Traditional Measurement Methods Research Articles

Measurement of ureteral length: Comparison of deep learning-based method and other estimation methods on CT and KUB

BackgroundAccurate preoperative assessment of ureteral length is crucial for effective ureteral stenting. PurposeUtilize a deep learning approach to measure ureter length on CT urography (CTU) images and compare the obtained results with those derived from other estimation methods. MethodsIn a retrospective cohort (cohort A, n = 411), CTU images were collected and used to develop a 3D deep learning model for the segmentation of bilateral ureters. The centerline of the ureters was determined based on the segmentation, and the length of the ureters was automatically obtained (CTU_ai). Another cohort (cohort B, n = 220) was collected as the hold-out test for the model. All patients in cohort B had KUB, non-contrast enhanced CT (CT NoC), and CTU images. Cohort B utilized eight measurement methods, with one annotated by two radiologists serving as the reference standard (CTU_ref) and the remaining seven as the studied methods, including three measurement methods applied to CTU (CTU_ai, CTU_oblique, CTU_slice), two applied to CT NoC (CT_oblique, CT_slice), and two applied to KUB (KUB_short, KUB_long). The results of the seven studied methods were compared to those of the reference in cohort B. ResultsAmong the 220 patients (96 females, 124 males), 437 ureters were measured for length (218 left, 219 right), with a median length of 24.7 (IQR 23.2–26.2) cm. No significant differences were observed between genders or laterality (both P > 0.05). Moreover, there was no correlation between ureteral length and age (r = −0.027, P = 0.573). The ureteral length measured by CTU_ai was not significantly different from that measured by CTU_ref (P = 0.514), whereas the length measured by the other studied methods was significantly different from that measured by CTU_ref (all P < 0.001). The ICC values with their 95 % confidence intervals (CIs) for the comparison between the reference standard (CTU_ref) and the other measurement methods: CTU_ai (ICC = 0.852, 95 % CI 0.825–0.876), CTU_oblique (ICC = 0.351, 95 % CI -0.083-0.689), CTU_slice (ICC = 0.269, 95 % CI -0.095-0.573), CTU_oblique_slice (ICC = 0.059, 95 % CI -0.032-0.218), CTU_slice (ICC = 0.049, 95 % CI -0.028-0.188), KUB_short (ICC = 0.151, 95 % CI 0.051–0.247), and KUB_long (ICC = 0.147, 95 % CI 0.034–0.253). For CTU_ai, in 89.0 % of the ureters, the ureteral length deviation was within 20 mm of the reference standard, which was the highest among all the studied methods (all P < 0.001). ConclusionThe deep learning model offers a reliable and accurate tool for ureteral length measurement on CTU images, which could enhance the effectiveness of ureteral stenting procedures. Its performance surpasses traditional measurement methods, making it a promising technology for integration into clinical practice.

Computer-Vision-Aided Deflection Influences Line Identification of Concrete Bridge Enhanced by Edge Detection and Time-Domain Forward Inference

To enhance the accuracy and efficiency of the deflection response measurement of concrete bridges with a non-contact scheme and address the ill-conditioned nature of the inverse problem in influence line (IL) identification, this study introduces a computer-vision-aided deflection IL identification method that integrates edge detection and time-domain forward inference (TDFI). The methodology proposed in this research leverages computer vision technology with edge detection to surpass traditional contact-based measurement methods, greatly enhancing the operational efficiency and applicability of IL identification and, in particular, addressing the challenge of accurately measuring small deflections in concrete bridges. To mitigate the limitations of the Lucas–Kanade (LK) optical flow method, such as unclear feature points within the camera’s field of view and occasional point loss in certain video frames, an edge detection technique is employed to identify maximum values in the first-order derivatives of the image, creating virtual tracking points at the bridge edges through image processing. By precisely defining the bridge boundaries, only the essential structural attributes are preserved to enhance the reliability of minimal deflection deformations under vehicular loads. To tackle the ill-posed nature of the inverse problem, a TDFI model is introduced to identify IL, recursively capturing the static bridge response generated by the bridge under the influence of successive axles of a multi-axle vehicle. The IL is then computed by dividing the response by the weight of the preceding axle. Furthermore, an axle weight ratio reduction coefficient is proposed to mitigate noise amplification issues, ensuring that the weight of the preceding axle surpasses that of any other axle. To validate the accuracy and robustness of the proposed method, it is applied to numerical examples of a simply supported concrete beam, indoor experiments on a similar beam, and field tests on a three-span continuous concrete beam bridge.

