Detection of early bruises on loquat using hyperspectral imaging technology coupled with band ratio and improved Otsu method

Combining transfer learning and hyperspectral imaging to identify bruises of pears across different bruise types

Mechanical bruise is one of the most crucial factors affecting the quality of pears, which has a huge influence on postharvest transportation, storage, and sale of pears. To rapidly detect early bruises of pears across different bruise types, hyperspectral imaging technology coupled with transfer learning methods was performed in this study. Two transfer learning methods, that is, transfer component analysis (TCA) and manifold embedded distribution alignment (MEDA), were applied for two tasks (impact bruise → crush bruise, crush bruise → impact bruise). Supporting vector machine (SVM) was set as a baseline to conduct analysis and comparison of the transferability of the models. The result showed that, for task 1 (impact bruise → crush bruise), MEDA and TCA-SVM model achieved a classification accuracy of 93.33% and 91.11% in target domain, individually. For task 2 (crush bruise →impact bruise), MEDA and TCA-SVM model achieved an accuracy of 88.89% and 85.19% in target domain, respectively. Both the two models improved the accuracy compared with SVM models (84.44% for task 1; 77.04% for task 2). Overall, the results indicated that transfer learning approaches could perform pear bruise detection across different bruise types. Hyperspectral imaging in combination with transfer learning methods is a promising possibility for the efficient and cost-saving field detection of fruit bruises among different bruise types. PRACTICAL APPLICATION: The production and export of pears are faced with problems of mechanical damage due to vibration, collision, impact, and other factors, which cause chemical changes in color, odor, and taste. Sometimes the bruise was too slight to be ignored which would infect with other fruits in the future. In this study, we used hyperspectral imaging combined with transfer learning method could detect these slight bruises caused by different factors. Distinguishing different types of damage can provide a reference for quick judgment of the process causing damage and take prompt measures to reduce economic losses.

Hyperspectral imaging coupled with machine learning for classification of anthracnose infection on mango fruit

Anthracnose is the major plant disease causing an economic loss of mango fruit. Anthracnose symptom is not visible at a quiescent stage and the infected fruit often enters the food chain before the infection is known. Detection of a pre-symptomatic anthracnose infection is thus, crucial to prevent the infected fruit from entering the food chain. This research applied hyperspectral imaging (HSI) spectroscopy integrated with machine learning (ML) including principal component analysis (PCA) and support vector machine (SVM) for rapid identification of quiescent infection of anthracnose in mango fruit. Mango fruit (Nam Dok Mai Si Thong) was artificially infected with Colletotrichum gloeosporioides and stored at 20 °C and 90 % RH. The HSI was used to collect the spectral and spatial data of the samples. PCA and SVM were respectively performed to explore the hyperspectral data and to classify different symptom severities. The obtained spectral data can be recognized as fingerprints ascribing to the metabolites produced by C. gloeosporioides and the decomposed fruit tissues caused by the fungal infection. The HSI integrated with ML was able to not only detect the anthracnose infection at a latent stage before the onset of disease symptoms but also correctly classify different symptom severities. The symptom maps were also constructed using false-color image processing to simplify the data visualization of different symptom severities. The capability of detecting a pre-symptomatic anthracnose infection is a key advantage of the developed ML-assisted HSI.

Handheld hyperspectral imaging as a tool for the post-mortem interval estimation of human skeletal remains

In forensic medicine, estimating human skeletal remains' post-mortem interval (PMI) can be challenging. Following death, bones undergo a series of chemical and physical transformations due to their interactions with the surrounding environment. Post-mortem changes have been assessed using various methods, but estimating the PMI of skeletal remains could still be improved. We propose a new methodology with handheld hyperspectral imaging (HSI) system based on the first results from 104 human skeletal remains with PMIs ranging between 1 day and 2000 years. To differentiate between forensic and archaeological bone material, the Convolutional Neural Network analyzed 65.000 distinct diagnostic spectra: the classification accuracy was 0.58, 0.62, 0.73, 0.81, and 0.98 for PMIs of 0 week-2 weeks, 2 weeks-6 months, 6 months-1 year, 1 year-10 years, and >100 years, respectively. In conclusion, HSI can be used in forensic medicine to distinguish bone materials >100 years old from those <10 years old with an accuracy of 98%. The model has adequate predictive performance, and handheld HSI could serve as a novel approach to objectively and accurately determine the PMI of human skeletal remains.

Assessing and detection of multiple bruises in peaches based on structured hyperspectral imaging

This study aimed to detect various types of postharvest damages in peaches based on structured hyperspectral imaging (S-HSI), including impact, falling, and compression damage, which can lead to bruising. The research involved three different spatial frequencies (60, 100, and 150 m-1) and used a 2π/3 phase shift interval to capture S-HSI images. These images were then processed using a mathematical demodulated model to create high-resolution image cubes that included both image and spectral information from the S-HSI data. Artificial neural network and principal component analysis were applied to develop bruise detection models using S-HSI spectra, which showed better discriminating effects compared with the ordinary hyperspectral spectra. The best performing discriminating models for healthy and three kinds of bruised samples were developed using the spectra of spatial frequency with 100 + 150 m-1, respectively. This study demonstrated the potential of S-HSI as an effective optical technique for bruise detection of peach.

