Optical inspection technology typically uses cameras, sensors, and optical elements to illuminate and image the surface of an object, capturing reflected light intensity data and comparing it with a standard feature image to determine whether the object is defective. With the improvement of industrial manufacturing precision, especially in the production of integrated circuits and components, optical inspection technology has gradually replaced traditional manual inspection and become a key technology for improving production efficiency and quality.

[0003] The AOI automated optical inspection (AOI) calibration method refers to a calibration method for AOI automated optical inspection (AOI) systems. In actual inspection operations, existing technologies only perform periodic standardized calibration for pixel resolution, dimensional indication, overall color recognition, grayscale, and brightness uniformity. Each parameter is calibrated independently, lacking in-depth analysis of subtle changes in channel response and regional brightness differences. Local differences between the actual scene in the inspection image and the standard calibration environment are ignored, making it difficult for the inspection equipment to dynamically adjust the color, grayscale, and brightness deviations of local areas. In particular, during the inspection of high-precision components such as high-density, fine-line integrated circuits, subtle color and brightness differences can easily make grayscale mutations at solder joints and pathway intersections difficult to effectively distinguish, resulting in local misjudgments and missed detections. This reduces the accuracy and consistency of product inspections, exposes overall quality control to a high risk of false detections, and seriously affects the stability of inspection results and production efficiency. Summary of the Invention

[0004] The purpose of the present invention is to solve the shortcomings of the prior art and to propose an AOI automatic optical inspection instrument calibration method and system.

[0005] In order to achieve the above object, the present invention adopts the following technical solution: an AOI automatic optical inspection instrument calibration method, comprising the following steps:

[0006] S1: Obtain the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, collect the reflected light intensity data of the spectral sensor in the key areas, calculate the difference between the measured value of the band and the reference value, and perform average processing to generate a reflection offset comparison value group;

[0007] S2: Based on the reflection offset reference value group, extract the brightness values of the three channels in the detection image, compare the measured brightness with the corresponding reference values, calculate the overall change amplitude, and generate a channel response correction ratio;

[0008] S3: Based on the channel response correction ratio, grayscale conversion is performed on the corrected image, the grayscale distribution of the intersection area of the solder joint and the via is extracted, the brightness mutation section is separated and the difference with the overall brightness is calculated, the area outside the judgment range is screened, and a list of grayscale change areas is generated;

[0009] S4: Based on the image grayscale change area list, extract the light wavelength and brightness data, compare the regional grayscale with the light source brightness, summarize the brightness change trend and record the average amplitude, and generate a brightness adjustment record table;

[0010] S5: Based on the brightness adjustment record table, formulate color and grayscale comparison rules, apply them to detector calibration control, perform image area matching and correction operations, and generate a detection image calibration comparison table.

[0011] As a further solution of the present invention, the reflection offset control value group includes red band deviation, green band deviation, and blue band deviation; the channel response correction ratio includes color change amplitude, channel brightness correction coefficient, and overall response adjustment value; the grayscale change area list includes solder point abnormal area, path intersection abnormal area, and brightness mutation abnormal area; the brightness modification record table includes light wavelength change trend, regional average brightness deviation, and light source brightness comparison data; the detection image calibration control table includes color matching rules, grayscale correction rules, and regional data calibration rules.

[0012] As a further solution of the present invention, the specific steps of S1 are:

[0013] S101: Obtaining the reflected light intensity reference values of the standard color plate in the red, green, and blue bands, respectively collecting the reflected light intensity values of the standard color plate under the illumination conditions of the corresponding light sources in the three bands, performing channel differentiation on the light intensity data of the bands, establishing a three-channel reference data set, and generating a three-channel reflection reference value;

[0014] S102: Based on the three-channel reflection reference values, collect the reflected light intensity data of the spectral sensor in the integrated circuit pad layer, metal interconnect layer and via port area, perform subtraction processing on the measured values of the bands and the corresponding reference values, obtain the light intensity difference of each sampling point in the red, green and blue bands, and obtain a three-channel reflection difference value set;

[0015] S103: calling the three-channel reflection difference value set, averaging the differences of all sampling points in the red, green and blue bands respectively, combining the three-channel average results as the overall reflection offset index, and obtaining a reflection offset reference value group.

[0016] As a further solution of the present invention, the specific steps of S2 are:

[0017] S201: Based on the reflection offset reference value group, obtain channel brightness values in the detection image, extract the channel brightness of corresponding pixels in the chip area, pair them with the same band data in the reflection offset reference value group, establish a correspondence between channel brightness and offset value, and generate a channel brightness acquisition data group;

[0018] S202: Based on the channel brightness acquisition data group, performing a difference calculation between the brightness of each channel and the corresponding offset value, summing up the channel difference data and calculating the average change value to obtain the overall brightness difference of the channel and obtain the brightness change amplitude values of the three channels;

[0019] S203: Calculate the ratio of the channel brightness change to the original brightness based on the brightness change amplitude values of the three channels, convert the ratio uniformly to construct a basis for channel brightness adjustment, and generate a channel response correction ratio.

[0020] As a further solution of the present invention, the specific calculation formula for calculating the ratio of the channel brightness change to the original brightness is:

[0021] ;

[0022] in, Represents the ratio of channel brightness change to original brightness, Representative The brightness value of each channel, Representative The brightness value of the reference channel, Represents the total number of channel brightness data points, Represents the maximum value of the channel brightness.