A New Method for Measuring Multilayer Thickness Using a Chromatic Confocal Sensor

Multilayer transparent plates play a crucial role in industrial fields, such as optical lenses, electrodes, and solar panels, because of their superior optical and electrical properties. The thickness and uniformity of such plates are decisive for the quality of the final product. However, traditional contact measurement methods are inadequate in accuracy and pose the risk of damaging the plates, making nondestructive measurement of multilayer transparent plate thickness rather challenging. A new measurement technology is urgently needed. This study proposes a new method for the thickness measurement of multilayer transparent plates based on chromatic confocal sensor technology. First, we investigated the dispersive behavior of light in various media layers and derived theoretical measurement models for single-layer and multilayer transparent plate thicknesses. Subsequently, we designed and constructed a measurement system using a C-series chromatic confocal sensor and optical instruments and prepared a five-layer transparent sample consisting of quartz and air layers to confirm the feasibility of the method. The results of the experiment show that the proposed method can accurately measure the thickness of the five-layer sample with a maximum absolute error within 13 µm and a maximum relative error of 4.27%, thus proving its validity, precision, and stability. The results further indicate the high practicality and reliability of this technology in production environments, theoretically enabling the simultaneous measurement of up to 18 layers of the plate and offering broad application prospects in the industry.

LiqD: Dynamic Liquid Level Detection under Containers

Abstract. In daily life and industrial production, it is crucial to accurately detect changes in liquid level in containers. Traditional contact measurement methods have some limitations, while emerging non-contact image processing technology shows good application prospects. This paper proposes a container dynamic liquid level detection model based on U-Net. This model uses the SAM model to generate an initial data set, and then evaluates and filters out high-quality pseudo-label images through the semi-supervised framework to build an exclusive data set. The model uses U-Net to extract masking images of containers from the data set, and uses morphological processing to compensate for masking defects. Subsequently, the model calculates the grayscale difference between adjacent video frame images at the same position, segments the liquid level change area by setting a difference threshold, and finally uses a lightweight neural network to classify the liquid level state and achieves the accuracy of 91.39%. This approach not only mitigates the impact of intricate surroundings, but also reduces the demand for training data, showing strong robustness and versatility. A large number of experimental results show that the proposed model can effectively detect the dynamic liquid level changes of the liquid in the container, providing a novel and efficient solution for related fields.

Phase-based video vibration measurement and fault feature extraction method for compound faults of rolling bearings

Vibration characterization of rotating machinery is crucial for determining rotational and failure frequencies. Traditional contact measurement methods have limitations, while high-speed cameras offer a non-contact alternative for measuring target vibrations, spatial phase-based techniques have recently been widely used in detecting subtle vibrations and show good robustness to imaging noise. In this paper, a vision-based vibration extraction method for rotating machinery is proposed, aiming at extracting minor vibrations of bearings from them and further analyzing their fault frequencies. To address the challenge of separating a single fault frequency from the extracted compound faulty vibration signals, kurtosis is employed to analyze the inverse convolution period of multiple periodic components, and the MOMEDA filter length is optimized using the golden section algorithm. MOMEDA is then used to enhance each periodic pulse separately, and fault frequency is obtained through envelope spectrum demodulation. In the experimental part, a phase-based method is used to extract minor vibration displacements from rotor vibration video, which is subsequently compared with eddy current sensors in both time and frequency domains to verify the accuracy of the proposed method in extracting vibration displacements based on vision. Finally, vibration signals are extracted from the bearing compound fault video, and the single fault frequency characteristics of the bearing are successfully separated using the adaptive MOMEDA method, which provides an efficient and reliable method in the field of rotating machinery fault diagnosis.

A Review: Phase Measurement Techniques Based on Metasurfaces

Phase carries crucial information about the light propagation process, and the visualization and quantitative measurement of phase have important applications, ranging from ultra-precision metrology to biomedical imaging. Traditional phase measurement techniques typically require large and complex optical systems, limiting their applicability in various scenarios. Optical metasurfaces, as flat optical elements, offer a novel approach to phase measurement by manipulating light at the nanoscale through light-matter interactions. Metasurfaces are advantageous due to their lightweight, multifunctional, and easy-to-integrate nature, providing new possibilities for simplifying traditional phase measurement methods. This review categorizes phase measurement techniques into quantitative and non-quantitative methods and reviews the advancements in metasurface-based phase measurement technologies. Detailed discussions are provided on several methods, including vortex phase contrast, holographic interferometry, shearing interferometry, the Transport of Intensity Equation (TIE), and wavefront sensing. The advantages and limitations of metasurfaces in phase measurement are highlighted, and future research directions are explored.