Multi-level color classification of post-consumer plastic packaging flakes by hyperspectral imaging for optimizing the recycling process

In a circular economy perspective, the development of fast and efficient sensor-based recognition strategies of plastic waste, not only by polymer but also by color, plays a crucial role for the production of high quality secondary raw materials in recycling plants. In this work, mixed colored flakes of high-density polyethylene (HDPE) from packaging waste were simultaneously classified by hyperspectral imaging working in the visible range (400-750 nm), combined with machine learning. Two classification models were built and compared: (1) Partial Least Square-Discriminant Analysis (PLS-DA) for 6 HDPE macro-color classes identification (i.e., white, blue, green, red, orange and yellow) and (2) hierarchical PLS-DA for a more accurate discrimination of the different HDPE color tones, providing as output 14 color classes. The obtained classification results were excellent for both models, with values of Recall, Specificity, Accuracy, and F-score in prediction close to 1. The proposed methodological approach can be utilized as sensor-based sorting logic in plastic recycling plants, tuning the output based on the required needs of the recycling plant, allowing to obtain a high-quality recycled HDPE of different colors, optimizing the plastic recycling process, in agreement with the principles of circular economy.

Comparison of 2D and 3D convolutional neural networks in hyperspectral image analysis of fruits applied to orange bruise detection

Recent advances in hyperspectral imaging (HSI) have demonstrated its ability to detect defects in fruit that may not be visible in RGB images. HSIs can be considered 3D images containing two spatial dimensions and one spectral dimension. Therefore, the first question that arises is how to process this type of information, either using 2D or 3D models. In this study, HSI in the 550-900 nm spectral range was used to detect bruising in oranges. Sixty samples of Thompson oranges were subjected to a mechanical bruising process, and HSIs were taken at different time intervals: before bruising, and 8 and 16 h after bruising. The samples were then classified using two convolutional neural network (CNN) models, a shallow 7-layer network (CNN-7) and a deep 18-layer network (CNN-18). In addition, two different input processing approaches are used: using 2D information from each band, and using the full 3D data from each HSI. The 3D models were the most accurate, with 94% correct classification for 3D-CNN-18, compared to 90% for 3D-CNN-7, and less than 83% for the 2D models. Our study suggests that 3D HSI may be a more effective technique for detecting fruit bruising, allowing the development of a fast, accurate, and nondestructive method for fruit sorting. PRACTICAL APPLICATION: Orange bruises can reduce the market value of food, which is why the food processing industry needs to carry out quality inspections. An effective way to perform this inspection is by using hyperspectral images that can be processed with 2D or 3D models, either with deep or shallow neural networks. The results of the comparison performed in this work can be useful for the development of more accurate and efficient bruise detection methods for fruit inspection.

Analysis of Light Penetration Depth in Apple Tissues by Depth-Resolved Spatial-Frequency Domain Imaging

Spatial-frequency domain imaging (SFDI) has been developed as an emerging modality for detecting early-stage bruises of fruits, such as apples, due to its unique advantage of a depth-resolved imaging feature. This paper presents theoretical and experimental analyses to determine the light penetration depth in apple tissues under spatially modulated illumination. Simulation and practical experiments were then carried out to explore the maximum light penetration depths in 'Golden Delicious' apples. Then, apple experiments for early-stage bruise detection using the estimated reduced scattering coefficient mapping were conducted to validate the results of light penetration depths. The results showed that the simulations produced comparable or a little larger light penetration depth in apple tissues (~2.2 mm) than the practical experiment (~1.8 mm or ~2.3 mm). Apple peel further decreased the light penetration depth due to the high absorption properties of pigment contents. Apple bruises located beneath the surface peel with the depth of about 0-1.2 mm could be effectively detected by the SFDI technique. This study, to our knowledge, made the first effort to investigate the light penetration depth in apple tissues by SFDI, which would provide useful information for enhanced detection of early-stage apple bruising by selecting the appropriate spatial frequency.

Visible- and near-infrared hyperspectral imaging for the quantitative analysis of PD-L1+ cells in human lymphomas: Comparison with fluorescent multiplex immunohistochemistry

INTRODUCTION

We analyzed the expression of PD-L1 in human lymphomas using hyperspectral imaging (HSI) compared to visual assessment (VA) and conventional digital image analysis (DIA) to strengthen further the value of HSI as a tool for the evaluation of brightfield-based immunohistochemistry (IHC). In addition, fluorescent multiplex immunohistochemistry (mIHC) was used as a second detection method to analyze the impact of a different detection method.

MATERIAL AND METHODS

18 cases (6 follicular lymphomas and 12 diffuse large B-cell lymphomas) were stained for PD-L1 by IHC and for PD-L1, CD3, and CD8 by fluorescent mIHC. The percentage of positively stained cells was evaluated with VA, HSI, and DIA for IHC and VA and DIA for mIHC. Results were compared between the different methods of detection and analysis.

RESULTS

An overall high concordance was found between VA, HSI, and DIA in IHC (Cohens Kappa = 0.810^VA/HSI, 0.710 ^VA/DIA, and 0.516 ^HSI/DIA) and for VA^mIHCversus DIA^mIHC (Cohens Kappa = 0.894). Comparing IHC and mIHC general agreement differed depending on the methods compared but reached at most a moderate agreement (Coheńs Kappa between 0.250 and 0.483). This is reflected by the significantly higher percentage of PD-L1+ cells found with mIHC (p^Friedman = 0.014).

CONCLUSION

Our study shows a good concordance for the different analysis methods. Compared to VA and DIA, HSI proved to be a reliable tool for assessing IHC. Understanding the regulation of PD-L1 expression will further enlighten the role of PD-L1 as a biomarker. Therefore it is necessary to develop an instrument, such as HSI, which can offer a reliable and objective evaluation of PD-L1 expression.