Hyperspectral signature-band extraction and learning: an example of sugar content prediction of Syzygium samarangense.

This study proposes a method to extract the signature bands from the deep learning models of multispectral data converted from the hyperspectral data. The signature bands with two deep-learning models were further used to predict the sugar content of the Syzygium samarangense. Firstly, the hyperspectral data with the bandwidths lower than 2.5 nm were converted to the spectral data with multiple bandwidths higher than 2.5 nm to simulate the multispectral data. The convolution neural network (CNN) and the feedforward neural network (FNN) used these spectral data to predict the sugar content of the Syzygium samarangense and obtained the lowest mean absolute error (MAE) of 0.400° Brix and 0.408° Brix, respectively. Secondly, the absolute mean of the integrated gradient method was used to extract multiple signature bands from the CNN and FNN models for sugariness prediction. A total of thirty sets of six signature bands were selected from the CNN and FNN models, which were trained by using the spectral data with five bandwidths in the visible (VIS), visible to near-infrared (VISNIR), and visible to short-waved infrared (VISWIR) wavelengths ranging from 400 to 700 nm, 400 to 1000 nm, and 400 to 1700 nm. Lastly, these signature-band data were used to train the CNN and FNN models for sugar content prediction. The FNN model using VISWIR signature bands with a bandwidth of ± 12.5 nm had a minimum MAE of 0.390°Brix compared to the others. The CNN model using VISWIR signature bands with a bandwidth of ± 10 nm had the lowest MAE of 0.549° Brix compared to the other CNN models. The MAEs of the models with only six spectral bands were even better than those with tens or hundreds of spectral bands. These results reveal that six signature bands have the potential to be used in a small and compact multispectral device to predict the sugar content of the Syzygium samarangense.

Sugariness prediction of Syzygium samarangense using convolutional learning of hyperspectral images.

Sugariness is one of the most important indicators to measure the quality of Syzygium samarangense, which is also known as the wax apple. In general, farmers used to measure sugariness by testing the extracted juice of the wax apple products. Such a destructive way to measure sugariness is not only labor-consuming but also wasting products. Therefore, non-destructive and quick techniques for measuring sugariness would be significant for wax apple supply chains. Traditionally, the non-destructive method to predict the sugariness or the other indicators of the fruits was based on the reflectance spectra or Hyperspectral Images (HSIs) using linear regression such as Multi-Linear Regression (MLR), Principal Component Regression (PCR), and Partial Least Square Regression (PLSR), etc. However, these regression methods are usually too simple to precisely estimate the complicated mapping between the reflectance spectra or HSIs and the sugariness. This study presents the deep learning methods for sugariness prediction using the reflectance spectra or HSIs from the bottom of the wax apple. A non-destructive imaging system fabricated with two spectrum sensors and light sources is implemented to acquire the visible and infrared lights with a range of wavelengths. In particular, a specialized Convolutional Neural Network (CNN) with hyperspectral imaging is proposed by investigating the effect of different wavelength bands for sugariness prediction. Rather than extracting spatial features, the proposed CNN model was designed to extract spectral features of HSIs. In the experiments, the ground-truth value of sugariness is obtained from a commercial refractometer. The experimental results show that using the whole band range between 400 and 1700 nm achieves the best performance in terms of °Brix error. CNN models attain the °Brix error of ± 0.552, smaller than ± 0.597 using Feedforward Neural Network (FNN). Significantly, the CNN's test results show that the minor error in the interval 0 to 10°Brix and 10 to 11°Brix are ± 0.551 and ± 0.408, these results indicate that the model would have the capability to predict if sugariness is below 10°Brix or not, which would be similar to the human tongue. These results are much better than ± 1.441 and ± 1.379 by using PCR and PLSR, respectively. Moreover, this study provides the test error in each °Brix interval within one Brix, and the results show that the test error is varied considerably within different °Brix intervals, especially on PCR and PLSR. On the other hand, FNN and CNN obtain robust results in terms of test error.

Autofluorescence Detection Method for Dental Plaque Bacteria Detection and Classification: Example of Porphyromonas gingivalis, Aggregatibacter actinomycetemcomitans, and Streptococcus mutans.

The use of fluorescence spectroscopy for plaque detection is a fast and effective way to monitor oral health. At present, there is no uniform specification for the design of the excitation light source of related products for generating fluorescence. To carry out experiments on dental plaque, the fluorescence spectra of three different bacterial species (Porphyromonas gingivalis, Aggregatibacter actinomycetemcomitans, and Streptococcus mutans) were measured by hyperspectral imaging microscopy (HIM). Three critical issues were found in the experiments. One issue was the unwanted spectrum generated from a mercury line source; two four-order low-pass filters were evaluated for eliminating the unwanted spectrum and meet the experimental requirements. The second issue was the red fluorescence generated from the microscope slide made of borosilicate glass; this could affect the observation of the red fluorescence from the bacteria; quartz microscope slides were found to reduce the fluorescence intensity by about 2 dB compared with the borosilicate slide. The third issue of photobleaching in the fluorescence of the Porphyromonas gingivalis was studied. This study proposes a method of classifying three bacteria based on the spectral intensity ratios (510/635 and 500/635 nm) under the 405 nm excitation light was proposed in this study. The sensitivity and specificity of the classification were approximately 99% and 99%, respectively.

Using System Identification to Construct an Inherent Model of Pupillary Light Reflex to Explore Diabetic Neuropathy.