Two-Stage Multimodal Method for Predicting Intramuscular Fat in Pigs

Intramuscular fat (IMF) content significantly influences pork tenderness, flavor, and juiciness. Maintaining an optimal IMF range not only enhances nutritional value but also improves the taste of pork products. However, traditional IMF measurement methods are often invasive and time-consuming. Ultrasound imaging technology offers a non-destructive solution capable of predicting IMF content and assessing backfat thickness as well as longissimus dorsi muscle area size. A two-stage multimodal network model was developed in this study. First, using B-mode ultrasound images, we employed the UNetPlus segmentation network to accurately delineate the longissimus dorsi muscle area. Subsequently, we integrated data on backfat thickness and longissimus dorsi muscle area to create a multimodal input for IMF content prediction using our model. The results indicate that UNetPlus achieves a 94.17% mean Intersection over Union (mIoU) for precise longissimus dorsi muscle area segmentation. The multimodal network achieves an R2 of 0.9503 for IMF content prediction, with Spearman and Pearson correlation coefficients of 0.9683 and 0.9756, respectively, all within a compact model size of 4.96 MB. This study underscores the efficacy of combining segmented longissimus dorsi muscle images with data on backfat thickness and muscle area in a two-stage multimodal approach for predicting IMF content.

Algorithm for extracting the normal cross-section parameters of multiple ball screw shaft ball tracks based on an optical micrometer measurement system

Abstract The accurate and efficient measurement of the normal cross-section parameters of multiple ball screw shaft spiral ball tracks are pivotal for ensuring quality control in ball track machining. Given the intricate nature of the ball screw shaft spiral ball track, balancing the accuracy and efficiency of the normal cross-section parameters measurement is a significant challenge. In this study, we present a method to calculate two core parameters, arc radius and contact angle. The method consists of four parts: the automatic axial cross-section separation method, the arc symmetric extraction method, the spiral transformation method, and the parameter algorithm based on the weighted least squares method. The experimental and simulation results validated the effectiveness of our method. Compared with the traditional axial measurement and transformation (AMT) method, our algorithm reduced the errors in arc radius and contact angle by up to 13.9 µm and 4.77°, respectively, and improved the accuracy by up to 78.34% and 85.04%. Compared with the traditional AMT methods and directly normal measurement method, the measurement time of our algorithm was reduced by up to 1565 s and 3475 s, respectively, and the efficiency was improved by up to 71.01% and 84.51%, respectively.

Detection of body shape changes in obesity monitoring using image processing techniques

Body measurements are primarily made with a tape measure. In measurements taken with a tape measure, the inability to take measurements from the same part of the body each time, incorrect positioning of the tape measure, the occurrence of incorrect measurements, and the need for a person to take the measurements are significant problems in the traditional measurement method. Due to the social distancing rule that must be followed during the Covid-19 pandemic, the close contact between the person to be measured and the person taking the measurement became the starting point of this study. This study focuses on the detecting body shape changes using image processing techniques with 2D imaging. The novelty of the work is that non-contact body measurements are taken more accurately and reliably using the cosine theorem. Regular monitoring of obese patients is important in combating obesity, which is also the source of many health problems. In the monitoring of obese patients, it is necessary to determine the rate of slimming in areas where fat accumulation is intense. The error margin between the real measurements of human models and the calculated measurements was calculated as an average of ± 5.16% for waistline and an average of ± 4.58% for hip size. The cosine theorem was used instead of the ellipse formula used in the literature, and it was observed that the cosine theorem obtained results closer to reality. It is also thought that the developed system will be beneficial not only for extracting body measurements but also for extracting body measurements contactless in the textile sector. The study demonstrates the feasibility of image processing for non-contact body anthropometry and shape tracking.