[0023] As a further solution of the present invention, the specific steps of S3 are:

[0024] S301: Obtain the channel response correction ratio, perform grayscale conversion on the corrected image, extract image pixel values of the solder joint area and the path intersection area, convert the three-channel brightness values into corresponding grayscale values according to the grayscale conversion formula in the image, and group all grayscale values in the solder joint area and the intersection area into independent grayscale data sets according to the image coordinate position to generate a regional grayscale distribution set;

[0025] S302: Based on the regional grayscale distribution set, the image is divided into continuous grayscale segments according to the column and row order. The difference between the grayscale average value of each segment and the average value of the adjacent segments is compared to detect continuous segments with a grayscale mutation threshold. The adjacent mutation segments are merged according to the threshold range to generate brightness mutation segment intervals.

[0026] S303: Call the brightness mutation segment interval, calculate the difference between the grayscale value of each mutation segment and the average grayscale value of the entire image, filter out segments with differences greater than the grayscale judgment threshold, and output the image area index group with significant grayscale differences according to the screening results to generate a grayscale change area list.

[0027] As a further solution of the present invention, the specific steps of S4 are:

[0028] S401: Obtaining an image acquisition timestamp for each area in the grayscale change area list, acquiring light source wavelength data and brightness data corresponding to the acquisition time point, and aggregating the wavelength values and brightness values of the same area at different time points in chronological order to form a combination of illumination data for each grayscale abnormal area, and generating a regional illumination information combination value;

[0029] S402: Based on the regional illumination information combination value, extract the grayscale value of each region and the brightness value of the light source at the corresponding time point, calculate the difference between the two, and classify and arrange them by wavelength type to obtain the comparative relationship between grayscale and brightness at different wavelengths, and generate a regional grayscale brightness change relationship group;

[0030] S403: Based on the regional grayscale brightness change relationship group, the grayscale and brightness differences in each wavelength group are summarized, the average amplitude of the differences in the same group is calculated, and all grouped average values are correspondingly integrated with the regional information, and imported into a unified data table structure to generate a brightness adjustment record table.

[0031] As a further solution of the present invention, the specific calculation formula for the light source wavelength data and brightness data corresponding to the acquisition time point is:

[0032] ;

[0033] Calculate the lighting combination and generate the regional lighting information combination value;

[0034] in, Represents at a point in time and between, area and region The combined value of lighting data, Represents at a point in time and The corresponding collection The difference in wavelength data, and Represents the time points and The corresponding collection Brightness data, Representative The time interval corresponding to the time period, Represents the number of wavelength data points involved in the calculation, summation symbol Indicates the cumulative calculation of all wavelength data points.

[0035] As a further solution of the present invention, the specific steps of S5 are:

[0036] S501: Based on the brightness trimming record table and the channel response correction ratio, extract the channel response value and the brightness trimming value of the image area, perform combination processing and classify according to the channel comparison rule, establish the color and brightness relationship corresponding to the area, and generate a color grayscale matching relationship group;

[0037] S502: Calling the color grayscale matching relationship group and the grayscale change area list, extracting the channel brightness and grayscale mutation range of the area to be calibrated, performing comparisons based on the corresponding relationships, screening areas that meet the conditions, and obtaining a regional channel comparison result group;

[0038] S503: Match the color and grayscale combination of the area to be calibrated according to the area channel comparison result group and the brightness adjustment value in the brightness modification record table, determine the correction number and replace the corresponding data, and obtain the detection image calibration comparison table.

[0039] AOI automatic optical inspection instrument calibration system, including:

[0040] The reflection acquisition and analysis module obtains the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, collects the reflected light intensity data of the spectral sensor at the pad layer, metal interconnect layer, and via port, calculates the difference between the measured value and the reference value, averages the difference in each band, integrates the band average offset, and generates a reflection offset comparison value group;

[0041] The channel brightness correction module extracts the red, green, and blue channel brightness values in the image based on the reflection offset reference value group, compares the measured brightness with the reference value, calculates the channel brightness difference and the overall change amplitude, converts it into a ratio form, and generates a channel response correction ratio;

[0042] The image grayscale recognition module performs grayscale conversion on the image according to the channel response correction ratio, extracts the grayscale distribution at the intersection of the solder joint and the path, compares the grayscale of the segment with the overall mean, determines whether the grayscale difference of the mutation segment exceeds the range, filters out abnormal segments, and generates a list of grayscale change areas;

[0043] The brightness trend extraction module calls the grayscale change area list, collects the light wavelength and light source brightness of the abnormal area during the corresponding period, compares the grayscale value with the light source brightness, classifies the change trend, calculates the average change amplitude, and generates a brightness adjustment record table;

[0044] The regional matching calibration module calls the brightness modification record table, grayscale change area list and channel response correction ratio, extracts the channel brightness and grayscale values of the area to be calibrated, determines the correction rule index according to the correction ratio and adjustment record, performs regional matching and adjustment, and generates a detection image calibration comparison table.

[0045] Compared with the prior art, the advantages and positive effects of the present invention are:

[0046] In this invention, the accuracy and reliability of image detection are enhanced through detailed analysis and precise correction of color offset and brightness differences. This solution combines real-time light source data and image information to effectively identify subtle changes and reduce the false positive rate. By comprehensively analyzing light intensity offset and regional brightness trends, the accuracy of grayscale and color correction is improved, ensuring the efficiency and quality of high-density circuit detection. This meticulous calibration mechanism significantly reduces detection errors, especially in high-precision environments, and optimizes product quality control and the stability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of the steps of the present invention

[0048] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0050] In the description of the present invention, it should be understood that the terms "length," "width," "up," "down," "front," "back," "left," "right," "vertical," "horizontal," "top," "bottom," "inside," "outside," and the like, indicating positions or relationships, are based on the positions or relationships shown in the accompanying drawings and are intended only to facilitate the description of the present invention and simplify the description. They do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limiting the present invention. Furthermore, in the description of the present invention, "plurality" means two or more, unless otherwise expressly and specifically defined.

