NIR Images Research Articles

Comparing Human Performance on Target Localization in Near Infrared and Long Wave Infrared for Cluttered Environments.

In the context of rapid advancements in AI, the accuracies and speeds among various AI models and methods are often compared. However, a basic question is rarely asked: is AI better than humans, and if so, under what conditions? This paper investigates human ability to detect distant landmark targets under cluttered surroundings such as buildings, trees, and clouds in NIR and LWIR images, aiming to facilitate AI object detection performance analysis. Our investigation employs perception tests and a human performance model to analyze object detection capabilities. The results reveal distinctive differences in NIR and LWIR detectability, showing that although LWIR performs less effectively at range, it offers superior robustness across various environmental conditions. Our findings suggest that AI could be particularly advantageous for object detection in LWIR as it outperform humans in terms of detection accuracy at a long range.

Development and In vitro and In vivo efficacy investigation of multifunctional, targeted, theranostic liposomes for imaging and photodynamic therapy of glioblastoma

The challenge of effectively diagnosing and treating glioblastoma, which has a high incidence and low survival rate, remains unresolved. Consequently, research efforts have increased to develop specific and effective diagnostic and therapeutic agents. In this study, N-acetyl glucosamine-modified, IR780-encapsulated, PEG-coated, nanosized, 68Ga-labeled, neutral, and positively charged theranostic liposomes were developed for GLUT1 targeting for PET/CT and NIR imaging and PDT/PTT of GBM. Characterization, in vitro release profile, stability, radiolabeling efficiency, and labeling stability were evaluated. In vitro cell uptake studies were conducted in RG2 and U87 GBM cell lines, NIR images were obtained in the RG2 and U87 cell lines, and fluorescence microscope images were obtained in the RG2 cell line. PDT/PTT activities were assessed after exposure to NIR light (808 nm, 0.8–1 W/cm2). Cytotoxicity was studied in RG2, U87, and L929 cell lines. In vivo studies were performed in GBM model nude mice. The liposomes had an optimum mean particle size (181–193 nm), high encapsulation efficiency (79–84 %), and zeta potential (−5 to −7 mV). The maximum 68Ga labeling efficiency was achieved with an incubation at 80 °C, pH: 3.5, and 5 min. Liposomes remained stable for 30 days at 4 °C. While the intracellular uptake of targeted formulations was higher than non-targeted ones, it was similar for positively charged and neutral formulations. In U87 and RG2 cell lines, cell viability remained above 50 % for liposomal formulations at a concentration of 1.5 μg/mL exposed to NIR light (808 nm, 0.8–1 W/cm2). The formulations showed significant PDT/PTT activity under NIR light and lower cytotoxicity in the L929 than in RG2 and U87 cell lines. In vivo bioluminescence images and biodistribution studies in U87 tumor-bearing nude mice revealed higher tumor uptake of targeted, IR780-encapsulated liposomal formulations in tumor tissue compared to non-targeted ones. Liposomal formulations showed higher tumor uptake than the free IR780 solution. The data suggest that targeted liposomes have potential as theranostic agents for PDT/PTT and multifunctional glioblastoma imaging.

Smart Ship Draft Reading by Dual-Flow Deep Learning Architecture and Multispectral Information.

In maritime transportation, a ship's draft survey serves as a primary method for weighing bulk cargo. The accuracy of the ship's draft reading determines the fairness of bulk cargo transactions. Human visual-based draft reading methods face issues such as safety concerns, high labor costs, and subjective interpretation. Therefore, some image processing methods are utilized to achieve automatic draft reading. However, due to the limitations in the spectral characteristics of RGB images, existing image processing methods are susceptible to water surface environmental interference, such as reflections. To solve this issue, we obtained and annotated 524 multispectral images of a ship's draft as the research dataset, marking the first application of integrating NIR information and RGB images for automatic draft reading tasks. Additionally, a dual-branch backbone named BIF is proposed to extract and combine spectral information from RGB and NIR images. The backbone network can be combined with the existing segmentation head and detection head to perform waterline segmentation and draft detection. By replacing the original ResNet-50 backbone of YOLOv8, we reached a mAP of 99.2% in the draft detection task. Similarly, combining UPerNet with our dual-branch backbone, the mIoU of the waterline segmentation task was improved from 98.9% to 99.3%. The inaccuracy of the draft reading is less than ±0.01 m, confirming the efficacy of our method for automatic draft reading tasks.

