Sterilization indicator card spectral image analysis method and system

Abstract

The invention discloses a sterilization indicator card spectral image analysis method and system, belongs to the technical field of sterilization indicator card analysis, and aims to solve the problem of interference caused by superposition of weak light radiation and chromogenic reaction signals due to gas ionization in a low-temperature plasma sterilization process. Comprising the following steps: acquiring spectral image data in a sterilization cabin; acquiring environmental parameter data in the sterilization cabin, wherein the environmental parameter data comprises temperature data, humidity data, pressure data and electromagnetic field intensity data; generating a background interference signal based on the environmental parameter data and a pre-stored interference spectrum model; subtracting the background interference signal from the spectral image data to obtain a characteristic spectral signal; and analyzing the characteristic spectrum signal to determine the color development state of the sterilization indicator card to obtain an analysis result.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sterilization indicator card analysis, and particularly relates to a sterilization indicator card spectral image analysis method and system. BACKGROUND

[0002] In the process of low-temperature plasma sterilization (such as hydrogen peroxide plasma sterilization), due to the superimposed interference of weak light radiation generated by gas ionization in the sterilization cabin and the color reaction of the chemical indicator card, the traditional optical imaging equipment cannot accurately separate the characteristic spectrum of the indicator card from the background interference signal, resulting in a significant increase in color judgment error. For example, when the pressure fluctuation range in the sterilization cabin is 20-200 Pa, the humidity dynamically changes (30%-90%RH), and there is a high-frequency electromagnetic field (13.56 MHz), the conventional RGB image acquisition system will be interfered by the ultraviolet-blue light band (280-450 nm) radiation generated by the plasma, so that the color characteristic value (such as the absorbance of the 550-600 nm band) of the formaldehyde low-temperature indicator card is submerged by the ionization noise, causing the color analysis algorithm to misjudge the effective coloration as a substandard state.

[0003] The disclosure of the above background art content is only used to assist in understanding the concept and technical solutions of the present application, and it does not necessarily belong to the prior art of the present patent application. In the absence of explicit evidence that the above content has been disclosed on the filing date of the present patent application, the above background art should not be used to evaluate the novelty and inventiveness of the present application. SUMMARY

[0004] The present application provides a sterilization indicator card spectral image analysis method and system, which is used to solve the problem of superimposed interference of weak light radiation caused by gas ionization and color reaction signal in the process of low-temperature plasma sterilization.

[0005] To achieve the above purpose, the embodiments of the present application disclose the following technical solutions:

[0006] In a first aspect, the embodiments of the present application provide a sterilization indicator card spectral image analysis method, including the following steps:

[0007] Obtain spectral image data in the sterilization cabin;

[0008] Obtain environmental parameter data in the sterilization cabin, the environmental parameter data including temperature data, humidity data, pressure data and electromagnetic field intensity data;

[0009] Generate background interference signals based on the environmental parameter data and the pre-stored interference spectrum model;

[0010] Subtract the background interference signals from the spectral image data to obtain characteristic spectrum signals;

[0011] The characteristic spectral signal is analyzed to determine the color development state of the sterilization indicator card, and an analysis result is obtained.

[0012] In the embodiments of the present application, through the organic combination of spectral imaging and environmental parameter detection inside the sterilization cabin, the accurate recovery of the true signal of the color development reaction on the chemical indicator card is realized, thereby solving the problem of superimposed interference of weak light radiation and color development reaction signal caused by gas ionization in the low-temperature plasma sterilization process. Specifically, the multi-band spectral imaging equipment is used to collect the optical signal inside the sterilization cabin, and the analog-to-digital conversion forms digital spectral data, and then the temperature, humidity, pressure and electromagnetic field sensor are used to collect the environmental state data to form a structured data packet. The pre-calibrated interference response mathematical model corresponds the environmental information and the corresponding spectral response function, and directly calculates the weak light radiation interference caused by gas ionization inside the sterilization cabin. The mathematical expression realizes the accurate quantification of the environmental interference component through different function combinations. The constructed background interference signal is deducted from the spectral image data in a pixel-by-pixel manner, and the noise is further eliminated through median filtering, and finally only the effective spectral features accurately reflecting the color development reaction of the chemical indicator card are retained. In this way, the problem of superimposed interference of weak light radiation and color development reaction signal caused by gas ionization in the low-temperature plasma sterilization process is effectively solved.

[0013] In a second aspect, the embodiments of the present application provide a spectral image analysis system for a sterilization indicator card, comprising:

[0014] a spectral image acquisition module, configured to acquire spectral image data inside a sterilization cabin;

[0015] an environmental parameter monitoring module, configured to acquire environmental parameter data inside the sterilization cabin, wherein the environmental parameter data comprises temperature data, humidity data, pressure data and electromagnetic field intensity data;

[0016] an interference signal generation module, configured to generate a background interference signal based on the environmental parameter data and a pre-stored interference spectral model;

[0017] a signal processing module, configured to subtract the background interference signal from the spectral image data to obtain a characteristic spectral signal;

[0018] a color development state analysis module, configured to analyze the characteristic spectral signal to determine the color development state of the sterilization indicator card, and obtain an analysis result.

[0019] In a third aspect, the embodiments of the present application provide an electronic device, comprising one or more processors; a storage device having one or more programs stored thereon; and when the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of the first aspect.

[0020] In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the method according to any one of the first aspect.

[0021] In a fifth aspect, an embodiment of the present application provides a computer program product, and the computer program product includes a computer program. The computer program is executed by a processor to implement the method according to any one of the first aspect.