[0051] See also Figure 1 , AOI automatic optical inspection instrument calibration method, including the following steps:

[0052] S1: Obtain the reflected light intensity reference values of the standard color plate in the red, green, and blue bands, collect the reflected light intensity data of the spectral sensor in the key area of the integrated circuit, calculate the difference between the measured value and the reference value in each band, and average the band errors to generate a reflection offset comparison value group;

[0053] S2: Based on the reflection offset reference value group, extract the brightness values of the three channels in the test image, compare the measured brightness with the corresponding reference values, calculate the overall change amplitude, and generate the channel response correction ratio;

[0054] S3: Based on the channel response correction ratio, grayscale conversion is performed on the corrected image to extract the grayscale distribution of the intersection area of the solder joint and the via. The brightness mutation segment is separated and the difference between the brightness mutation segment and the overall brightness is calculated. The area outside the judgment range is filtered out to generate a list of grayscale change areas.

[0055] S4: Based on the grayscale change area list, extract the light wavelength and brightness data at the time of acquisition, compare the grayscale of each area with the brightness of the light source at the corresponding time point, classify the change trend, record the average change amplitude, and generate a brightness adjustment record table;

[0056] S5: Based on the brightness modification record table, combined with the channel response correction ratio and the image grayscale change area list, a color and grayscale comparison rule is established and applied to the detector calibration control. Area matching and data correction are performed on the image to generate a detection image calibration comparison table.

[0057] The reflection offset control value group includes the red band deviation, green band deviation, and blue band deviation. The channel response correction ratio includes the color change amplitude, channel brightness correction coefficient, and overall response adjustment value. The grayscale change area list includes the abnormal solder joint area, the abnormal path intersection area, and the abnormal brightness mutation area. The brightness modification record table includes the light wavelength change trend, regional average brightness deviation, and light source brightness comparison data. The detection image calibration control table includes color matching rules, grayscale correction rules, and regional data calibration rules.

[0058] The specific steps of S1 are:

[0059] S101: Obtaining the reflected light intensity reference values of the standard color plate in the red, green, and blue bands, respectively collecting the reflected light intensity values of the standard color plate under the illumination conditions of the corresponding light sources in the three bands, performing channel differentiation on the light intensity data of the bands, establishing a three-channel reference data set, and generating a three-channel reflection reference value;

[0060] To obtain the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, it is necessary to select a standard color plate with uniform surface color and stable reflective performance as the collection object. Combined with the commonly used light source for integrated circuit detection, it is irradiated in different bands in the experimental environment. The wavelength of the light source is set to 625nm, 530nm, and 470nm, corresponding to the red, green, and blue channels respectively. In each band, a spectral sensor is used to record the reflected light intensity data of multiple positions of the standard color plate, ensuring that the illumination angle is vertically 90 degrees to avoid interference introduced by changes in the incident angle. During collection, the brightness of the light source needs to be controlled within 1000 lux. The sensor is used to continuously collect data from multiple points in the same band to ensure representativeness. For example, 5 points are collected in the red channel, and the reflectance values are 2.1, 2.0, 2.2, 2.1, and 2.1. mW / cm², calculate the average value of this set of data as the benchmark light intensity value for the red channel, and repeat the same process for the other two channels. The collected values are classified into channel attributes respectively. After the channel information is annotated, a three-channel data set is constructed. Each set of data contains the band identifier, sampling point location and reflection value. The average value of the reflection data in each channel is used as the reflection intensity benchmark of the channel under the standard color plate, and they are named as the red channel benchmark value, green channel benchmark value and blue channel benchmark value respectively, forming the three-channel reflection benchmark value.

[0061] S102: Based on the three-channel reflection reference values, collect the reflected light intensity data of the spectral sensor in the integrated circuit pad layer, metal interconnect layer and via port area, perform subtraction processing on the measured values of the bands and the corresponding reference values, obtain the light intensity difference of each sampling point in the red, green and blue bands, and obtain a three-channel reflection difference value set;

[0062] Based on the three-channel reflection reference value, during the integrated circuit image acquisition process, three areas, namely the pad layer, metal interconnection layer and via port, are selected as detection targets. An equal number of sampling points are arranged in these areas, and the lighting conditions are kept consistent. The reflected light intensity data of each point is collected in turn under the three light source conditions. The sensor records the actual reflection value under the current light source and compares it with the three-channel reference value established in the early stage. The difference between the actual reflection and the standard value of each point in the red, green and blue channels is calculated. Each difference and its corresponding channel and point information are recorded to form a complete sampling point reflection difference detailed data. All difference data are classified and grouped according to channels, and integrated into a data set containing spatial position, channel information and difference content, namely the three-channel reflection difference set.

