Hyperspectral Reflectance Imaging System Research Articles

Measurement of rat and human tissue optical properties for improving the optical detection and visualization of peripheral nerves.

Peripheral nerve damage frequently occurs in challenging surgical cases resulting in high costs and morbidity. Various optical techniques have proven effective in detecting and visually enhancing nerves, demonstrating their translational potential for assisting in nerve-sparing medical procedures. However, there is limited data characterizing the optical properties of nerves in comparison to surrounding tissues, thus limiting the optimization of optical nerve detection systems. To address this gap, the absorption and scattering properties of rat and human nerve, muscle, fat, and tendon were determined from 352-2500 nm. The optical properties highlighted an ideal region in the shortwave infrared for detecting embedded nerves, which remains a significant challenge for optical approaches. A 1000-1700 nm hyperspectral diffuse reflectance imaging system was used to confirm these results and identify optimal wavelengths for nerve imaging contrast in an in vivo rat model. Optimal nerve visualization contrast was achieved using 1190/1100 nm ratiometric imaging and was sustained for nerves embedded under ≥600 µm of fat and muscle. Overall, the results provide valuable insights for optimizing the optical contrast of nerves, including those embedded in tissue, which could lead to improved surgical guidance and nerve-sparing outcomes.

Identification of Chilling Injury in Kiwifruit Using Hyperspectral Structured-Illumination Reflectance Imaging System (SIRI) with Support Vector Machine (SVM) Modelling

Accurate detection of chilling injury in kiwifruit is challenging because the symptoms are mainly manifested in the interior. This work reports a method for detecting the chilling injury of ‘Hongyang’ kiwifruit to provide nondestructive discrimination. Kiwifruit samples with varying levels of chilling injury were analyzed by a hyperspectral structured-illumination reflectance imaging (SIRI) system. After demodulation, direct current (DC) and alternating current (AC) images with spatial frequencies of 30, 60, and 120 m−1 were obtained and labeled as F30, F60, and F120. Predictive models were developed to optimize the preprocessing and modeling methods. Prediction models established the results of DC and AC with different spatial frequencies and were compared. The autoscale-support vector machine (SVM) models were optimal for AC at different spatial frequencies, and the multiplicative scatter correction (MSC)-SVM model was optimal for DC. The combined features of F30, F60, and F120, as well as the spectral features of DC, had better accuracy for classifying chilling injury. The optimal model of hyperspectral SIRI system for detecting chilling injury was the F30 based on combined features, with calibration accuracy of 98.1% and prediction accuracy of 94.2%. This study has shown that structured illumination had higher accuracy than uniform illumination in predicting chilling injury. Further, this approach allows the identification of kiwifruit with chilling injury using a hyperspectral structured-illumination reflectance imaging system.

Finite Element Analysis and Near-Infrared Hyperspectral Reflectance Imaging for the Determination of Blueberry Bruise Grading.

Bruising of the subcutaneous tissues of blueberries is an important form of mechanical damage. Different levels of bruising have a significant effect on the post-harvest marketing of blueberries. To distinguish different grades of blueberry bruises and explore the effects of different factors, explicit dynamic simulation and near-infrared hyperspectral reflectance imaging were employed without harming the blueberries in this study. Based on the results of the compression experiment, an explicit dynamic simulation of blueberries was performed to measure the potential locations of bruises and preliminarily divide the bruise stages. A near-infrared hyperspectral reflectance imaging system was used to detect the actual blueberry bruises. According to the blueberry photos taken by the near-infrared hyperspectral reflectance imaging system, the actual bruise rates of blueberries were obtained by using the Environment for Visualizing Images software for training and classification. Bruise grades of blueberries were divided accordingly. Response surface methodology was used to determine the effects of ripeness, loading speed and loading location on the blueberry bruising rate. Under the optimized parameters, the actual damage rate of blueberries was 1.1%. The results provide an important theoretical basis for the accurate and rapid identification and classification of blueberry bruise damage.