Investigation of the Transition to Environmental Remote Sensing and Factors Influencing Effective Decision-Making on Soil Preparation and Sowing Timing: A Case Study

The advancement of smart metering technology is progressing steadily and inevitably across various key economic sectors. The utilizatio.n of remote sensors in agriculture presents unique characteristics and specific challenges. In this study, an on-site experiment was carried out on a Slovakian production farm to analyze the transition from traditional measurement methods to smart meters, focusing on timing decisions related to soil preparation and sowing and their relation to scientifically justified dates. Consequently, a clear distinction was observed in terms of the timing decisions made regarding agricultural activities during traditional, combined, and scientifically based approaches in meteorological data readings. This study contrasts these three scenarios and deliberates on the factors that need to be carefully evaluated before incorporating remote sensors into agricultural processes. This study serves as a valuable resource for individuals involved in the adoption of smart metering practices in the Eastern European agricultural sector and promotes an improved understanding of the interactions within smart-sensing, scientific developments, and land management that contribute to the goal of land-system sustainability.

Rekonstrukcja miejsca zdarzenia drogowego w oparciu o dane geoprzestrzenne Geoportalu Krajowego

The purpose of the article is to analyze the potential use of free spatial data available in the National Geoportal to support traffic accident reconstruction. The research focuses on the capabilities and limitations of using LiDAR and orthophotomaps data in the context of reconstructing traffic accident scenes. A comparative methodology was employed, involving the analysis of geospatial data in relation to traditional surveying techniques, exemplified by a real traffic accident analysis using the PC-Crash soft-ware. The main findings of the research indicate high precision of orthophotos and LiDAR data in reproducing the actual topography and elements of road infrastructure. The analysis conducted on a 3D model created from LiDAR data showed that modern measurement techniques allow a more accurate reconstruction of the accident's trajectory and assessment of road visibility conditions. Integrating these data with traditional measurement methods can significantly enhance the standards of forensic experts' work, contributing to an increased accuracy in determining accident scenarios and, more broadly, to a better understanding of accident causes.

Radial polarisation patterns identify macular damage: a machine learning approach

ABSTRACT Clinical relevance Identifying polarisation-modulated patterns may be an effective method for both detecting and monitoring macular damage. Background The aim of this work is to determine the effectiveness of polarisation-modulated patterns in identifying macular damage and foveolar involvement using a methodology that involved feature selection, Naïve Bayes supervised machine learning, cross validation, and use of an interpretable nomogram. Methods A cross-sectional study involving 520 eyes was undertaken, encompassing both normal and abnormal cases, including those with age-related macular disease, diabetic retinopathy or epiretinal membrane. Macular damage and foveolar integrity were assessed using optical coherence tomography. Various polarisation-modulated geometrical and optotype patterns were employed, along with traditional methods for visual function measurement, to complete perceptual detection and identification measures. Other variables assessed included age, sex, eye (right, left) and ocular media (normal, pseudophakic, cataract). Redundant variables were removed using a Fast Correlation-Based Filter. The area under the receiver operating characteristic curve and Matthews correlation coefficient were calculated, following 5-fold stratified cross validation, for Naïve Bayes models describing the relationship between the selected predictors of macular damage and foveolar involvement. Results Only radially structured polarisation-modulated patterns and age emerged as predictors of macular damage and foveolar involvement. All other variables, including traditional logMAR measures of visual acuity, were identified as redundant. Naïve Bayes, utilising the Fast Correlation-Based Filter selected features, provided a good prediction for macular damage and foveolar involvement, with an area under the receiver operating curve exceeding 0.7. Additionally, Matthews correlation coefficient showed a medium size effect for both conditions. Conclusions Radially structured polarisation-modulated geometric patterns outperform polarisation-modulated optotypes and standard logMAR acuity measures in predicting macular damage, regardless of foveolar involvement.

Real-time Blood Pressure Prediction on Wearable Devices using Edge Based Deep Neural Networks: A Hardware-software Co-design Approach

This paper presents the hardware realization of a real-time blood pressure (BP) prediction model for wearable devices, utilizing long short-term memory (LSTM) deep neural networks (DNNs). The proposed system uses both electrocardiogram (ECG) and photoplethysmogram (PPG) signal values for BP prediction. It aims to address the limitations of traditional BP measurement methods, providing a low error, minimal computational overhead, more accurate and convenient alternative system for individuals with hypertension or at risk for cardiovascular diseases. The utilization of split matrix approach leads to a reduction in hardware complexity across the entire system. This technique involves breaking down the larger weight matrices used in the computations of DNNs into smaller matrices. This fragmentation results in a decrease in the complexity of the hardware responsible for performing matrix vector multiplications (MVMs) within LSTMs. The resultant architecture of the predictive model gains several advantages, including a lowered level of complexity in terms of the space occupied by individual cells, decreased processing delay, and reduced power consumption. Furthermore, this approach enables the achievement of a notably improved minimum achievable clock period of 2.972 ns. This prediction model can operate locally on wearable devices, reducing the reliance on cloud computing and improving privacy and security. The performance evaluations are carried out using both analytical and implementation results. The results indicate that the proposed model can be practically applied to real-world problems and can potentially enhance the accuracy of various machine-learning tasks.