[0063] S103: calling the three-channel reflection difference value set, averaging the differences of all sampling points in the red, green, and blue bands, combining the three-channel average results as the overall reflection offset index, and obtaining a reflection offset reference value group;

[0064] The three-channel reflection difference set is called to aggregate the reflection differences of all points collected in each band. The data of the red, green, and blue bands are summarized by channel respectively. The average difference level of all sampling points in each channel is counted as the overall offset performance of the channel in the target area. For example, the red channel counts the reflection differences of 10 points to obtain the average difference value. The same statistical process is repeated for the green and blue channels. The average differences of the three channels are combined to form a complete overall offset expression structure of the reflected light intensity. This combined data can be used as the basis for subsequent color correction and channel brightness trimming. The results are uniformly named as the reflection offset control value group.

[0065] The specific steps of S2 are:

[0066] S201: Based on the reflection offset reference value group, obtain the channel brightness value in the detection image, extract the channel brightness of the corresponding pixel in the chip area, pair it with the same band data in the reflection offset reference value group, establish the corresponding relationship between the channel brightness and the offset value, and generate a channel brightness acquisition data group;

[0067] Based on the reflectance offset reference value set, the first step is to extract the brightness values for each channel in the test image and determine the pixel data for the target chip area. This process uses image processing tools to extract the image's RGB channel brightness values (or brightness data in other color spaces) and select relevant pixels within the chip area for analysis. For example, after selecting a region in the test image and obtaining its brightness data, suppose a pixel has RGB brightness values of 255, 240, and 230. These values are then compared with the data for the same band in the reflectance offset reference value set. During this comparison, the brightness data for each band is individually matched with the offset data in the reflectance offset reference value set. This data set then establishes a correspondence between channel brightness and offset values. The key to this process lies in accurately extracting the brightness of each channel in the image and accurately comparing and matching them to generate the channel brightness acquisition data set used for subsequent calculations.

[0068] S202: Based on the channel brightness acquisition data group, calculate the difference between the brightness of each channel and the corresponding offset value, summarize the channel difference data and calculate the average change value to obtain the overall brightness difference of the channel and obtain the brightness change amplitude values of the three channels;

[0069] After obtaining the channel brightness acquisition data set, the next task is to calculate the difference between each channel's brightness and its corresponding offset value. This difference can be calculated by comparing each channel's brightness data with its corresponding offset value. For example, the red channel's brightness data may be presented as several sets of values, while the corresponding offset value is another set. For each set of brightness and offset values, the difference between them is calculated. By summing up all the difference data, an average change in brightness for each channel can be obtained. Assuming that the calculated difference values for the red channel are within a fixed range, these differences are ultimately aggregated into an average change value, which represents the degree of brightness variation of the red channel throughout the entire acquisition data. A similar calculation method is applied to the brightness difference values of the green and blue channels to determine the brightness variation of each channel. Combining the calculated results for all channels further derives the overall brightness difference value of the image.

[0070] S203: Calculate the ratio of the channel brightness change to the original brightness based on the brightness change amplitude values of the three channels, convert the ratio uniformly to construct a basis for channel brightness adjustment, and generate a channel response correction ratio;

[0071] The specific formula for calculating the ratio of channel brightness change to original brightness is:

[0072] ;

[0073] in, Represents the ratio of channel brightness change to original brightness, Representative The brightness value of each channel, Representative The brightness value of the reference channel, Represents the total number of channel brightness data points, Represents the maximum value of the channel brightness;

[0074] In this formula, This value represents the ratio of the channel brightness change to the original brightness. It is used to evaluate the relative effectiveness of channel brightness correction. The values of all parameters are obtained through data monitoring or acquisition and are linked to the performance indicators of the actual device.

[0075] Indicates the The actual brightness values of each channel are obtained by a brightness sensor or image processing device. In practice, brightness values may be obtained by reading image data from a sensor and converting it into numerical values. For example, the brightness distribution of an image under lighting equipment is collected, with a value range of 0 to 255.

[0076] It is obtained by comparing with a set of standard or original reference images. For example, if the brightness of the standard image channel used for comparison is .

[0077] Indicates the amount of channel data to be compared. In this example, assume that there are data points, that is, the brightness of the five channels is compared.

[0078] This value is determined by the brightness sensor's specifications, and its maximum value is 255, indicating the maximum limit of image brightness.

[0079] Through the collected data, assume that we have the following actual brightness value data (unit: brightness value): - Luminance value of the reference channel: ;

[0080] First, calculate the absolute sum of the brightness differences:

[0081] ;

[0082] ;

[0083] Then, calculate the sum of the squared brightness:

[0084] ;

[0085] ;

[0086] ;

[0087] ;

[0088] Calculate the square root of the denominator:

[0089] ;

[0090] Finally, plug in these calculation results:

[0091] ;

[0092] The results show that the ratio of channel brightness change to original brightness is about 0.0255, or 2.55%. This ratio reflects the difference between the actual brightness value and the reference brightness value, and is normalized by the maximum brightness.

[0093] The specific steps of S3 are:

[0094] S301: Obtain channel response correction ratios, perform grayscale conversion on the corrected image, extract image pixel values from the solder joint area and the path intersection area, convert the three-channel brightness values into corresponding grayscale values based on the grayscale conversion formula in the image, and aggregate all grayscale values in the solder joint area and the intersection area into independent grayscale data sets according to image coordinate positions to generate a regional grayscale distribution set;

[0095] In practical image processing applications, the image's channel response correction ratio is first obtained and used to perform grayscale conversion. Specifically, for each pixel, the image's three channel values (red, green, and blue) are converted to a single grayscale value using a standard weighted grayscale conversion formula. For example, if the red, green, and blue channel values of a pixel in an image are 120, 200, and 150, respectively, the corresponding grayscale value can be calculated. This process effectively unifies the image's brightness information, laying the foundation for subsequent processing steps. Next, by extracting pixel values at the intersection of the solder joint and the via and grouping these grayscale values, a dataset is generated that contains the grayscale distribution of these areas. For example, if the grayscale values of the solder joint area are relatively uniform and prominent, the grayscale data will be concentrated within a certain range, facilitating subsequent analysis. In this way, the image's grayscale information is accurately extracted, providing the necessary basic data support for subsequent image processing.