Cover Picture: Astron. Nachr. 6/2024

Color‐magnitude diagram of the lower mass end of the Main Sequence of globular cluster NGC 6752, as derived from NIR images of a deep field observed under a HST Large Programme led by L.R.Bedin. Three main stellar populations can be reliably distinguished within this cluster. The three isochrones (blue, green, and red lines) were computed with different chemical compositions, adjusted to match the observed colors of the different generations of stars at an age of 12.63 Gy. In the lower left part of the plot, the corresponding isochrone for the White Dwarfs (at an age of 12.5 Gy) is shown in purple, together with the three WD candidates shown as orange crosses. For each isochrone, specific mass values are marked by labeled filled dots. A detailed analysis of the HST data and a discussion of possible scenarios for the formation of multiple stellar populations within NGC 6752 is presented in the article by Scalco et al., this issue e240018. image

Design and Implementation of a Self-Supervised Algorithm for Vein Structural Patterns Analysis Using Advanced Unsupervised Techniques

Compared to other identity verification systems applications, vein patterns have the lowest potential for being used fraudulently. The present research examines the practicability of gathering vascular data from NIR images of veins. In this study, we propose a self-supervision learning algorithm that envisions an automated process to retrieve vascular patterns computationally using unsupervised approaches. This new self-learning algorithm sorts the vascular patterns into clusters and then uses 2D image data to recuperate the extracted vascular patterns linked to NIR templates. Our work incorporates multi-scale filtering followed by multi-scale feature extraction, recognition, identification, and matching. We design the ORC, GPO, and RDM algorithms with these inclusions and finally develop the vascular pattern mining model to visualize the computational retrieval of vascular patterns from NIR imageries. As a result, the developed self-supervised learning algorithm shows a 96.7% accuracy rate utilizing appropriate image quality assessment parameters. In our work, we also contend that we provide strategies that are both theoretically sound and practically efficient for concerns such as how many clusters should be used for specific tasks, which clustering technique should be used, how to set the threshold for single linkage algorithms, and how much data should be excluded as outliers. Consequently, we aim to circumvent Kleinberg’s impossibility while attaining significant clustering to develop a self-supervised learning algorithm using unsupervised methodologies.

The Impact of Illumination on Finger Vascular Pattern Recognition

This paper studies the impact of illumination direction and bundle width on finger vascular pattern imaging and recognition performance. A qualitative theoretical model is presented to explain the projection of finger blood vessels on the skin. A series of experiments were conducted using a scanner of our design with illumination from the top, a single-direction side (left or right), and narrow or wide beams. A new dataset was collected for the experiments, containing 4,428 NIR images of finger vein patterns captured under well-controlled conditions to minimize position and rotation angle differences between different sessions. Top illumination performs well because of more homogenous, which enhances a larger number of visible veins. Narrower bundles of light do not affect which veins are visible, but they reduce the overexposure at finger boundaries and increase the quality of vascular pattern images. The narrow beam achieves the best performance with 0% of FNMR@FMR0.01%, and the wide beam consistently results in a higher false nonmatch rate. The comparison of left- and right-side illumination has the highest error rates because only the veins in the middle of the finger are visible in both images. Different directional illumination may be interoperable since they produce the same vascular pattern and principally are the projected shadows on the finger surface. Score and image fusion for right- and left-side result in recognition performance similar to that obtained with top illumination, indicating the vein patterns are independent of illumination direction. All results of these experiments support the proposed model.

IFAST: Weakly Supervised Interpretable Face Anti-Spoofing From Single-Shot Binocular NIR Images

IFAST: Weakly Supervised Interpretable Face Anti-Spoofing From Single-Shot Binocular NIR Images

Reviewing Vegetation Indices for Mobile Application: Potentials and Challenges

Vegetation are quantitative metrics that are used to assess the density of vegetation as well as its health and vitality. Vegetation indices are important in precision agriculture and monitoring environmental conditions. For years, vegetation indices have been derived from remote sensing or aerial imaging data, with focus on large plantation estate and green coverage. Recently, there is a growing interest in using mobile phone for measuring vegetation indices at a more affordable cost. The spectral range for vegetation indices extends from 400 nm to 900 nm, which places it in the VIS and NIR spectral categories, respectively. The CMOS sensor that is typically found in mobile phone cameras has the capacity to capture NIR images. This paper aims to give a background in understanding vegetation indices available and weighing the suitability of using these indices for mobile applications. The potential of using these indices has been establish when the studies indicate several works have successfully used mobile phone camera to capture vegetation indices formulation, but still additional features is needed to ensure the standardisation and consistency of image calibration.