Smart dimensional quality assessment of embedded steel plates based on images and laser data fusion

Abstract Accurate and efficient positioning is critical to ensuring the dimensional quality assessment of embedded steel plates. However, traditional manual measurement methods struggle to efficiently measure and evaluate these plates. Vision-based measurement methods offer advantages such as high resolution, fast data acquisition, and processing speed, allowing accurate measurement of 2D coordinates. LiDAR can capture highly accurate point clouds, due to the unordered nature of point clouds, processing and analysis require significant computational resources. This paper proposes a method for smart 3D localization of embedded steel plates using image and laser data. (1) We introduce an improved Rectangular Diagonal Constraint Harris (RDC-Harris) corner detection method and achieve subpixel 2D corner detection of embedded plates based on deep learning；(2) Given a calibrated camera-LiDAR, we develop a smart detection algorithm guided by 2D image bounding boxes, achieving 3D corner localization. In indoor testing and engineering applications, this method effectively ensures the dimensional quality of embedded steel plates. Compared to traditional manual inspection, the measurement efficiency reaches 10 minutes per station, with an accuracy of 2.12 mm.

A method for measuring carbon emissions from power plants using a CNN-LSTM-Attention model with Bayesian optimization

Accurate measurement of CO2 emissions from coal-fired power plants is crucial for achieving China's “carbon neutrality” goal; however, traditional CO2 emission measurement methods have several limitations, and emerging prediction models rarely utilize real-time monitoring data from power plants at the micro level. To address these challenges, this study presents a novel hybrid convolutional neural network with long short-term memory (CNN-LSTM)-Attention model, leveraging real-time monitoring data to enhance the accuracy of CO2 emission predictions. The proposed model employs a hybrid architecture that leverages the strength of CNN, LSTM, and Attention mechanism. To address the challenges of multiple hyperparameters and difficult selection, the Bayesian optimization algorithm is used to optimize the hyperparameters ensuring optimal performance. Using historical operational data from a 660 MW generator set in Hubei province, the proposed model was evaluated and validated horizontally by using three evaluation metrics. Additionally, the vertical evaluation and validation of the proposed model were done using the operational data from other months. The results indicate that the proposed model achieved the highest performance across every evaluation index for predicting CO2 emissions from coalfired power plants, and the prediction accuracy of the CO2 emission in the future months is also guaranteed.

Exploring the Fundamentals of Bilirubinometry: Methods of Assessment, Timely Monitoring, and Intervention in Neonatal Jaundice with Integrated Phototherapy Solutions—A Review

A frequent ailment in infants, neonatal jaundice is characterized by high bilirubin levels and yellowing of the skin and eyes. It needs to be carefully managed to avoid serious consequences like kernicterus. The principles of bilirubinometry are examined in this review paper, with particular attention paid to different evaluation techniques, the value of prompt monitoring, and modern intervention approaches. Newborns may find it uncomfortable to undergo intrusive blood drawing as part of traditional bilirubin measurement methods. Transcutaneous bilirubinometry (TcB), on the other hand, provides a non-invasive substitute that improves monitoring effectiveness and lessens patient pain. The mainstay of care for newborn jaundice is still phototherapy, which uses light to change bilirubin into a form that is easier to excrete. The efficacy and safety of phototherapy have been enhanced by recent developments, especially about LED-based technology. The evaluation also looks at integrated phototherapy options that optimize therapeutic results and improve neonatal safety by combining automated treatment modifications with real-time bilirubin monitoring. To improve neonatal health outcomes and lessen difficulties related to hyperbilirubinemia, this review emphasizes the significance of timely and effective care of neonatal jaundice by synthesizing existing achievements and highlighting the incorporation of technology innovations

Experimental research of helicopter blade load in flight based on optical sensing