[0022] The technical effects brought by any one of the second aspect to the fifth aspect can refer to the technical effects brought by different design manners in the first aspect, and will not be described here. BRIEF DESCRIPTION OF DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained without creative labor on the basis of the provided drawings.

[0024] Figure 1 A flowchart of a sterilization indicator card spectral image analysis method provided by some embodiments of the present application;

[0025] Figure 2 A structural schematic diagram of a sterilization indicator card spectral image analysis system provided by some embodiments of the present application.

[0026] Figure 3 A structural schematic diagram of an electronic device suitable for implementing some embodiments of the present application. DETAILED DESCRIPTION

[0027] Specific embodiments of the present application will now be described in detail. Although the present application is described in conjunction with these specific embodiments, it is noted that the present application is not intended to be limited to these specific embodiments. On the contrary, the specific embodiments are intended to cover alternatives, modifications, and equivalents, which can be included within the spirit and scope of the present application as defined by the claims. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application can be practiced without some or all of these specific details.

[0028] The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0029] Summary of the application: In the process of low-temperature plasma sterilization (such as hydrogen peroxide plasma sterilization), due to the superimposed interference of weak light radiation generated by gas ionization in the sterilization cabin and the color reaction of the chemical indicator card, the traditional optical imaging equipment cannot accurately separate the characteristic spectrum of the indicator card from the background interference signal, resulting in a significant increase in color interpretation error. For example, when the pressure fluctuation range in the sterilization cabin is 20-200 Pa, the humidity dynamically changes (30%-90%RH), and there is a high-frequency electromagnetic field (13.56 MHz), the conventional RGB image acquisition system will be disturbed by the ultraviolet-blue light band (280-450 nm) radiation generated by the plasma, causing the color characteristic value (such as the absorbance of the 550-600 nm band) of the formaldehyde low-temperature indicator card to be overwhelmed by ionization noise, resulting in a false judgment of the color analysis algorithm that the effective coloration is not up to standard.

[0030] To solve the above technical problems, the technical scheme provided by the present application is as follows: a sterilization indicator card spectral image analysis method is provided, comprising the following steps: acquiring spectral image data in the sterilization cabin; acquiring environmental parameter data in the sterilization cabin, the environmental parameter data including temperature data, humidity data, pressure data and electromagnetic field intensity data; generating a background interference signal based on the environmental parameter data and a pre-stored interference spectrum model; subtracting the background interference signal from the spectral image data to obtain a characteristic spectrum signal; analyzing the characteristic spectrum signal to determine the coloration state of the sterilization indicator card, and obtaining an analysis result.

[0031] This method realizes the accurate recovery of the coloration reaction signal on the chemical indicator card by combining spectral imaging and environmental parameter detection inside the sterilization cabin, thereby solving the problem of superimposed interference of weak light radiation caused by gas ionization and coloration reaction signal in the process of low-temperature plasma sterilization. Specifically, a multi-band spectral imaging device is used to collect optical signals in the sterilization cabin, and after analog-to-digital conversion, digital spectral data is formed, and then temperature, humidity, pressure and electromagnetic field sensors are used to collect environmental state data to form a structured data package. The pre-calibrated interference response mathematical model corresponds the environmental information to the corresponding spectral response function, and directly calculates the weak light radiation interference caused by gas ionization in the sterilization cabin. The mathematical expression realizes the accurate quantification of environmental interference components through different function combinations. The constructed background interference signal is subtracted from the spectral image data in a pixel-by-pixel manner, and noise is further removed by median filtering, and finally only the effective spectral features accurately reflecting the coloration reaction of the chemical indicator card are retained. In this way, the problem of superimposed interference of weak light radiation caused by gas ionization and coloration reaction signal in the process of low-temperature plasma sterilization is effectively solved.

[0032] After introducing the basic principles of the present application, the various non-limiting embodiments of the present application will be specifically introduced in conjunction with the drawings of the specification. Please refer toFigure 1 The embodiment of the application provides a sterilization indicator card spectral image analysis method, comprising the following steps:

[0033] S101: acquiring spectral image data in a sterilization cabin;

[0034] Specifically, in some embodiments, the spectral image data in the sterilization cabin can be acquired through the following steps:

[0035] Firstly, the original optical signal of the sterilization cabin is collected by using a multi-band spectral imaging device;

[0036] Secondly, the original optical signal is converted into digital initial spectral data through analog-digital conversion;

[0037] Thirdly, according to a preset spectral band division rule, the digital initial spectral data is divided into at least three independent spectral channels according to the wavelength dimension, and is represented by a three-dimensional matrix , wherein , respectively, are spatial pixel coordinates, is a band number;

[0038] Fourthly, a spatial pixel calibration operation is performed on each spectral channel to eliminate optical distortion;

[0039] Specifically, in some embodiments, the spatial pixel calibration operation can be performed on each spectral channel to eliminate optical distortion through the following steps:

[0040] Firstly, the intrinsic calibration matrix and the extrinsic calibration matrix of the spectral camera are acquired;

[0041] Secondly, the optical distortion correction mapping function is constructed according to the intrinsic calibration matrix and the extrinsic calibration matrix;

[0042] Specifically, in the process of constructing the correction mapping function, the following formula is used to correct the original pixel coordinates , wherein and are horizontal and vertical pixel coordinates, the focal length and are the principal point coordinates are camera intrinsic parameters, the radial parameter is calculated as:

[0043]

[0044] Thirdly, the formula of the corrected pixel coordinates is calculated as:

[0045]

[0046] wherein are first, second, third radial distortion correction coefficients, respectively;