Cyclic style generative adversarial network for near infrared and visible light face recognition

Near Infrared and Visible Light (NIR-VIS) face recognition attracts attention from researchers because of its potential for safety, illumination invariance, and stability. Nevertheless, the difference between NIR and VIS domains, the domain gap, remains a huge problem for matching NIR and VIS images. Specifically, for the same identity, the appearance in the NIR domain is different from the VIS domain. Thus, traditional face recognition methods cannot be effective. To address this problem, this paper proposes a novel model, called Cyclic-Style GAN (CS-GAN). First, the pre-trained Style-GAN 3 network is embedded into the Cycle-GAN structure for NIR-VIS cross-domain learning. Second, there is a cyclic subspace learning method consisting of latent loss and style loss, through which both style (domain feature) and facial characteristic features are learned to improve the quality of synthesized images. The model synthesizes realistic VIS images from NIR images and does the face recognition task in the VIS domain. The proposed method achieves 99.6% Rank-1 accuracy on the CASIA NIR-VIS 2.0 database which is a state-of-the-art result. The visualization results show that the proposed model synthesizes VIS images with a clear texture of faces and in close-to-reality color.

Eye detection and coarse localization of pupil for video-based eye tracking systems

A video-based eye tracking system generally captures NIR images, each of which contains one or two eyes of a subject. The subject’s point of gaze is then determined using 3D eye model and pupil centre corneal reflection technique. Eye detection and pupil localization play significant roles in video-based eye tracking systems. However, face rotation, wearing glasses, eye-shape variation and illumination variation make it difficult to detect an eye and localize a pupil accurately in the images captured by video-based eye tracking systems. In this paper, we proposed an eye detector that adopts a coarse-to-fine strategy. The eye detector consists of three classifiers: an ATLBP-THACs feature-based cascade classifier, a branch CNN and a multi-task CNN. We also proposed a method for coarse pupil localization. Coarse localization is an important step for pupil localization since it can provide initial pupil coordinates for a fine pupil localization method. Given a downscaled eye image, a shallow CNN is used to estimate the location of seven landmarks. On this basis, pupil center and radius are estimated. A method for small dim target enhancement is used to increase the contrast between pupil and background. The main goal of pupil enhancement is to make it easier to binarize an eye image. At last, component filtering is made by utilizing the estimated pupil center and radius. We collected a dataset named neepuEYE dataset that consists of 5500 NIR eye images from 109 people. The images can be used to generate augmented samples for training an eye detector since they contain eyes with different shape, orientation and pupil localization. Experimental results show that our eye detector is a fast and robust detector. Furthermore, our method for coarse pupil localization can obtain not only high detection rate but also high localization speed.

Syncretic Space Learning Network for NIR-VIS Face Recognition

To overcome the technical bottleneck of face recognition in low-light scenarios, Near-InfraRed and VISible (NIR-VIS) heterogeneous face recognition is proposed for matching well-lit VIS faces with poorly lit NIR faces. Current cross-modal synthesis methods visually convert the NIR modality to the VIS modality and then perform face matching in the VIS modality. However, using a heavyweight GAN network on unpaired NIR-VIS faces may lead to high synthesis difficulty, low inference efficiency, and other problems. To alleviate the above problems, we simultaneously synthesize NIR and VIS images into modality-independent syncretic images and propose a novel syncretic space learning (SSL) model to eliminate the modal gap. First, Syncretic Modality Generator (SMG) synthesizes NIR and VIS images into syncretic images using channel-level convolution with a shallow CNN. In particular, the discriminative structural information is well preserved and the face quality can be further improved with small modal variations in a self-supervised learning manner. Second, Modality-adversarial Syncretic space Learning (MSL) projects NIR and VIS images into the syncretic space by a syncretic-modality adversarial learning strategy with syncretic pattern guided objective, so the modal gap of NIR-VIS faces can be effectively reduced. Finally, the Syncretic Distribution Consistency (SDC) constructed by NIR-syncretic, syncretic-syncretic, and VIS-syncretic consistency can enhance the intra-class compactness and learn discriminative representations. Extensive experiments on three challenging datasets demonstrate the effectiveness of the SSL method.