Abstract The actual flight measurement of blade load is an extremely important part of the new helicopter. In order to solve the problems existing in the traditional electrical measurement method, such as weak anti-interference ability, short life, and large added mass, a flight measurement method of blade load based on optical sensing is proposed. Firstly, the strain mode distribution law is obtained by calculating the dynamic response of the real blade. The optimal layout of the optical fiber measurement points is determined. Through theoretical analysis of strain transferring and experimental verification, a highly reliable fusion scheme of blade and fiber is designed to meet the flight requirements. Based on the power line carrier technology, the optical sensing test system for helicopter flight test is developed. The flight test of blade load is completed successfully. The results of optical fiber measurement are consistent with the results of traditional electrical measurement, which indicates that the optical sensing technology has good applicability in the measurement of helicopter blade load. At the same time, it has been proved that the optical measurement system set is reliable and durable. It is of great significance for the leap from electric measurement to optical measurement.

A portable dual-mode colorimetric and fluorescence sensing platform for RGB detection in liquid solutions

The color of liquids is crucial in food safety, pharmaceuticals, cosmetics, and environmental monitoring. Traditional color measurement methods typically require expensive spectrophotometers, limiting their utility in rapid testing and cost-effective applications. This study developed a cost-effective, portable dual-mode colorimetric and fluorescence sensing platform with using the TCS230 sensor and STM32F103ZET6 microcontroller for real-time RGB color detection. Equipped with built-in white and ultraviolet light sources, the platform operates reliably across different environmental conditions, aided by its darkroom design and white balance calibration strategy to minimize ambient light interference. Tests with fluorescent and dye solutions show stability and reliability of the platform. The relationship between color saturation and concentration under different concentrations showed the excellent correlation coefficients above 0.99 for CuSO4 and KMnO4 solutions. The measurement deviations of 1.93% to 3.41%, render it an efficient tool for on-site and multiple-mode color testing.

Design and testing of a low-cost mobile platform for contactless building surveying

After the completion of building construction, evaluating the accuracy of the distance between the lower edge of electrical switches and the one-meter line of the building is a crucial metric for assessing construction quality. Currently, the traditional measurement method basically uses manual measurement and is inefficient. To overcome this problem, we present a low-cost, non-contact mobile platform for building measurement, based on a 2D laser rangefinder and RGB camera. The system mainly consists of six key components: a mobile chassis, dual-axis gimbal, laser rangefinder, RGB camera, industrial control computer, and an automatic one-meter line calibration device, which can achieve high-precision distance measurement. Firstly, a sensorless control method for brushless DC motors (BLDCM) based on the Extended Kalman Filter (EKF) algorithm is proposed, which effectively improves the accuracy and robustness of rotor position estimation. Secondly, an automatic calibration device is developed to ensure the laser line consistently remains at a height of one meter from the ground. Finally, by combining image processing technology and 2D laser range data, the distance between the lower edge of the electrical switch and the building’s one-meter line is precisely measured using a triangulation algorithm. Experimental results show that the system’s measurements, compared to manual measurements, have a relative error percentage of 0.57%, while the automatic calibration device has a maximum error of only 0.2 centimeter. Therefore, the system shows great potential for widespread application in the field of building measurement.

A MLP architecture fusing RGB and CASSI for computational spectral imaging

The coded Aperture Snapshot Spectral Imaging (CASSI) system offers significant advantages in dynamically acquiring hyper-spectral images compared to traditional measurement methods. However, it faces the following challenges: (1) Traditional masks rely on random patterns or analytical design, limiting CASSI’s performance improvement. (2) Existing CASSI reconstruction algorithms do not fully utilize RGB information. (3) High-quality reconstruction algorithms are often slow and limited to offline scene reconstruction. To address these issues, this paper proposes a new MLP architecture, Spectral-Spatial MLP (SSMLP), which replaces the transformer structure with a network using CASSI measurements and RGB as multimodal inputs. This maintains reconstruction quality while significantly improving reconstruction speed. Additionally, we constructed a teacher-student network (SSMLP with a teacher, SSMLP-WT) to transfer the knowledge learned from a large model to a smaller network, further enhancing the smaller network’s accuracy. Extensive experiments show that SSMLP matches the performance of transformer-based structures in spectral image reconstruction while improving inference speed by at least 50%. The reconstruction quality of SSMLP-WT is further improved by knowledge transfer without changing the network, and the teacher boosts the performance by 0.92 dB (44.73 dB vs. 43.81 dB).