Early Detection of Tomato Spotted Wilt Virus by Hyperspectral Imaging and Outlier Removal Auxiliary Classifier Generative Adversarial Nets (OR-AC-GAN)

Tomato spotted wilt virus is a wide-spread plant disease in the world. It can threaten thousands of plants with a persistent and propagative manner. Early disease detection is expected to be able to control the disease spread, to facilitate management practice, and further to guarantee accompanying economic benefits. Hyperspectral imaging, a powerful remote sensing tool, has been widely applied in different science fields, especially in plant science domain. Rich spectral information makes disease detection possible before visible disease symptoms showing up. In the paper, a new hyperspectral analysis proximal sensing method based on generative adversarial nets (GAN) is proposed, named as outlier removal auxiliary classifier generative adversarial nets (OR-AC-GAN). It is an all-in-one method, which integrates the tasks of plant segmentation, spectrum classification and image classification. The model focuses on image pixels, which can effectively visualize potential plant disease positions, and keep experts’ attention on these diseased pixels. Meanwhile, this new model can improve the performances of classic spectrum band selection methods, including the maximum variance principle component analysis (MVPCA), fast density-peak-based clustering, and similarity-based unsupervised band selection. Selecting spectrum wavebands reasonably is an important preprocessing step in spectroscopy/hyperspectral analysis applications, which can reduce the computation time for potential in-field applications, affect the prediction results and make the hyperspectral analysis results explainable. In the experiment, the hyperspectral reflectance imaging system covers the spectral range from 395 nm to 1005 nm. The proprosed model makes use of 83 bands to do the analysis. The plant level classification accuracy gets 96.25% before visible symptoms shows up. The pixel prediction false positive rate in healthy plants gets as low as 1.47%. Combining the OR-AC-GAN with three existing band selection algorithms, the performance of these band selection models can be significantly improved. Among them, MVPCA can leverage only 8 spectrum bands to get the same plant level classification accuracy as OR-AC-GAN, and the pixel prediction false positive rate in healthy plants is 1.57%, which is also comparable to OR-AC-GAN. This new model can be potentially transferred to other plant diseases detection applications. Its property to boost the performance of existing band selection methods can also accelerate the in-field applications of hyperspectral imaging technology.

Development of Noninvasive Classification Methods for Different Roasting Degrees of Coffee Beans Using Hyperspectral Imaging.

This study aimed to develop an approach for quickly and noninvasively differentiating the roasting degrees of coffee beans using hyperspectral imaging (HSI). The qualitative properties of seven roasting degrees of coffee beans (unroasted, light, moderately light, light medium, medium, moderately dark, and dark) were assayed, including moisture, crude fat, trigonelline, chlorogenic acid, and caffeine contents. These properties were influenced greatly by the respective roasting degree. Their hyperspectral images (874–1734 nm) were collected using a hyperspectral reflectance imaging system. The spectra of the regions of interest were manually extracted from the HSI images. Then, principal components analysis was employed to compress the spectral data and select the optimal wavelengths based on loading weight analysis. Meanwhile, the random frog (RF) methodology and the successive projections algorithm were also adopted to pick effective wavelengths from the spectral data. Finally, least squares support vector machine (LS-SVM) was utilized to establish discriminative models using spectral reflectance and corresponding labeled classes for each degree of roast sample. The results showed that the LS-SVM model, established by the RF selecting method, with eight wavelengths performed very well, achieving an overall classification accuracy of 90.30%. In conclusion, HSI was illustrated as a potential technique for noninvasively classifying the roasting degrees of coffee beans and might have an important application for the development of nondestructive, real-time, and portable sensors to monitor the roasting process of coffee beans.

Identification of Bruise and Fungi Contamination in Strawberries Using Hyperspectral Imaging Technology and Multivariate Analysis

Mechanical bruise and fungi contamination are two typical defective features for strawberries, resulting in quick quality deterioration of the strawberries during transportation and storage. In this work, the approach of combined image processing with spectra analysis was successfully developed to identify defective strawberries (bruised and fungal infected) using hyperspectral reflectance imaging system. Hyperspectral image data was exploited by minimum noise fraction (MNF) transformation for strawberry defects distinguished by combining thresholding and morphology procedures, and defective regions were located and separated for spectra extracting. The linkages between quality parameters and spectra features were established based on the target defective regions of the fruit. After spectra normalization, three different spectral regions (400 to 600 nm, 650 to 720 nm, and 900 to 1010 nm) were identified for healthy, bruised, or infected strawberries, and eight optimal wavelengths were selected by the successive projection algorithms (SPA) from the whole range of wavelengths. Both linear and non-linear algorithms were developed to identify defective types in strawberries. The results indicated that based on full wavelengths, SVM model performed the highest overall identification accuracy, with the accuracy of 96.91% for calibration and 92.59% for prediction of the fruit. This work shows that hyperspectral reflectance imaging technology has the potential for identifying defective strawberries and provides theoretical basis for the development of online classification of different defected fruits.