[0096] S302: Based on the regional grayscale distribution set, the image is divided into continuous grayscale segments according to the column and row order. The difference between the grayscale average value of each segment and the average value of the adjacent segments is compared to detect continuous segments with a grayscale mutation threshold. The boundaries of adjacent mutation segments are merged according to the threshold range to generate brightness mutation segment intervals.

[0097] Based on the regional grayscale distribution set, each image region is divided into several continuous grayscale segments. First, the average grayscale value of each segment must be calculated. For example, if the grayscale values of a column of pixels in an image are a series of data, the average of these data can be calculated to obtain the average grayscale value of the column. After calculating the average value for each region, the system compares the average values of adjacent grayscale segments. If the difference exceeds the set grayscale mutation threshold, a region with significant brightness mutation is identified. If the brightness variation between certain grayscale segments is too large (for example, a grayscale value change of more than 10), the system automatically marks these regions as having brightness mutations. Next, if the differences between multiple adjacent mutation segments are small, the boundaries are merged to form a single region, which helps identify more significant brightness mutations.

[0098] S303: Calling the brightness mutation segment interval, calculating the difference between the grayscale value of each mutation segment and the average grayscale value of the entire image, screening the segments with the difference greater than the grayscale judgment threshold, and outputting the image region index group with significant grayscale difference based on the screening results to generate a grayscale change region list;

[0099] After obtaining the brightness mutation segments, the system will further process the grayscale value of each mutation segment and calculate the difference with the average grayscale value of the entire image. If the difference exceeds the set grayscale judgment threshold (for example, the threshold is set to 5), the mutation segment is considered to have a significant grayscale difference and requires further analysis. Through this process, the system can filter out those areas with significant grayscale differences from the entire image. For example, if the grayscale value of a mutation area is 135 and the average grayscale value of the entire image is 120, then their difference is 15, which is greater than the set difference threshold of 5, so the area will be marked as an area with significant grayscale changes. Through this judgment process, the system ultimately generates a list of grayscale change areas to help further analyze and process the image in detail.

[0100] The specific steps of S4 are:

[0101] S401: Obtain the image acquisition timestamp of each area in the grayscale change area list, acquire the light source wavelength data and brightness data corresponding to the acquisition time point, and aggregate the wavelength values and brightness values of the same area at the different time points in chronological order to form a combination of illumination data for each grayscale abnormal area, and generate a regional illumination information combination value;

[0102] The specific calculation formula for the light source wavelength data and brightness data corresponding to the acquisition time point is:

[0103] ;

[0104] Calculate the lighting combination and generate the regional lighting information combination value;

[0105] in, Represents at a point in time and between, area and region The combined value of lighting data, Represents at a point in time and The corresponding collection The difference in wavelength data, and Represents the time points and The corresponding collection Brightness data, Representative The time interval corresponding to the time period, Represents the number of wavelength data points involved in the calculation, summation symbol Indicates the cumulative calculation of all wavelength data points;

[0106] Parameter definition and acquisition method:

[0107] By comparing the wavelength changes and brightness data of the light source at two time points, the changes in the lighting characteristics of the area can be reflected.

[0108] The calculation method is:

[0109]

[0110] in, and Time points and Moment Wavelength measurement. Wavelength data is obtained by taking multiple measurements of the same area at different time points using a spectrometer. The unit of measurement is nanometers (nm).

[0111] The calculation method is:

[0112] ;

[0113] in, and Time points and The timestamp is in seconds. The timestamp is obtained during image acquisition using a high-precision clock.

[0114] and The unit of measurement is lux (lx), which is obtained by measuring the same area at different time points using a camera or photometer.

[0115] It is determined according to the experimental design and the required spectral resolution, and the value range is generally between 1 and 100.

[0116] Formula calculation derivation process:

[0117] Assume that at time and Three wavelengths were collected ( ), the specific steps are as follows:

[0118] Calculate wavelength difference :

[0119] For example, at time point and The collected wavelength data are:

[0120] For wavelength , , , then the wavelength difference is:

[0121] ;

[0122] For wavelength , , , then the wavelength difference is:

[0123] ;

[0124] For wavelength , , , then the wavelength difference is:

[0125] ;

[0126] Calculating time intervals :

[0127] Assumed time point and The timestamps are:

[0128] ;

[0129] ;

[0130] The time interval is then calculated as:

[0131] ;

[0132] Calculate the sum of squares of the brightness data:

[0133] Assume that at time and The collected brightness data is as follows:

[0134] For wavelength , , ;

[0135] For wavelength , , ;

[0136] For wavelength , , ;

[0137] The sum of squares of each wavelength data is calculated as:

[0138] ;

[0139] ;

[0140] ;

[0141] Calculate the numerator and denominator:

[0142] The numerator is calculated as:

[0143] ;

[0144] The denominator is calculated as:

[0145] ;

[0146] Calculate the combined value of lighting data :

[0147] Lighting data combination value Calculated as:

[0148] ;

[0149] The significance of the calculation results:

[0150] Represents at a point in time and between, area and region The combined value of the illumination data. This value reflects the combined effect of the wavelength change and brightness change of the light source between two time points. A higher combined value indicates that the illumination characteristics of the area have changed significantly during this period.