Rapid appearance quality of rice based on machine vision and convolutional neural network research on automatic detection system.

In the process of rice production and storage, there are many defects in the traditional detection methods of rice appearance quality, but using modern high-precision instruments to detect the appearance quality of rice has gradually developed into a new research trend at home and abroad with the development of agricultural artificial intelligence. In this study, we independently designed a fast automatic rice appearance quality detection system based on machine vision technology by introducing convolutional neural network and image processing technology. In this study, NIR and RGB images were generated into five-channel image data by superposition function, and image are preprocessed by combining the Watershed algorithm with the Otus adaptive threshold function. Different grains in the samples were labeled and put in the convolutional neural network for training. The rice grains were classified and the phenotype data were analyzed by selecting the optimal training model to realize the detection of rice appearance quality. The experimental results showed that the resolution of the system could reach 92.3%. In the detection process, the system designed with this method not only reduces the subjectivity problems caused by different detection environments, visual fatigue caused large sample size and the inspector's personal factors, but also significantly improves the detection time and accuracy, which further enhances the detection efficiency of rice appearance quality, and has positive significance for the development of the rice industry.

Phenomics based prediction of plant biomass and leaf area in wheat using machine learning approaches.

Phenomics has emerged as important tool to bridge the genotype-phenotype gap. To dissect complex traits such as highly dynamic plant growth, and quantification of its component traits over a different growth phase of plant will immensely help dissect genetic basis of biomass production. Based on RGB images, models have been developed to predict biomass recently. However, it is very challenging to find a model performing stable across experiments. In this study, we recorded RGB and NIR images of wheat germplasm and Recombinant Inbred Lines (RILs) of Raj3765xHD2329, and examined the use of multimodal images from RGB, NIR sensors and machine learning models to predict biomass and leaf area non-invasively. The image-based traits (i-Traits) containing geometric features, RGB based indices, RGB colour classes and NIR features were categorized into architectural traits and physiological traits. Total 77 i-Traits were selected for prediction of biomass and leaf area consisting of 35 architectural and 42 physiological traits. We have shown that different biomass related traits such as fresh weight, dry weight and shoot area can be predicted accurately from RGB and NIR images using 16 machine learning models. We applied the models on two consecutive years of experiments and found that measurement accuracies were similar suggesting the generalized nature of models. Results showed that all biomass-related traits could be estimated with about 90% accuracy but the performance of model BLASSO was relatively stable and high in all the traits and experiments. The R2 of BLASSO for fresh weight prediction was 0.96 (both year experiments), for dry weight prediction was 0.90 (Experiment 1) and 0.93 (Experiment 2) and for shoot area prediction 0.96 (Experiment 1) and 0.93 (Experiment 2). Also, the RMSRE of BLASSO for fresh weight prediction was 0.53 (Experiment 1) and 0.24 (Experiment 2), for dry weight prediction was 0.85 (Experiment 1) and 0.25 (Experiment 2) and for shoot area prediction 0.59 (Experiment 1) and 0.53 (Experiment 2). Based on the quantification power analysis of i-Traits, the determinants of biomass accumulation were found which contains both architectural and physiological traits. The best predictor i-Trait for fresh weight and dry weight prediction was Area_SV and for shoot area prediction was projected shoot area. These results will be helpful for identification and genetic basis dissection of major determinants of biomass accumulation and also non-invasive high throughput estimation of plant growth during different phenological stages can identify hitherto uncovered genes for biomass production and its deployment in crop improvement for breaking the yield plateau.

Study on the detection of water status of tomato (Solanum lycopersicum L.) by multimodal deep learning.

Water plays a very important role in the growth of tomato (Solanum lycopersicum L.), and how to detect the water status of tomato is the key to precise irrigation. The objective of this study is to detect the water status of tomato by fusing RGB, NIR and depth image information through deep learning. Five irrigation levels were set to cultivate tomatoes in different water states, with irrigation amounts of 150%, 125%, 100%, 75%, and 50% of reference evapotranspiration calculated by a modified Penman-Monteith equation, respectively. The water status of tomatoes was divided into five categories: severely irrigated deficit, slightly irrigated deficit, moderately irrigated, slightly over-irrigated, and severely over-irrigated. RGB images, depth images and NIR images of the upper part of the tomato plant were taken as data sets. The data sets were used to train and test the tomato water status detection models built with single-mode and multimodal deep learning networks, respectively. In the single-mode deep learning network, two CNNs, VGG-16 and Resnet-50, were trained on a single RGB image, a depth image, or a NIR image for a total of six cases. In the multimodal deep learning network, two or more of the RGB images, depth images and NIR images were trained with VGG-16 or Resnet-50, respectively, for a total of 20 combinations. Results showed that the accuracy of tomato water status detection based on single-mode deep learning ranged from 88.97% to 93.09%, while the accuracy of tomato water status detection based on multimodal deep learning ranged from 93.09% to 99.18%. The multimodal deep learning significantly outperformed the single-modal deep learning. The tomato water status detection model built using a multimodal deep learning network with ResNet-50 for RGB images and VGG-16 for depth and NIR images was optimal. This study provides a novel method for non-destructive detection of water status of tomato and gives a reference for precise irrigation management.