[0047] a fourth sub-step of calculating, for each original pixel coordinate grid of the spectral channel, a corresponding ideal non-distorted coordinate grid;

[0048] a fifth sub-step of resampling the spectral intensity values of the original pixel coordinate grid to the ideal non-distorted coordinate grid using a bilinear interpolation algorithm;

[0049] a sixth sub-step of performing an edge clipping operation on the resampled spectral channel to remove invalid boundary pixels;

[0050] a seventh sub-step of generating the calibrated spectral channel data and labeling the spatial coordinate metadata. This scheme uses the intrinsic and extrinsic parameters of the spectral imaging device to construct a mathematical mapping function, which accurately converts the spatial coordinates of each pixel in the original spectral data to the ideal coordinates in the non-distorted state, achieving the elimination of optical distortion. The elimination of optical distortion effectively reduces the pixel displacement error caused by distortion, thereby ensuring the accurate spatial alignment of multi-band spectral data. At the same time, after data resampling using bilinear interpolation and edge clipping of the image, spectral image data with high spatial consistency and uniformity is generated, providing a high-quality basis for subsequent image fusion and feature extraction. Finally, based on the accurate calibration of the data processing effect, the stability and accuracy of the spectral signal extraction process are enhanced, and the detection reliability and precision of the overall system are improved.

[0051] a fifth step of performing data fusion on the calibrated spectral channels to construct a three-dimensional spectral image data matrix;

[0052] a sixth step of storing the three-dimensional spectral image data matrix as the spectral image data within the sterilization chamber. This scheme uses a multi-band spectral imaging device to collect the original optical signals within the sterilization chamber, and uses high-precision analog-to-digital conversion to convert the analog optical signals into digital initial spectral data. At the same time, the pre-set spectral band division rule divides the initial data into multiple independent spectral channels according to the wavelength dimension, and each channel presents the spectral intensity information in the form of a two-dimensional matrix. After strict spatial pixel calibration operation, the spatial position error caused by the inherent distortion of the optical imaging system is eliminated, and the data of different bands are accurately aligned in space. A data fusion algorithm is used to construct a three-dimensional spectral image data matrix with matched and accurate spatial and spectral information. In this way, the spectral information can be fully extracted and the spatial coordinate consistency can be ensured, achieving high-precision capture of the spectral characteristics of the indicator card chemical color reaction, thereby providing a clear and interference-free data basis for subsequent signal processing, greatly improving the recognition accuracy of the color information of the sterilization indicator card and the reliability of the overall system detection.

[0053] S102: Obtain the environmental parameter data in the sterilization cabin, which includes temperature data, humidity data, pressure data and electromagnetic field intensity data;

[0054] Specifically, in some embodiments, the environmental parameter data in the sterilization cabin can be obtained by the following steps: real-time monitoring of the cavity temperature in the sterilization cabin by a temperature sensing unit to generate a temperature raw electrical signal;

[0055] First, real-time monitoring of the relative humidity in the sterilization cabin by a humidity sensing unit to generate a humidity raw electrical signal;

[0056] Second, real-time monitoring of the gas pressure in the sterilization cabin by a pressure sensing unit to generate a pressure raw electrical signal;

[0057] Third, real-time monitoring of the high-frequency electromagnetic field intensity in the sterilization cabin by an electromagnetic field sensing unit to generate an electromagnetic field raw electrical signal;

[0058] Fourth, performing signal conditioning operations on the temperature raw electrical signal, humidity raw electrical signal, pressure raw electrical signal and electromagnetic field raw electrical signal, including noise reduction filtering and signal amplification;

[0059] Fifth, inputting the conditioned electrical signals into a data acquisition card for synchronous sampling to generate discretized temperature sampling values, humidity sampling values and pressure sampling values;

[0060] Sixth, aligning the temperature sampling values, humidity sampling values and pressure sampling values by time stamp and packaging them as structured environmental parameter data packets;

[0061] Seventh, outputting the structured environmental parameter data packets as the environmental parameter data in the sterilization cabin. This scheme collects the environmental parameters in the sterilization cabin through the temperature sensing unit, humidity sensing unit, pressure sensing unit and electromagnetic field sensing unit. The collected signals are processed by noise reduction filtering and amplification and then discretely sampled to form structured environmental parameter data packets, thereby ensuring that the environmental parameters accurately reflect the actual state of the sterilization cabin.

[0062] S103: Generating a background interference signal based on the environmental parameter data and the pre-stored interference spectrum model;

[0063] Specifically, in some embodiments, the background interference signal can be generated based on the environmental parameter data and the pre-stored interference spectrum model by the following steps:

[0064] First, calling the pre-stored interference spectrum model from the non-volatile memory, which includes temperature-spectrum response function, humidity-spectrum response function, pressure-spectrum response function and electromagnetic field-spectrum response function;

[0065] Second step, parsing the temperature sampling value, humidity sampling value and pressure sampling value in the environmental parameter data packet;

[0066] Third step, inputting the temperature sampling value into the temperature-spectrum response function to calculate the temperature interference component;

[0067] Fourth step, inputting the humidity sampling value into the humidity-spectrum response function to calculate the humidity interference component;

[0068] Fifth step, inputting the pressure sampling value into the pressure-spectrum response function to calculate the pressure interference component;

[0069] Sixth step, inputting the electromagnetic field intensity sampling value into the electromagnetic field-spectrum response function to calculate the electromagnetic field interference component;

[0070] Seventh step, according to the preset weight coefficient, performing weighted superposition operation on the temperature interference component, the humidity interference component and the pressure interference component to generate a background interference signal matrix consistent with the spatial dimension of the spectrum image data matrix, and the specific formula is as follows:

[0071]

[0072] In the formula, are spectrum interference components generated by temperature, humidity, pressure and electromagnetic field respectively; , wherein are temperature, humidity, pressure and electromagnetic field intensity sampling values parsed from the structured environmental parameter data packet; are corresponding pre-stored spectrum response functions; , wherein , , is a preset constant coefficient, which can be determined by calibration experiment, represents the current sampling temperature value; , wherein , , are pre-determined constant coefficients, represents the current sampling humidity value; , wherein , , are pre-determined coefficients, represents the current sampling pressure value; , wherein , , are pre-determined coefficients, The electromagnetic field intensity of the current sampling is represented. The scheme utilizes the temperature spectral response function, humidity spectral response function, pressure spectral response function and electromagnetic field spectral response function in the pre-established interference spectrum model in the nonvolatile memory, so that the environmental parameter data collected in the sterilization cabin is directly substituted into the mathematical expression with a clear polynomial form, and the interference effects of each environmental factor on the spectral signal are quantified. The relationship between the environmental parameters and the spectral signal is accurately quantified by using the polynomial calculation method, and the background interference signal matrix is generated by weighted summation with a predetermined weight, so that the composite influence of environmental factors on the spectral data is fully considered in the deduction process.

[0073] S104: Subtract the background interference signal from the spectral image data to obtain a characteristic spectral signal;

[0074] Specifically, in some embodiments, the background interference signal can be subtracted from the spectral image data to obtain a characteristic spectral signal by the following steps:

[0075] Firstly, spatial coordinate registration operation is performed on the spectral image data matrix and the background interference signal matrix, so that the pixel positions of the two are one-to-one corresponding; the specific mathematical relationship is as follows:

[0076]

[0077] In the formula, indicates the horizontal and vertical coordinates of a pixel in the original spectral image data matrix, indicates the corresponding pixel coordinates after calibration, is the pixel registration mapping matrix of .

[0078] Secondly, the spectral intensity difference of the spectral image data matrix and the background interference signal matrix at the same coordinate point is calculated pixel by pixel;

[0079] Thirdly, when the difference calculation result is negative, the spectral intensity of the pixel point is set to zero;

[0080] Fourthly, the median filtering operation is performed on the difference result after the zero setting processing to eliminate impulse noise. Specifically, for a given pixel , the filtered spectral intensity is expressed as:

[0081]

[0082] In the formula, indicates the spectral intensity of the difference result after the zero setting processing at the coordinate , indicates the median of the pixel intensity in the given window, is the filtering window radius, to locate the offset of the window relative to the center pixel

[0083] Fifth step, reconstruct the filtered difference data into a characteristic spectral signal matrix;

[0084] Sixth step, verify the consistency of the dimension of the characteristic spectral signal matrix and the original spectral image data matrix. This scheme is to eliminate the superposition effect between the original data and the interference signal by accurately registering the spatial coordinates of the spectral image data matrix and the background interference signal matrix, and using affine or projection transformation to construct a pixel registration mapping matrix, so that the original pixel coordinates and the corrected coordinates correspond strictly, and then calculate the spectral intensity difference at each pixel position. The negative part is set to zero in the calculation process to avoid introducing physically unreasonable signal values, then the median filter is used to smooth the pixel intensity in each local window to eliminate impulse noise, and finally the reconstructed characteristic spectral signal matrix is completely consistent with the original spectral data in the spatial dimension.

[0085] S105: analyze the characteristic spectral signal to determine the color development state of the sterilization indicator card, and obtain an analysis result.

[0086] Specifically, in some embodiments, the characteristic spectral signal can be analyzed to determine the color development state of the sterilization indicator card by the following steps to obtain an analysis result:

[0087] First step, locate the pre-set region of interest of the sterilization indicator card in the characteristic spectral signal matrix;

[0088] Second step, extract the average spectral intensity value of all pixel points in the target waveband in the region of interest;

[0089] Third step, input the average spectral intensity value into a pre-trained color development state classification model, and the classification model contains a chemical color development reaction feature library; calculate the Euclidean distance between the average spectral intensity value and the qualified sterilization threshold, the critical sterilization threshold and the unqualified sterilization threshold.

[0090] Specifically, in some embodiments, the color development state classification model is a support vector machine model based on a radial basis kernel function, which contains a chemical color development reaction feature library, a support vector set and corresponding Lagrange multiplier coefficients, width parameters of the radial basis kernel function and classification penalty coefficients; the chemical color development reaction feature library stores standard spectral feature vectors of qualified sterilization state, standard spectral feature vectors of critical sterilization state and standard spectral feature vectors of unqualified sterilization state;

[0091] ​The average spectral intensity value can be input into a pre-trained color development state classification model containing a chemical color development reaction feature library by the following steps: the step of calculating the Euclidean distance of the average spectral intensity value from the qualified sterilization threshold, the critical sterilization threshold, and the unqualified sterilization threshold includes:

[0092] The first sub-step is to load the pre-trained color development state classification model from the non-volatile memory,

[0093] The second sub-step is to arrange the average spectral intensity value in order of wavelength to construct an input feature vector;

[0094] The third sub-step is to perform standardization processing on the input feature vector to generate a standardized feature vector , and the specific mathematical expression is as follows:

[0095]

[0096] In the formula, represents any element (average spectral intensity value) in the input feature vector, is the mean of the vector, is the standard deviation;

[0097] The fourth sub-step is to calculate the similarity value of the standardized feature vector and each support vector in the support vector set ( ) by a radial basis kernel function, and the specific expression is as follows:

[0098]