[0151] S402: Based on the combined value of regional illumination information, extract the grayscale value of each region and the brightness value of the light source at the corresponding time point, calculate the difference between the two, and classify and arrange them by wavelength type to obtain the comparative relationship between grayscale and brightness at different wavelengths, and generate a regional grayscale brightness change relationship group;

[0152] Based on the extracted regional illumination information, the next step is to extract the grayscale value of each region and calculate the difference between it and the corresponding light source brightness value at that point in time. The grayscale value reflects the brightness change of the surface or object in the region, while the light source brightness value records the ambient light intensity at that moment. For example, at one moment, the grayscale value of a region is 150, corresponding to a light source brightness of 2000 lux. At another moment, the grayscale value of the region changes to 160, and the light source brightness increases to 2200 lux. The difference between the two changes can be calculated: a grayscale difference of 10 and a brightness difference of 200. This method can assess the trend of regional grayscale value changes with illumination at different time points or under different light source conditions. Next, this data is categorized and organized according to different wavelengths of light sources, such as 450nm, 550nm, and 650nm, which represent different light source conditions. This classification allows the relationship between grayscale and brightness changes at different wavelengths to be determined. This provides basic data for subsequent comparative analysis of grayscale and brightness changes, helping to understand the impact of different wavelength light sources on image grayscale.

[0153] S403: Based on the regional grayscale brightness change relationship group, the grayscale and brightness differences in each wavelength group are summarized, the average amplitude of the differences in the same group is calculated, and all the grouped average values are correspondingly integrated with the regional information and imported into a unified data table structure to generate a brightness adjustment record table;

[0154] Based on the regional grayscale and brightness variation relationship groups, the next step is to summarize the grayscale and brightness differences within each wavelength group and calculate the average magnitude of the differences within the group. First, the difference data for each wavelength group must be summarized, grouped together, and the average of these differences calculated. For example, if the grayscale and brightness difference data for multiple regions within a certain wavelength range is as follows: grayscale differences of 10, 12, and 9, and brightness differences of 200, 180, and 220, respectively, these differences can be summarized to calculate the average difference value for that wavelength group. The resulting results will display the average regional grayscale and brightness differences at different wavelengths. These results are combined with the regional information to form a complete brightness adjustment record. By summarizing the grayscale and brightness differences for each wavelength group, this table provides a basis for subsequent lighting adjustments, further improving product quality control accuracy.

[0155] The specific steps of S5 are:

[0156] S501: Based on the brightness trimming record table and the channel response correction ratio, extract the channel response value and the brightness trimming value of the image area, perform combination processing and classify according to the channel comparison rule, establish the color and brightness relationship corresponding to the area, and generate a color grayscale matching relationship group;

[0157] First, we need to obtain a brightness trimming record table, which includes brightness trimming parameters for different image areas. The channel response correction ratio reflects the color response characteristics of the image area in different channels. For each area, there is a corresponding channel response correction value and brightness trimming value. These correction values can be used to obtain the color response of the actual image area. Next, the image area is classified according to the channel comparison rules. The channel comparison rules can be distinguished according to the range of the response correction ratio. For example, if the red channel response correction ratio of a certain area is 1.1 and the green channel response correction ratio is 0.9, then the area may belong to a specific category. Through the changes in these ratios, the color and brightness relationship corresponding to the area is established. Finally, through these relationships, a color grayscale matching relationship group is generated, which can be used in subsequent image calibration to achieve precise brightness adjustment of the target area.

[0158] S502: Calling the color grayscale matching relationship group and the grayscale change area list, extracting the channel brightness and grayscale mutation range of the area to be calibrated, performing comparisons based on the corresponding relationships, screening the areas that meet the conditions, and obtaining the area channel comparison result group;

[0159] First, a color grayscale matching relationship group is extracted, which includes a predefined relationship model between channel response and grayscale change. The grayscale change region list contains grayscale mutations in each region of the image. Grayscale mutation refers to a sharp change in brightness within a certain area of the image, which occurs at the edge or texture of an object. For each area to be calibrated, the channel brightness and grayscale mutation range of that area are extracted. For example, a region may have a sudden change in brightness from 80 to 160. This needs to be compared with the corresponding value in the color grayscale matching relationship group to determine whether it meets the matching conditions. The comparison process can be determined by simple rules: if the regional brightness coincides with the grayscale range in the matching relationship group, the region is considered to meet the conditions. Based on these comparison results, the qualified regions are screened, and the final regional channel comparison result group is obtained, which provides reference data for subsequent color calibration.

[0160] S503: Match the color and grayscale combination of the area to be calibrated according to the regional channel comparison result group and the brightness adjustment value in the brightness modification record table, determine the correction number and replace the corresponding data, and obtain the detection image calibration comparison table;

[0161] First, it is necessary to combine the regional channel comparison result group with the brightness adjustment value in the brightness modification record table. The brightness modification record table provides brightness correction parameters for different image areas. These parameters include the adjusted brightness value and the corresponding correction coefficient. According to the channel comparison results, the color and grayscale combination of the area to be calibrated can be matched with the brightness adjustment value to ensure that the brightness correction during the calibration process meets expectations. If the color and grayscale combination of a certain area matches a certain brightness adjustment value, the correction number of the area is the number of the brightness adjustment value. For example, assuming that the red channel brightness of a certain area is 120, the green channel brightness is 130, and the blue channel brightness is 110, the most appropriate brightness adjustment value is found through comparison and corresponds to the area. Finally, the obtained detection image calibration comparison table contains the correction number of each area and replaces the color and brightness information in the original data to obtain the calibrated image data.