Hyperspectral Imaging for Predicting the Internal Quality of Kiwifruits Based on Variable Selection Algorithms and Chemometric Models

We investigated the feasibility and potentiality of determining firmness, soluble solids content (SSC), and pH in kiwifruits using hyperspectral imaging, combined with variable selection methods and calibration models. The images were acquired by a push-broom hyperspectral reflectance imaging system covering two spectral ranges. Weighted regression coefficients (BW), successive projections algorithm (SPA) and genetic algorithm–partial least square (GAPLS) were compared and evaluated for the selection of effective wavelengths. Moreover, multiple linear regression (MLR), partial least squares regression and least squares support vector machine (LS-SVM) were developed to predict quality attributes quantitatively using effective wavelengths. The established models, particularly SPA-MLR, SPA-LS-SVM and GAPLS-LS-SVM, performed well. The SPA-MLR models for firmness (Rpre = 0.9812, RPD = 5.17) and SSC (Rpre = 0.9523, RPD = 3.26) at 380–1023 nm showed excellent performance, whereas GAPLS-LS-SVM was the optimal model at 874–1734 nm for predicting pH (Rpre = 0.9070, RPD = 2.60). Image processing algorithms were developed to transfer the predictive model in every pixel to generate prediction maps that visualize the spatial distribution of firmness and SSC. Hence, the results clearly demonstrated that hyperspectral imaging has the potential as a fast and non-invasive method to predict the quality attributes of kiwifruits.

Hyperspectral Imaging for Presymptomatic Detection of Tobacco Disease with Successive Projections Algorithm and Machine-learning Classifiers

We investigated the feasibility and potentiality of presymptomatic detection of tobacco disease using hyperspectral imaging, combined with the variable selection method and machine-learning classifiers. Images from healthy and TMV-infected leaves with 2, 4, and 6 days post infection were acquired by a pushbroom hyperspectral reflectance imaging system covering the spectral range of 380–1023 nm. Successive projections algorithm was evaluated for effective wavelengths (EWs) selection. Four texture features, including contrast, correlation, entropy, and homogeneity were extracted according to grey-level co-occurrence matrix (GLCM). Additionally, different machine-learning algorithms were developed and compared to detect and classify disease stages with EWs, texture features and data fusion respectively. The performance of chemometric models with data fusion manifested better results with classification accuracies of calibration and prediction all above 80% than those only using EWs or texture features; the accuracies were up to 95% employing back propagation neural network (BPNN), extreme learning machine (ELM), and least squares support vector machine (LS-SVM) models. Hence, hyperspectral imaging has the potential as a fast and non-invasive method to identify infected leaves in a short period of time (i.e. 48 h) in comparison to the reference images (5 days for visible symptoms of infection, 11 days for typical symptoms).

Automatic Identification of Rock-Forming Minerals in Granite Using Laboratory Scale Hyperspectral Reflectance Imaging and Artificial Neural Networks

Laser cleaning of stones is a well-established technique in conservation of Cultural Heritage. In case of polymineralic granular rocks like granite, the tuning of the laser parameters for safe cleaning becomes a demanding task due to the differential response of the constituent minerals to laser irradiation. In this sense, a compromise solution must be reached between removing unwanted layers and safeguarding the original characteristics of the stone substrate. Consequently, the need of non-invasive, rapid and accurate methods for in situ identification of the minerals in the stone surface is highlighted. The aim of this paper is to demonstrate the ability of a laboratory scale hyperspectral reflectance imaging system, in combination with artificial neural networks for in situ, accurate identification of constituent minerals of a hercynian granite; with the ultimate goal of achieving automatic adjustment of laser irradiation parameters in cleaning processes. The effectiveness of a neural network with the structure of a three-layer perceptron was evaluated by comparing calculated results with modal analysis composition obtained by petrographic microscope and a high degree of accordance, above 95%, was achieved.

Rapid prototyping of biomimetic vascular phantoms for hyperspectral reflectance imaging.