[0099] In the formula, represents the Euclidean distance between and the support vector , and is the width parameter of the radial basis kernel function;

[0100] The fifth sub-step is to calculate the decision function value based on the similarity value and the Lagrange multiplier coefficient, and the specific formula is as follows:

[0101]

[0102] In the formula, represents the corresponding Lagrange multiplier coefficient ( ) of each support vector ; represents the bias term;

[0103] The sixth sub-step is to generate an initial classification result according to the positive and negative signs and the absolute value size of the decision function value;

[0104] A seventh sub-step, reading the qualified sterilization threshold vector, the critical sterilization threshold vector and the unqualified sterilization threshold vector from the chemical color reaction feature library;

[0105] An eighth sub-step, calculating the Euclidean distance between the normalized feature vector and the qualified sterilization threshold vector;

[0106] A ninth sub-step, calculating the Euclidean distance between the normalized feature vector and the critical sterilization threshold vector;

[0107] A tenth sub-step, calculating the Euclidean distance between the normalized feature vector and the unqualified sterilization threshold vector.

[0108] A fourth step, selecting the threshold with the smallest Euclidean distance as the determination result;

[0109] A fifth step, generating an analysis result report containing the determination result, the confidence and the timestamp;

[0110] A sixth step, transmitting the analysis result report to the human-computer interaction interface of the sterilization control system. The input feature vector is uniformly distributed through a single normalization formula, so as to provide subsequent radial basis kernel function support vector machine model for high-precision discrimination. The pre-stored support vector is used to calculate the Euclidean distance and the similarity, and the decision function calculation process is constructed, so that each determination is derived from strict mathematical operation, and the determination result is obtained. In this way, it can be ensured that the determination result is highly matched with the actual chemical color reaction state, so as to ensure that the spectral feature change is still accurately recognized when it is subtle, and effectively reduce the influence of external noise and error signal interference.

[0111] Please refer to Figure 2 , based on the same inventive concept as the spectrum image analysis method of the sterilization indicator card in the foregoing embodiment, the embodiment of the application provides a spectrum image analysis system of a sterilization indicator card, comprising:

[0112] A spectrum image acquisition module 201 is configured to acquire spectrum image data in a sterilization cabin;

[0113] An environmental parameter monitoring module 202 is configured to acquire environmental parameter data in the sterilization cabin, wherein the environmental parameter data comprises temperature data, humidity data, pressure data and electromagnetic field intensity data;

[0114] An interference signal generation module 203 is configured to generate background interference signals based on the environmental parameter data and pre-stored interference spectrum models;

[0115] A signal processing module 204 is configured to subtract the background interference signals from the spectrum image data to obtain feature spectrum signals;

[0116] A color state analysis module 205 is configured to analyze the feature spectrum signals to determine the color state of the sterilization indicator card, and obtain an analysis result.

[0117] In some embodiments, the spectral image acquisition module 201 is specifically used for:

[0118] acquiring an original optical signal of the sterilization cabin using a multi-band spectral imaging device;

[0119] performing analog-to-digital conversion on the original optical signal to generate digitized initial spectral data;

[0120] According to a preset spectral band division rule, the digitized initial spectral data is divided into at least three independent spectral channels according to the wavelength dimension, and a three-dimensional matrix is represented, where are spatial pixel coordinates, respectively, is a band number;

[0121] performing a spatial pixel calibration operation on each spectral channel to eliminate optical distortion;

[0122] performing data fusion on the calibrated spectral channels to construct a three-dimensional spectral image data matrix;

[0123] storing the three-dimensional spectral image data matrix as spectral image data in the sterilization cabin.

[0124] In some embodiments, the environmental parameter monitoring module 202 is specifically used for:

[0125] monitoring the temperature in the sterilization cabin cavity in real time through a temperature sensing unit to generate a temperature original electrical signal;

[0126] monitoring the relative humidity in the sterilization cabin in real time through a humidity sensing unit to generate a humidity original electrical signal;

[0127] monitoring the gas pressure in the sterilization cabin in real time through a pressure sensing unit to generate a pressure original electrical signal;

[0128] monitoring the high-frequency electromagnetic field intensity in the sterilization cabin in real time through an electromagnetic field sensing unit to generate an electromagnetic field original electrical signal;

[0129] performing signal conditioning operations on the temperature original electrical signal, the humidity original electrical signal, the pressure original electrical signal, and the electromagnetic field original electrical signal, including noise reduction filtering and signal amplification;

[0130] inputting the conditioned electrical signals into a data acquisition card for synchronous sampling to generate discretized temperature sampling values, humidity sampling values, and pressure sampling values;

[0131] aligning the temperature sampling values, humidity sampling values, and pressure sampling values according to timestamps to encapsulate as structured environmental parameter data packets;

[0132] output the structured environment parameter data packet as the environment parameter data in the sterilization cabin.