[0162] See also Figure 2 , AOI automatic optical inspection instrument calibration system, including:

[0163] The reflection acquisition and analysis module obtains the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, collects the reflected light intensity data of the spectral sensor at the pad layer, metal interconnect layer, and via port, calculates the difference between the measured value and the reference value, averages the difference in each band, integrates the band average offset, and generates a reflection offset comparison value group;

[0164] The channel brightness correction module extracts the red, green, and blue channel brightness values in the image based on the reflection offset reference value group, compares the measured brightness with the reference value, calculates the channel brightness difference and the overall change amplitude, converts it into a ratio form, and generates a channel response correction ratio;

[0165] The image grayscale recognition module converts the image grayscale according to the channel response correction ratio, extracts the grayscale distribution at the intersection of the solder joint and the path, compares the grayscale of the segment with the overall mean, determines whether the grayscale difference of the mutation segment exceeds the range, filters out abnormal segments, and generates a list of grayscale change areas;

[0166] The brightness trend extraction module calls the grayscale change area list, collects the light wavelength and light source brightness of the corresponding period in the abnormal area, compares the grayscale value with the light source brightness, classifies the change trend, calculates the average change amplitude, and generates a brightness adjustment record table;

[0167] The area matching calibration module calls the brightness modification record table, grayscale change area list and channel response correction ratio, extracts the channel brightness and grayscale values of the area to be calibrated, determines the correction rule index based on the correction ratio and adjustment record, performs area matching and adjustment, and generates a detection image calibration comparison table.

[0168] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. AOI automatic optical inspection instrument calibration method, characterized in that, The following steps are involved: S1: Obtain the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, collect the reflected light intensity data of the spectral sensor in the key areas, calculate the difference between the measured value of the band and the reference value, and perform average processing to generate a reflection offset comparison value group; S2: Based on the reflection offset reference value group, extract the brightness values of the three channels in the detection image, compare the measured brightness with the corresponding reference values, calculate the overall change amplitude, and generate a channel response correction ratio; S3: Based on the channel response correction ratio, grayscale conversion is performed on the corrected image, the grayscale distribution of the intersection area of the solder joint and the via is extracted, the brightness mutation section is separated and the difference with the overall brightness is calculated, the area outside the judgment range is screened, and a list of grayscale change areas is generated; S4: Based on the grayscale change area list, extract the light wavelength and brightness data, compare the regional grayscale with the light source brightness, summarize the brightness change trend and record the average amplitude, and generate a brightness adjustment record table; S5: Based on the brightness adjustment record table, formulate color and grayscale comparison rules, apply them to detector calibration control, perform image area matching and correction operations, and generate a detection image calibration execution comparison table; The specific steps of S4 are: S401: Obtaining an image acquisition timestamp for each area in the grayscale change area list, acquiring light source wavelength data and brightness data corresponding to the acquisition time point, and aggregating the wavelength values and brightness values of the same area at different time points in chronological order to form a combination of illumination data for each grayscale abnormal area, and generating a regional illumination information combination value; S402: Based on the regional illumination information combination value, extract the grayscale value of each region and the brightness value of the light source at the corresponding time point, calculate the difference between the two, and classify and arrange them by wavelength type to obtain the comparative relationship between grayscale and brightness at different wavelengths, and generate a regional grayscale brightness change relationship group; S403: Summarizing the grayscale and brightness differences in each wavelength group based on the regional grayscale and brightness change relationship group, calculating the average amplitude of the differences in the same group, integrating all grouped average values with the regional information, and importing them into a unified data table structure to generate a brightness adjustment record table; The specific calculation formula for the light source wavelength data and brightness data corresponding to the acquisition time point is: ； Calculate the lighting combination and generate the regional lighting information combination value; in, Represents at a point in time and between, area and region The combined value of lighting data, Represents at a point in time and The corresponding collection The difference in wavelength data, and Represents the time points and The corresponding collection Brightness data, Representative The time interval corresponding to the time period, Represents the number of wavelength data points involved in the calculation, summation symbol Indicates the cumulative calculation of all wavelength data points.

2. The AOI automatic optical inspection instrument calibration method according to claim 1, characterized in that: The reflection offset control value group includes red band deviation, green band deviation, and blue band deviation; the channel response correction ratio includes color change amplitude, channel brightness correction coefficient, and overall response adjustment value; the grayscale change area list includes solder joint abnormal area, path intersection abnormal area, and brightness mutation abnormal area; the brightness modification record table includes light wavelength change trend, regional average brightness deviation, and light source brightness comparison data; the detection image calibration execution comparison table includes color matching rules, grayscale correction rules, and regional data calibration rules.