The emerging technique of rapid prototyping with three-dimensional (3-D) printers provides a simple yet revolutionary method for fabricating objects with arbitrary geometry. The use of 3-D printing for generating morphologically biomimetic tissue phantoms based on medical images represents a potentially major advance over existing phantom approaches. Toward the goal of image-defined phantoms, we converted a segmented fundus image of the human retina into a matrix format and edited it to achieve a geometry suitable for printing. Phantoms with vessel-simulating channels were then printed using a photoreactive resin providing biologically relevant turbidity, as determined by spectrophotometry. The morphology of printed vessels was validated by x-ray microcomputed tomography. Channels were filled with hemoglobin (Hb) solutions undergoing desaturation, and phantoms were imaged with a near-infrared hyperspectral reflectance imaging system. Additionally, a phantom was printed incorporating two disjoint vascular networks at different depths, each filled with Hb solutions at different saturation levels. Light propagation effects noted during these measurements—including the influence of vessel density and depth on Hb concentration and saturation estimates, and the effect of wavelength on vessel visualization depth—were evaluated. Overall, our findings indicated that 3-D-printed biomimetic phantoms hold significant potential as realistic and practical tools for elucidating light–tissue interactions and characterizing biophotonic system performance.

Estimating blueberry mechanical properties based on random frog selected hyperspectral data

A hyperspectral reflectance and transmittance imaging system was developed to non-destructively evaluate the comprehensive mechanical properties of blueberry. Reflectance and transmittance spectra were extracted from segmented hyperspectral images of whole fruit and correlated with fruit mechanical properties obtained from texture profile analysis and puncture analysis using least squares-support vector machine. A random frog spectral selection approach was applied to collect informative wavelengths. Prediction models based on random frog selected reflectance and transmittance spectra gave similar results to those based on respective full spectra. Combined spectra with single random frog, which were obtained by combining random frog selected reflectance and transmittance into one spectral vector, were feasible for predicting hardness, springiness, resilience, force max and final force, with Rp (RPD) values of 0.86 (1.78), 0.72 (1.73), 0.79 (1.78), 0.77 (1.51) and 0.84 (1.72), respectively. When applying random frog again for combined spectra with single random frog, the obtained models were also satisfactory with fewer wavelengths. In conclusion, the use of hyperspectral reflectance and transmittance as well as their combined spectra, coupled with random frog approach, showed a considerable potential for predicting blueberry mechanical properties.

Real-time evaluation of polyphenol oxidase (PPO) activity in lychee pericarp based on weighted combination of spectral data and image features as determined by fuzzy neural network

A novel method of using hyperspectral imaging technique with the weighted combination of spectral data and image features by fuzzy neural network (FNN) was proposed for real-time prediction of polyphenol oxidase (PPO) activity in lychee pericarp. Lychee images were obtained by a hyperspectral reflectance imaging system operating in the range of 400–1000nm. A support vector machine-recursive feature elimination (SVM-RFE) algorithm was applied to eliminating variables with no or little information for the prediction from all bands, resulting in a reduced set of optimal wavelengths. Spectral information at the optimal wavelengths and image color features were then used respectively to develop calibration models for the prediction of PPO in pericarp during storage, and the results of two models were compared. In order to improve the prediction accuracy, a decision strategy was developed based on weighted combination of spectral data and image features, in which the weights were determined by FNN for a better estimation of PPO activity. The results showed that the combined decision model was the best among all of the calibration models, with high R2 values of 0.9117 and 0.9072 and low RMSEs of 0.45% and 0.459% for calibration and prediction, respectively. These results demonstrate that the proposed weighted combined decision method has great potential for improving model performance. The proposed technique could be used for a better prediction of other internal and external quality attributes of fruits.

Development of a Hyperspectral Imaging System for the Early Detection of Apple Rottenness Caused by Penicillium

AbstractAutomatic detection of early rottenness caused by Penicillium is still a challenge due to the high similarity between the rotten region and sound tissue, and the large variations in surface background color of apples. A hyperspectral reflectance imaging system and a systematic approach were developed to detect the early rottenness caused by Penicillium on Fuji apples. The principal component analysis of the hyperspectral reflectance images in the full region (400–1,000 nm) of spectra was used to develop hyperspectral image analytical algorithm and select the efficient wavelengths. Independent component analysis (ICA) based on the selected efficient wavelengths (810 and 970 nm, respectively) and simple thresholding methods were used to segment and classify the rottenness from the sound tissue. Finally, ICA‐based image processing and classification algorithm was developed based on the images at 810 and 970 nm to realize the fast inspection of early rottenness. The detection result with 97% overall accuracy indicated that the proposed system and algorithm were efficient and suitable for the detection of the early rottenness caused by Penicillium on Fuji apples. This study was the first attempt to use hyperspectral imaging system to detect the early rottenness caused by Penicillium on Fuji apples and would lay a foundation for the development of multispectral imaging system for fast inspection of rottenness. The limitation of our research is the limited inspection view of the samples. Future work will be focused on simultaneous whole surface inspection using multispectral imaging system.Practical ApplicationsThe algorithm and results in our paper can provide a foundational basis to develop a real‐time inspection system to detect rottenness on apples in the postharvest processing line, or develop a monitoring system to monitor the quality changes in storage shelf.