[0133] In some embodiments, the interference signal generation module 203 is specifically configured to:

[0134] call a pre-stored interference spectrum model from the non-volatile memory, the interference spectrum model containing a temperature-spectrum response function, a humidity-spectrum response function, a pressure-spectrum response function, and an electromagnetic field-spectrum response function;

[0135] parse the temperature sampling value, the humidity sampling value, and the pressure sampling value in the environment parameter data packet;

[0136] input the temperature sampling value into the temperature-spectrum response function to calculate a temperature interference component;

[0137] input the humidity sampling value into the humidity-spectrum response function to calculate a humidity interference component;

[0138] input the pressure sampling value into the pressure-spectrum response function to calculate a pressure interference component;

[0139] input the electromagnetic field intensity sampling value into the electromagnetic field-spectrum response function to calculate an electromagnetic field interference component;

[0140] According to the preset weight coefficient, the temperature interference component, the humidity interference component, and the pressure interference component are weighted and superimposed to generate a background interference signal matrix consistent with the spatial dimension of the spectrum image data matrix, and the specific formula is as follows:

[0141]

[0142] In the formula, are spectrum interference components generated by temperature, humidity, pressure, and electromagnetic field, respectively; wherein are temperature, humidity, pressure, and electromagnetic field intensity sampling values parsed from the structured environment parameter data packet, respectively; are corresponding pre-stored spectrum response functions, respectively; wherein , , is a preset constant coefficient, represents the current sampling temperature value; wherein , , is a pre-determined constant coefficient, represents the current sampling humidity value; wherein , , is a predetermined coefficient, represents the current sampled pressure value; , , is a predetermined coefficient, represents the current sampled electromagnetic field intensity.

[0143] In some embodiments, the signal processing module 204 is specifically configured to:

[0144] perform a spatial coordinate registration operation on the spectral image data matrix and the background interference signal matrix, so that the pixel positions of the two are one-to-one corresponding; The specific mathematical relationship is expressed as follows:

[0145]

[0146] In the formula, represents the horizontal and vertical coordinates of a pixel in the original spectral image data matrix, represents the corresponding pixel coordinates after calibration, is a pixel registration mapping matrix of ;

[0147] pixel-by-pixel calculate the spectral intensity difference of the spectral image data matrix and the background interference signal matrix at the same coordinate point;

[0148] When the difference calculation result is a negative value, the spectral intensity of the pixel point is set to zero;

[0149] perform a median filtering operation on the zero-handling difference result to eliminate impulse noise. Specifically, for a given pixel , the filtered spectral intensity is expressed as:

[0150]

[0151] In the formula, represents the spectral intensity of the zero-handling difference result at the coordinate , represents the median of the pixel intensity within the given window, is the filtering window radius, is the offset of the pixel within the window relative to the center pixel ;

[0152] reconstruct the filtered difference data into a feature spectral signal matrix;

[0153] verify the consistency of the dimensions of the feature spectral signal matrix and the original spectral image data matrix.

[0154] ​In some embodiments, the color development state analysis module 205 is specifically configured to:

[0155] locating a preset region of interest of the sterilization indicator card in the characteristic spectral signal matrix;

[0156] extracting the average spectral intensity value of all pixels in the region of interest in the target waveband;

[0157] inputting the average spectral intensity value into a pre-trained color development state classification model, the classification model comprising a chemical color development reaction feature library; calculating the Euclidean distance between the average spectral intensity value and the qualified sterilization threshold, the critical sterilization threshold and the unqualified sterilization threshold;

[0158] selecting the threshold with the smallest Euclidean distance as the determination result;

[0159] generating an analysis result report comprising the determination result, the confidence and the timestamp;

[0160] transmitting the analysis result report to the human-computer interaction interface of the sterilization control system.

[0161] In some embodiments, the spectral image acquisition module 201 is specifically further configured to:

[0162] obtaining the intrinsic calibration matrix and the extrinsic calibration matrix of the spectral camera;

[0163] constructing an optical distortion correction mapping function according to the intrinsic calibration matrix and the extrinsic calibration matrix;

[0164] Specifically, in the process of constructing the correction mapping function, the following formula is used for distortion correction of the original pixel coordinates , wherein and are the horizontal and vertical pixel coordinates, the focal length and are the principal point coordinates, and the camera intrinsic parameters are calculated as :

[0165]

[0166] The formula for calculating the corrected pixel coordinates is:

[0167]

[0168] wherein are the first-order, second-order and third-order radial distortion correction coefficients, respectively;

[0169] For each spectral channel, the corresponding ideal non-distorted coordinate grid is calculated for the original pixel coordinate grid.​

[0170] Resample the spectral intensity values of the original pixel coordinate grid to an ideal non-distorted coordinate grid using a bilinear interpolation algorithm;

[0171] Perform edge clipping operation on the resampled spectral channels to remove invalid boundary pixels;

[0172] Generate calibrated spectral channel data and mark spatial coordinate metadata.

[0173] In some embodiments, the color development state classification model is a support vector machine model based on a radial basis kernel function, containing a chemical color development reaction feature library, a support vector set and corresponding Lagrange multiplier coefficients and a width parameter of the radial basis kernel function and a classification penalty coefficient; the chemical color development reaction feature library stores standard spectral feature vectors of qualified sterilization states, standard spectral feature vectors of critical sterilization states and standard spectral feature vectors of unqualified sterilization states;

[0174] The color development state analysis module 205 is specifically further used for:

[0175] Loading a pre-trained color development state classification model from a non-volatile memory,

[0176] Arranging the average spectral intensity values in order of wavelength to construct an input feature vector;

[0177] Performing standardization processing on the input feature vector to generate a standardized feature vector , and the specific mathematical expression is as follows:

[0178]

[0179] In the formula, represents any element (average spectral intensity value) in the input feature vector, is the mean value of the vector, is the standard deviation;

[0180] Calculating the similarity value between the standardized feature vector and each support vector in the support vector set ( ) through a radial basis kernel function, and the specific expression is as follows:

[0181]

[0182] In the formula, represents the Euclidean distance between and the support vector , and is the width parameter of the radial basis kernel function;

[0183] The decision function value is calculated based on the similarity value and the Lagrange multiplier coefficient The specific formula is as follows:

[0184]

[0185] In the formula, Each support vector Corresponding Lagrange multiplier coefficient (b) is represented; ) is represented; The bias term is represented;

[0186] The initial classification result is generated according to the positive and negative signs and the absolute value size of the decision function value;

[0187] The qualified sterilization threshold vector, the critical sterilization threshold vector and the unqualified sterilization threshold vector are read from the chemical color reaction feature library;

[0188] The Euclidean distance between the standardized feature vector and the qualified sterilization threshold vector is calculated;

[0189] The Euclidean distance between the standardized feature vector and the critical sterilization threshold vector is calculated;

[0190] The Euclidean distance between the standardized feature vector and the unqualified sterilization threshold vector is calculated.