Detection and Classification of Saffron Adulterants by Vis-Nir Imaging, Chemical Analysis, and Soft Computing.

Saffron (Crocus sativus L.) is the most expensive spice in the world, known for its unique aroma and coloring in the food industry. Hence, its high price is frequently adulterated. In the current study, a variety of soft computing methods, including classifiers (i.e., RBF, MLP, KNN, SVM, SOM, and LVQ), were employed to classify four samples of fake saffron (dyed citrus blossom, safflower, dyed fibers, and mixed stigma with stamens) and three samples of genuine saffron (dried by different methods). RGB and spectral images (near-infrared and red bands) were captured from prepared samples for analysis. The amount of crocin, safranal, and picrocrocin were measured chemically to compare the images' analysis results. The comparison results of the classifiers indicated that KNN could classify RGB and NIR images of samples in the training phase with 100% accuracy. However, KNN's accuracy for different samples in the test phase was between 71.31% and 88.10%. The RBF neural network achieved the highest accuracy in training, test, and total phases. The accuracy of 99.52% and 94.74% was obtained using the features extracted from RGB and spectral images, respectively. So, soft computing models are helpful tools for detecting and classifying fake and genuine saffron based on RGB and spectral images.

Automated observation of physical snowpack properties in Ny-Ålesund

The snow season in the Svalbard archipelago generally lasts 6–10 months a year and significantly impacts the regional climate, glaciers mass balance, permafrost thermal regime and ecology. Due to the lack of long-term continuous snowpack physical data, it is still challenging for the numerical snow physics models to simulate multi-layer snowpack evolution, especially for remote Arctic areas. To fill this gap, in November 2020, an automated nivometric station (ANS) was installed ∼1 km Southwest from the settlement of Ny-Ålesund (Spitzbergen, Svalbard), in a flat area over the lowland tundra. It automatically provides continuous snow data, including NIR images of the fractional snow-cover area (fSCA), snow depth (SD), internal snow temperature and liquid water content (LWC) profiles at different depths with a 10 min time resolution. Here we present the first-year record of automatic snow preliminary measurements collected between November 2020 and July 2021 together with weekly manual observations for comparison. The snow season at the ANS site lasted for 225 days with an annual net accumulation of 117 cm (392 mm of water equivalent). The LWC in the snowpack was generally low (<4%) during wintertime, nevertheless, we observed three snow-melting events between November and February 2021 and one in June 2021, connected with positive temperature and rain on snow events (ROS). In view of the foreseen future developments, the ANS is the first automated, comprehensive snowpack monitoring system in Ny-Ålesund measuring key essential climate variables needed to understand the seasonal evolution of the snow cover on land.

Influence of unregulated storage conditions on physico-chemical, organoleptic and NIR spectral characteristics of yellow cheese

In the present work, software and hardware tools are proposed for determining the change in the main characteristics of Bulgarian yellow cheese during storage in conditions not regulated by the manufacturers. NIR images in the 800-1100 nm range of yellow cheese samples from 3 manufacturers were obtained using a GT-903 video camera with the IR-filter removed from the camera lens. Several physicochemical characteristics of the product were determined - active acidity, electrical conductivity and completely dissolved solids. Data from organoleptic evaluation of the product are presented. Using ABC- XYZ analysis, informative wavelengths are selected from the spectral features. Spectral indices calculated as ratios of the reflectance coefficients of selected wavelengths were defined and used to predict the storage characteristics of yellow cheese. It has been found that the shelf life of yellow cheese can be predicted with an accuracy of up to 95%, and the active acidity with an accuracy of up to 88%, depending on the manufacturer. The obtained results can be used for analyzes of yellow cheese during its storage and applied in automatic measurement and control systems, as well as in advisory systems for evaluating the quality of yellow cheese in the different stages of its production, transport and storage.