Detection of Early Rottenness on Apples by Using Hyperspectral Imaging Combined with Spectral Analysis and Image Processing

Detection of early rottenness on apples is still a challenging task for the automatic grading system due to the highly similarity between the rotten and sound tissues both in spectral and spatial domains. This research was conducted to develop an algorithm for detecting the early rottenness on apples by using hyperspectral reflectance imaging system combined with spectral analysis and image processing. In spectral domain, chemometric and pattern recognition methods were conducted for spectral analysis. In order to select the candidate optimal wavelengths that carry the most important information for distinguishing the rottenness from the sound tissues, successive projections algorithm (SPA) was conducted on the full range of average spectra extracted from the (regions of interest (ROIs) of sound and rotten tissues. The efficiency of the selected candidate optimal wavelengths for rottenness detection was also testified by using a binary particle least square discriminant analysis (PLS-DA) classifier in the spectral domain. In spatial domain, combined image processing methods were conducted for spatial analysis. In order to verify that the images at the optimal wavelengths were efficient and develop a robust detection algorithm, both principal component analysis (PCA) and minimum noise fraction (MNF) combined with conventional image processing methods were conducted on the images at the optimal wavelengths for image processing. Finally, the whole detection algorithm based on SPA-PLS-DA-MNF by using hyperspectral imaging combined with spectral analysis and image processing was designed and testified by the 120 testing apples. The results with 98 % overall detection accuracy indicated that the proposed algorithm was efficient and suitable for the rottenness apple detection. This research provides a foundational basis to develop the fast online inspection or real-time monitoring system for rottenness detection on apples both in the postharvest processing line or storage shelf.

Hyperspectral Imaging Coupled with Random Frog and Calibration Models for Assessment of Total Soluble Solids in Mulberries.

Chemometrics methods coupled with hyperspectral imaging technology in visible and near infrared (Vis/NIR) region (380–1030 nm) were introduced to assess total soluble solids (TSS) in mulberries. Hyperspectral images of 310 mulberries were acquired by hyperspectral reflectance imaging system (512 bands) and their corresponding TSS contents were measured by a Brix meter. Random frog (RF) method was used to select important wavelengths from the full wavelengths. TSS values in mulberry fruits were predicted by partial least squares regression (PLSR) and least-square support vector machine (LS-SVM) models based on full wavelengths and the selected important wavelengths. The optimal PLSR model with 23 important wavelengths was employed to visualise the spatial distribution of TSS in tested samples, and TSS concentrations in mulberries were revealed through the TSS spatial distribution. The results declared that hyperspectral imaging is promising for determining the spatial distribution of TSS content in mulberry fruits, which provides a reference for detecting the internal quality of fruits.

Detection of cracks on tomatoes using a hyperspectral near-infrared reflectance imaging system.

The objective of this study was to evaluate the use of hyperspectral near-infrared (NIR) reflectance imaging techniques for detecting cuticle cracks on tomatoes. A hyperspectral NIR reflectance imaging system that analyzed the spectral region of 1000–1700 nm was used to obtain hyperspectral reflectance images of 224 tomatoes: 112 with and 112 without cracks along the stem-scar region. The hyperspectral images were subjected to partial least square discriminant analysis (PLS-DA) to classify and detect cracks on the tomatoes. Two morphological features, roundness (R) and minimum-maximum distance (D), were calculated from the PLS-DA images to quantify the shape of the stem scar. Linear discriminant analysis (LDA) and a support vector machine (SVM) were then used to classify R and D. The results revealed 94.6% and 96.4% accuracy for classifications made using LDA and SVM, respectively, for tomatoes with and without crack defects. These data suggest that the hyperspectral near-infrared reflectance imaging system, in addition to traditional NIR spectroscopy-based methods, could potentially be used to detect crack defects on tomatoes and perform quality assessments.

Three-dimensional printing of tissue phantoms for biophotonic imaging.