[0191] It can be understood that the modules recorded in the sterilization indicator card spectral image analysis system correspond to the steps in the sterilization indicator card spectral image analysis method described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method also apply to the sterilization indicator card spectral image analysis system and the modules contained therein, and will not be repeated here.

[0192] Please refer to Figure 3, based on the inventive concept of the sterilization indicator card spectral image analysis method in the foregoing embodiments, an electronic device is provided according to embodiments of the present application. The electronic device can include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device includes a processing device 301 (e.g., a central processing unit, a graphic processing unit, or the like) that can perform various appropriate actions and processes according to a program stored in a ROM 302 (Read Only Memory) or a program loaded into a RAM 303 (Random Access Memory) from a storage device 308. In the RAM 303, various programs and data required for the operation of the electronic device are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output interface (i.e., I / O interface 305) is also connected to the bus 304.

[0193] Generally, the following devices can be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, and the like; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, and the like; a storage device 308 including, for example, a magnetic tape, a hard disk, and the like; and a communication device 309. The communication device 309 can allow the electronic device to communicate wirelessly or wiredly with other devices to exchange data.

[0194] In particular, according to some embodiments of the present application, the processes described above with reference to the flowcharts can be implemented as a computer software program. For example, some embodiments of the present application include a computer program product including a computer program carried on a computer readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In some such embodiments, the computer program can be downloaded and installed from a network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-described functions defined in the methods of some embodiments of the present application are performed.

[0195] Note that the computer readable medium in some embodiments of the present application can be a computer readable signal medium or a computer readable storage medium or any combination thereof. The computer readable storage medium can be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any suitable combination thereof. More specific examples of the computer readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus or device. In some embodiments of the present application, the computer readable signal medium can include a data signal that propagates in a baseband or as part of a carrier wave in a propagated data signal, in which the computer readable program code is carried. Such a propagated data signal can take any of a variety of forms, including but not limited to electro-magnetic, optical, or any suitable combination thereof. The computer readable signal medium can also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. The program code contained on the computer readable medium can be transmitted by any suitable medium, including but not limited to wire, cable, RF (radio frequency), etc., or any suitable combination thereof.

[0196] In some embodiments, the client, server, or both can communicate using any current known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet, and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any current known or future developed networks.

[0197] The computer readable medium described above can be included in the electronic device described above; or exist separately from the electronic device and not be assembled into the electronic device. The computer readable medium described above carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device can implement the method steps of any of the technical solutions described above.

[0198] Computer program code for carrying out operations of some embodiments of the application can be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0199] The computer program instructions can also be loaded onto a computer or other programmable information processing apparatus to cause a series of operations to be performed on the computer or other programmable information processing apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable information processing apparatus implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0200] The modules described in some embodiments of the present application can be implemented by software, or by hardware. The described modules can also be set in a processor. It can be understood that the name of the modules does not constitute a limitation on the modules themselves in some cases.

[0201] The functions described above in the detailed description can be performed by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0202] Some embodiments of the present application also provide a computer program product comprising a computer program which, when executed by a processor, implements any of the above sterilization indicator card spectral image analysis methods.

[0203] Although the present application has been described in detail with general description and specific embodiments above, some modifications or improvements can be made to the present application, which is obvious to those skilled in the art on the basis of the present application. Therefore, these modifications or improvements made on the basis of not deviating from the spirit of the present application, all belong to the scope of protection claimed by the present application.

Claims

1. A method for analyzing spectral images of sterilization indicator cards, characterized in that: The following steps are involved: Acquire spectral image data in the sterilization chamber; Acquiring environmental parameter data in the sterilization chamber, wherein the environmental parameter data includes temperature data, humidity data, pressure data, and electromagnetic field strength data; Generate background interference signals based on environmental parameter data and pre-stored interference spectrum models; Subtracting the background interference signal from the spectral image data to obtain the characteristic spectral signal; Analyze the characteristic spectral signal to determine the color development state of the sterilization indicator card and obtain the analysis result.

2. The method for analyzing spectral images of sterilization indicator cards according to claim 1, wherein: The steps of obtaining spectral image data in the sterilization chamber include: Use multi-band spectral imaging equipment to collect the original optical signals of the sterilization chamber; Performing analog-to-digital conversion on the original optical signal to generate digital initial spectral data; According to the preset spectrum band division rules, the digital initial spectrum data is decomposed into at least three independent spectrum channels according to the wavelength dimension, and the three-dimensional matrix is ​​used to generate the spectrum. Indicates that are spatial pixel coordinates, Number the bands; Perform spatial pixel calibration on each spectral channel to eliminate optical distortion; The calibrated spectral channels are fused to construct a three-dimensional spectral image data matrix; The three-dimensional spectral image data matrix is ​​stored as spectral image data in the sterilization chamber.