Automatic Method for Segmentation of Fluorescent Images Obtained in the Near-Infrared Region

Introduction. Near-infrared fluorescence imaging technology is widely used in laparoscopic surgery. Intraoperative fluorescence navigation is based on accurate segmentation of fluorescent regions in near-infrared images (NIR images), thus increasing the accuracy and safety of surgical intervention. Moreover, it is an important auxiliary technology for laparoscopic surgery. Therefore, the search for an automatic method that allows for accurate segmentation of fluorescent regions in NIR images can contribute to an improved efficiency of intraoperative navigation.Aim. Development of a method for automatic segmentation of fluorescent images obtained in the near infrared range. Materials and methods. The proposed method consists of two stages. At the first stage, a preliminary segmentation of the image is performed based on the adaptive threshold found by Otsu’s method. At the second stage, the segmented area is refined using Otsu’s weighted method. The main advantage of the proposed method consists in the automatic determination of parameter α, which determines the performance of Otsu’s weighted method. Experiments were carried out using 276 actual laparoscopic images. The metric misclassification error (ME) was used to assess the quality of segmentation.Results. The average ME of the proposed method was found to be 10.4 %, compared to that obtained by the conventional Otsu’s method of 27.1 %.Conclusion. In comparison with Otsu’s method, the developed method shows an increased efficiency and accuracy of fluorescent image segmentation. This allows for a higher diagnostic accuracy and a more efficient navigation during laparoscopic surgery.

LRINet: Long-range imaging using multispectral fusion of RGB and NIR images

When imaging at a long distance by ordinary visible cameras, the wavelength of visible light is easily interfered by fog or atmospheric effects, resulting in blurry or lost details in RGB images. However, NIR cameras are robust to the long distance imaging without color. In this paper, we propose long-range imaging using multispectral fusion of RGB and NIR images, called LRINet. We adopt unsupervised learning for the fusion to solve the absence of ground truth. LRINet is an end-to-end network based on convolutional neural networks (CNNs) that consists of three steps for the multispectral fusion: feature extraction, fusion and reconstruction. To align unpaired data and treat the discrepancy between RGB and NIR images, we construct WarpingNet to warp NIR features, and add it into the feature extraction. Since dark channel prior (DCP) provides distance from the camera by light transmission degree, we combine it with structure loss as the weight for fusion. To ensure the color fidelity, LRINet operates the fusion on the input of the RGB luma channel and NIR image. Experimental results show that LRINet produces natural-looking color images with clear details by successfully treating discrepancy between RGB and NIR images and outperforms state-of-art fusion models in term of both visual quality and quantitative measurements.

Estimation of chlorophyll distribution in banana canopy based on RGB-NIR image correction for uneven illumination

Chlorophyll generally measured by Soil and Plant Analysis Development (SPAD) meter is an important indicator for the evaluation of plant photosynthesis ability and growth status. In view of the uneven distribution of illumination on broad-leaved banana canopy in the field, a correction method based on dark channel prior (DCP) is proposed to enhance the image quality, and improve the estimating accuracy of chlorophyll content. First, RGB (Red, Green, Blue) and NIR (near-infrared band) images of banana plant were separately obtained, and the two images were matched and aligned after preprocessing. Second, the channels in the region of interest (ROI) were split and restructured. The restructured image was corrected based on the DCP principle. Then, the optimal channels were selected according to the correlation analysis to form a new RGB (NewRGB) image, to simplify that OriRGB-NIR and NewRGB-NIR indicated the multispectral image before and after correction. The image features related to color features (CFs) and vegetation indices (VIs) were extracted and optimized as input variables for the chlorophyll estimation modeling. Finally, the random forest regression (RFR) was used to build the SPAD value estimation models, in which OriRGB-NIR-RFR model and the NewRGB-NIR-RFR model were named to show the results before and after image correction. Results show that the proposed correction method of uneven illumination reduced the image contrast and obtained more uniform values. At the same time, the accuracy of the model after correction was higher than that prior to correction. The modeling Rv2 of NewRGB-NIR-RFR with 11 variables reached 0.692. As a result, the visual distribution map of chlorophyll SPAD values was established, thereby providing the basis for the dynamic monitoring of crop nutrition.