We have investigated the potential of tissue phantoms fabricated with thermosoftening- and photopolymerization-based three-dimensional (3D) printers for use in evaluation of biophotonic imaging systems. The optical properties of printed polymer samples were measured and compared to biological tissues. Phantoms with subsurface channels as small as 0.2mm in diameter were fabricated and imaged with microscopy, x-ray microtomography, and optical coherence tomography to characterize morphology. These phantoms were then implemented to evaluate the penetration depth of a hyperspectral reflectance imaging system used in conjunction with a near-infrared contrast agent. Results indicated that 3D printing may provide a suitable platform for performance testing in biophotonics, although subsurface imaging is critical to mitigate printer-to-printer variability in matrix homogeneity and feature microstructure.

초분광 반사광 영상을 이용한 무(Raphanus sativus L) 종자의 발아와 불발아 비파괴 판별

Purpose: Nondestructive evaluation of seed viability is a highly demanded technique in the seed industry. In this study, hyperspectral imaging system was used for discrimination of viable and non-viable radish seeds. Method: The spectral data with the range from 400 to 1000 nm measured by hyperspectral reflectance imaging system were used. A calibration and a test models were developed by partial least square discrimination analysis (PLS-DA) for classification of viable and non-viable radish seeds. Either each data set of visible (400~750 nm) and NIR (750~1000 nm) spectra and the spectra of the combined spectral ranges were used for developing models. Results: The discrimination accuracy of calibration was 84% for visible range and 76.3% for NIR range. The discrimination accuracy of test was 84.2% for visible range and 75.8% for NIR range. The discrimination accuracies of calibration and test with full range were 92.2% and 92.5%, respectively. The resultant images based on the optimal PLS-DA model showed high performance for the discrimination of the nonviable seeds from the viable seeds with the accuracy of 95%. Conclusions: The results showed that hyperspectral reflectance imaging has good potential for discriminating nonviable radish seeds from massive amounts of viable seeds.

초분광 영상을 이용한 송이토마토의 비파괴 품질 예측

Spectroscopic measurement method based on visible and near-infrared wavelengths was prominent technology for rapid and non-destructive evaluation of internal quality of fruits. Reflectance measurement was performed to evaluate firmness, soluble solid content, and acid content of truss tomatoes by hyperspectral reflectance imaging system. The Vis/NIR reflectance spectra was acquired from truss tomatoes sorted by 6 ripening stages. The multivariable analysis based on partial least square (PLS) was used to develop regression models with several preporcessing methods, such as smoothing, normalization, multiplicative scatter correction (MSC), and standard normal variate (SNV). The best model was selected in terms of coefficient of determination of calibration (<TEX>$R_c^2$</TEX>) and full cross validation (<TEX>$R_{cv}^2$</TEX>), and root mean standard error of calibration (RMSEC) and full cross validation (RMSECV). The results of selected models were 0.8976 (<TEX>$R_p^2$</TEX>), 6.0207 kgf (RMSEP) with gaussian filter of smoothing, 0.8379 (<TEX>$R_p^2$</TEX>), <TEX>$0.2674^{\circ}Bx$</TEX> (RMSEP) with the mean of normalization, and 0.7779 (<TEX>$R_p^2$</TEX>), 0.1033% (RMSEP) with median filter of smoothing for firmness, soluble solid content (SSC), and acid content, respectively. Results show that Vis / NIR hyperspectral reflectance imaging technique has good potential for the measurement of internal quality of truss tomato.

Hyperspectral Reflectance Imaging for Detecting a Foodborne Pathogen: Campylobacter

This article is concerned with the development of a hyperspectral reflectance imaging technique for detecting and identifying one of the most common foodborne pathogens, Campylobacter. Direct plating using agars is an effective tool for laboratory tests and analyses of microorganisms. The morphology (size, growth pattern, color, etc.) of colonies grown on agar plates has been widely used to tentatively differentiate organisms. However, it is sometimes difficult to differentiate target organisms like Campylobacters from other contaminants grown together on the same agar plates. A hyperspectral reflectance imaging system operating at the visible and near-infrared (VNIR) spectral region from 400 nm to 900 nm was set up to measure spectral signatures of 17 different Campylobacter and non-Campylobacter subspecies. Protocols for culturing, imaging samples and for calibrating measured data were developed. The VNIR spectral library of all 17 organisms commonly encountered in poultry was established from calibrated hyperspectral reflectance images. A pattern classification algorithm was developed to locate and identify 48 h cultures of Campylobacter and non-Campylobacter contaminants on background agars (blood agar and Campy-Cefex) with over 99% accuracy. The Bhattacharyya distance, a statistical separability measure, was used to predict the performance of the pattern classification algorithm at a few wavelength bands chosen by the principal component analysis (PCA) band weightings. This research has a potential to be expanded to detect other pathogens grown on agar media.