3. The AOI automatic optical inspection instrument calibration method according to claim 1, characterized in that: The specific steps of S1 are: S101: Obtaining the reflected light intensity reference values of the standard color plate in the red, green, and blue bands, respectively collecting the reflected light intensity values of the standard color plate under the illumination conditions of the corresponding light sources in the three bands, performing channel differentiation on the light intensity data of the bands, establishing a three-channel reference data set, and generating a three-channel reflection reference value; S102: Based on the three-channel reflection reference values, collect the reflected light intensity data of the spectral sensor in the integrated circuit pad layer, metal interconnect layer and via port area, perform subtraction processing on the measured values of the bands and the corresponding reference values, obtain the light intensity difference of each sampling point in the red, green and blue bands, and obtain a three-channel reflection difference value set; S103: calling the three-channel reflection difference value set, averaging the differences of all sampling points in the red, green and blue bands respectively, combining the three-channel average results as the overall reflection offset index, and obtaining a reflection offset reference value group.

4. The AOI automatic optical inspection instrument calibration method according to claim 3, characterized in that: The specific steps of S2 are: S201: Based on the reflection offset reference value group, obtain channel brightness values in the detection image, extract the channel brightness of corresponding pixels in the chip area, pair them with the same band data in the reflection offset reference value group, establish a correspondence between channel brightness and offset value, and generate a channel brightness acquisition data group; S202: Based on the channel brightness acquisition data group, performing a difference calculation between the brightness of each channel and the corresponding offset value, summing up the channel difference data and calculating the average change value to obtain the overall brightness difference of the channel and obtain the brightness change amplitude values of the three channels; S203: Calculate the ratio of the channel brightness change to the original brightness based on the brightness change amplitude values of the three channels, convert the ratio uniformly to construct a basis for channel brightness adjustment, and generate a channel response correction ratio.

5. The AOI automatic optical inspection instrument calibration method according to claim 4, characterized in that: The specific calculation formula for the ratio of the channel brightness change to the original brightness is: ； in, Represents the ratio of channel brightness change to original brightness, Representative The brightness value of each channel, Representative The brightness value of the reference channel, Represents the total number of channel brightness data points, Represents the maximum value of the channel brightness.

6. The AOI automatic optical inspection instrument calibration method according to claim 4, characterized in that: The specific steps of S3 are: S301: Obtain the channel response correction ratio, perform grayscale conversion on the corrected image, extract image pixel values of the solder joint area and the path intersection area, convert the three-channel brightness values into corresponding grayscale values according to the grayscale conversion formula in the image, and group all grayscale values in the solder joint area and the intersection area into independent grayscale data sets according to the image coordinate position to generate a regional grayscale distribution set; S302: Based on the regional grayscale distribution set, the image is divided into continuous grayscale segments according to the column and row order. The difference between the grayscale average value of each segment and the average value of the adjacent segments is compared to detect continuous segments with a grayscale mutation threshold. The adjacent mutation segments are merged according to the threshold range to generate brightness mutation segment intervals. S303: Call the brightness mutation segment interval, calculate the difference between the grayscale value of each mutation segment and the average grayscale value of the entire image, filter out segments with differences greater than the grayscale judgment threshold, and output the image area index group with significant grayscale differences according to the screening results to generate a grayscale change area list.

7. The AOI automatic optical inspection instrument calibration method according to claim 1, characterized in that: The specific steps of S5 are: S501: Based on the brightness trimming record table and the channel response correction ratio, extract the channel response value and the brightness trimming value of the image area, perform combination processing and classify according to the channel comparison rule, establish the color and brightness relationship corresponding to the area, and generate a color grayscale matching relationship group; S502: Calling the color grayscale matching relationship group and the grayscale change area list, extracting the channel brightness and grayscale mutation range of the area to be calibrated, performing comparisons based on the corresponding relationships, screening areas that meet the conditions, and obtaining a regional channel comparison result group; S503: Match the color and grayscale combination of the area to be calibrated according to the area channel comparison result group and the brightness adjustment value in the brightness modification record table, determine the correction number and replace the corresponding data, and obtain the detection image calibration execution comparison table.

8. AOI automatic optical inspection instrument calibration system, characterized in that, The system is used to perform the AOI automatic optical inspection instrument calibration method according to any one of claims 1 to 7, and the system comprises: The reflection acquisition and analysis module obtains the reference values of the reflected light intensity of the standard color plate in the red, green, and blue bands, collects the reflected light intensity data of the spectral sensor at the pad layer, metal interconnect layer, and via port, calculates the difference between the measured value and the reference value, averages the difference in each band, integrates the band average offset, and generates a reflection offset comparison value group; The channel brightness correction module extracts the red, green, and blue channel brightness values in the image based on the reflection offset reference value group, compares the measured brightness with the reference value, calculates the channel brightness difference and the overall change amplitude, converts it into a ratio form, and generates a channel response correction ratio; The image grayscale recognition module performs grayscale conversion on the image according to the channel response correction ratio, extracts the grayscale distribution at the intersection of the solder joint and the path, compares the grayscale of the segment with the overall mean, determines whether the grayscale difference of the mutation segment exceeds the range, filters out abnormal segments, and generates a list of grayscale change areas; The brightness trend extraction module calls the grayscale change area list, collects the light wavelength and light source brightness of the abnormal area during the corresponding period, compares the grayscale value with the light source brightness, classifies the change trend, calculates the average change amplitude, and generates a brightness adjustment record table; The area matching calibration module calls the brightness modification record table, grayscale change area list and channel response correction ratio, extracts the channel brightness and grayscale values of the area to be calibrated, determines the correction rule index according to the correction ratio and adjustment record, performs area matching and adjustment, and generates a detection image calibration execution comparison table.

Images