3. The method for analyzing spectral images of sterilization indicator cards according to claim 2, wherein: The steps for obtaining environmental parameter data in the sterilization chamber include: The temperature of the sterilization chamber cavity is monitored in real time through the temperature sensing unit to generate the original temperature electrical signal; The relative humidity in the sterilization chamber is monitored in real time through the humidity sensing unit to generate the original electrical signal of humidity; The pressure sensing unit monitors the gas pressure in the sterilization chamber in real time and generates a pressure original electrical signal; The electromagnetic field sensing unit monitors the high-frequency electromagnetic field intensity in the sterilization chamber in real time and generates the original electromagnetic field electrical signal; Performing signal conditioning operations on the temperature original electrical signal, the humidity original electrical signal, the pressure original electrical signal, and the electromagnetic field original electrical signal, including noise reduction filtering and signal amplification; The conditioned electrical signal is input into the data acquisition card for synchronous sampling to generate discrete temperature sampling values, humidity sampling values ​​and pressure sampling values; Aligning the temperature sampling value, humidity sampling value, and pressure sampling value according to timestamps and encapsulating them into a structured environmental parameter data packet; The structured environmental parameter data packet is output as environmental parameter data in the sterilization chamber.

4. The method for analyzing spectral images of sterilization indicator cards according to claim 3, wherein: The steps of generating a background interference signal based on the environmental parameter data and the pre-stored interference spectrum model include: Recalling a pre-stored interference spectrum model from a non-volatile memory, wherein the interference spectrum model includes a temperature-spectrum response function, a humidity-spectrum response function, a pressure-spectrum response function, and an electromagnetic field-spectrum response function; Parse the temperature sampling value, humidity sampling value and pressure sampling value in the environmental parameter data packet; Inputting the temperature sampling value into the temperature-spectral response function to calculate the temperature interference component; Inputting the humidity sampling value into the humidity-spectral response function to calculate the humidity interference component; Inputting the pressure sampling value into a pressure-spectral response function to calculate a pressure interference component; Inputting the electromagnetic field intensity sampling value into the electromagnetic field-spectral response function to calculate the electromagnetic field interference component; According to the preset weight coefficients, the temperature interference component, humidity interference component and pressure interference component are weighted superpositioned to generate a background interference signal matrix consistent with the spatial dimension of the spectral image data matrix. The specific formula is as follows: Where, They are the spectral interference components generated by temperature, humidity, pressure and electromagnetic fields; ,in They are the temperature, humidity, pressure and electromagnetic field intensity sampling values ​​parsed from the structured environmental parameter data packet; are the corresponding pre-stored spectral response functions; ,in , , is the preset constant coefficient, Indicates the current sampling temperature value; in , , is a predetermined constant coefficient, Indicates the current sampled humidity value; in , , is a predetermined coefficient, Indicates the current sampled pressure value; in , , is a predetermined coefficient, Indicates the electromagnetic field strength of the current sample.

5. The method for analyzing spectral images of sterilization indicator cards according to claim 4, wherein: The steps of subtracting the background interference signal from the spectral image data to obtain the characteristic spectral signal include: Perform spatial coordinate registration on the spectral image data matrix and the background interference signal matrix to make the pixel positions of the two correspond one to one. The specific mathematical relationship is expressed as follows: Where, Represents the horizontal and vertical coordinates of a pixel in the original spectral image data matrix, Indicates the corresponding pixel coordinates after calibration, for The pixel registration mapping matrix; Calculate the spectral intensity difference between the spectral image data matrix and the background interference signal matrix at the same coordinate point pixel by pixel; When the difference calculation result is a negative value, the pixel spectral intensity is set to zero; Perform median filtering on the difference result after zero processing to eliminate impulse noise. Specifically, for a given pixel , the filtered spectral intensity Expressed as: Where, Indicates that the difference result after zeroing is in the coordinate The spectral intensity, represents the median pixel intensity within a given window, is the filter window radius, is the pixel relative to the center of the window offset; Reconstruct the filtered difference data into a characteristic spectrum signal matrix; Verify the consistency of the dimension of the characteristic spectral signal matrix with the original spectral image data matrix.

6. The method for analyzing spectral images of sterilization indicator cards according to any one of claims 1 to 5, characterized in that: The steps of analyzing the characteristic spectral signal to determine the color development state of the sterilization indicator card and obtaining the analysis result include: Locating a preset region of interest of the sterilization indicator card in the characteristic spectral signal matrix; Extract the average spectral intensity value of all pixels in the target band within the region of interest; Inputting the average spectral intensity value into a pre-trained color development state classification model, wherein the classification model includes a chemical color development reaction feature library; calculating the Euclidean distance between the average spectral intensity value and a qualified sterilization threshold, a critical sterilization threshold, and an unqualified sterilization threshold; Select the threshold with the smallest Euclidean distance as the judgment result; Generate analysis result report including judgment result, confidence level and time stamp; The analysis result report is transmitted to the human-computer interaction interface of the sterilization control system.

7. A sterilization indicator card spectral image analysis system, characterized in that: include: Spectral image acquisition module, used to obtain spectral image data in the sterilization chamber; Environmental parameter monitoring module, used to obtain environmental parameter data in the sterilization chamber, the environmental parameter data including temperature data, humidity data, pressure data and electromagnetic field strength data; An interference signal generation module, configured to generate a background interference signal based on environmental parameter data and a pre-stored interference spectrum model; A signal processing module is used to subtract background interference signals from spectral image data to obtain characteristic spectral signals; The color development state analysis module is used to analyze the characteristic spectral signal to determine the color development state of the sterilization indicator card and obtain the analysis result.

8. An electronic device, characterized in that: include: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, which implements the method according to any one of claims 1 to 6 when executed by a processing device.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processing device, the method according to any one of claims 1 to 6 is implemented.

Images