This study proposed a pupillary light reflex (PLR) inherent model based on the system identification method to demonstrate the dynamic physiological mechanism of the PLR, in which pupillary constriction and dilation are controlled by the sympathetic and parasympathetic nervous system. This model was constructed and verified by comparing the simulated and predicted PLR response with that of healthy participants. The least root-mean-square error (RMSE) of simulated PLR response was less than 0.7% when stimulus duration was under 3 ms. The RMSE of predicted PLR response increased by approximately 6.76%/s from the stimulus duration of 1 ms to 3 s, when the model directly used the parameters extracted from the PLR at the stimulus duration of 10 ms. When model parameters were derived from the regression by the measured PLR response, the RMSE kept under 8.5%. The model was applied to explore the PLR abnormalities of the people with Diabetic Mellitus (DM) by extracting the model parameters from 42 people with DM and comparing these parameters with those of 42 healthy participants. The parameter in the first-order term of the elastic force of the participants with DM was significantly lower than that of the healthy participants (p < 0.05). The sympathetic force and sympathetic action delay of the participants with DM were significantly larger (p < 0.05) and longer (p < 0.0001) than that of the healthy ones, respectively. The reason might be that the sympathetic nervous system, which controls the dilator muscle, degenerated in diabetic patients.

Band-Selection of a Portal LED-Induced Autofluorescence Multispectral Imager to Improve Oral Cancer Detection.

This aim of this study was to find effective spectral bands for the early detection of oral cancer. The spectral images in different bands were acquired using a self-made portable light-emitting diode (LED)-induced autofluorescence multispectral imager equipped with 365 and 405 nm excitation LEDs, emission filters with center wavelengths of 470, 505, 525, 532, 550, 595, 632, 635, and 695 nm, and a color image sensor. The spectral images of 218 healthy points in 62 healthy participants and 218 tumor points in 62 patients were collected in the ex vivo trials at China Medical University Hospital. These ex vivo trials were similar to in vivo because the spectral images of anatomical specimens were immediately acquired after the on-site tumor resection. The spectral images associated with red, blue, and green filters correlated with and without nine emission filters were quantized by four computing method, including summated intensity, the highest number of the intensity level, entropy, and fractional dimension. The combination of four computing methods, two excitation light sources with two intensities, and 30 spectral bands in three experiments formed 264 classifiers. The quantized data in each classifier was divided into two groups: one was the training group optimizing the threshold of the quantized data, and the other was validating group tested under this optimized threshold. The sensitivity, specificity, and accuracy of each classifier were derived from these tests. To identify the influential spectral bands based on the area under the region and the testing results, a single-layer network learning process was used. This was compared to conventional rules-based approaches to show its superior and faster performance. Consequently, four emission filters with the center wavelengths of 470, 505, 532, and 550 nm were selected by an AI-based method and verified using a rule-based approach. The sensitivities of six classifiers using these emission filters were more significant than 90%. The average sensitivity of these was about 96.15%, the average specificity was approximately 69.55%, and the average accuracy was about 82.85%.

Adjustable panoramic inspection system for submillimeter fasteners.

Fasteners are critical and indispensable locking components in mechanical assembly. Submillimeter fasteners are massively and widely used in electronic devices. This study proposed an adjustable panoramic inspection system for M2 to M0.8 submillimeter fasteners. The system mainly consists of a panoramic imaging module, a back-light module, and an image grabbing and computing module. The panoramic imaging module would form four equal optical path lengths to keep the same imaging amplification between the different directions of the field of view. The back-light module was designed to provide uniform illumination and enhance the contrast of the pitch edge between the fasteners and the background. The image grabbing and computing module with a high-speed camera was designed to be adjustable for different sizes of submillimeter fasteners. The realized system can offer the function of four images in one shot to make a panoramic scene, independent illumination for recognizing, inspect screws from M0.8 to M2.0 screws, and short time consumption of image processing, such as 3.284 ms for M0.8 screws and 2.384 ms for M2.0 screws, to achieve examination of 6000 pieces in 1 min.

Core/shell structured CdS/polydopamine/TiO2 ternary hybrids as highly active visible-light photocatalysis.

Core/shell structured CdS/polydopamine/TiO2 (CdS/PDA/TiO2) ternary hybrids were fabricated by sequentially coating of PDA and TiO2 on CdS nanospheres through dopamine self-polymerization and TBOT hydrolysis and hydrothermal processes. The reaction rate constants of CdS/PDA/TiO2 ternary hybrids toward the degradation of RhB, MB and phenol were more than 3 times higher than those of CdS/TiO2 hybrids. The remarkably improved photocatalytic activity was attributed to enhanced light absorption and charge carrier separation efficiency associated with the introduction of PDA.

Portable LED-induced autofluorescence spectroscopy for oral cancer diagnosis.

Oral cancer is a serious and growing problem in many developing and developed countries. To improve the cancer screening procedure, we developed a portable light-emitting-diode (LED)-induced autofluorescence (LIAF) imager that contains two wavelength LED excitation light sources and multiple filters to capture ex vivo oral tissue autofluorescence images. Compared with conventional means of oral cancer diagnosis, the LIAF imager is a handier, faster, and more highly reliable solution. The compact design with a tiny probe allows clinicians to easily observe autofluorescence images of hidden areas located in concave deep oral cavities. The ex vivo trials conducted in Taiwan present the design and prototype of the portable LIAF imager used for analyzing 31 patients with 221 measurement points. Using the normalized factor of normal tissues under the excitation source with 365 nm of the central wavelength and without the bandpass filter, the results revealed that the sensitivity was larger than 84%, the specificity was not smaller than over 76%, the accuracy was about 80%, and the area under curve of the receiver operating characteristic (ROC) was achieved at about 87%, respectively. The fact shows the LIAF spectroscopy has the possibilities of ex vivo diagnosis and noninvasive examinations for oral cancer.

Image quality affected by diffraction of aperture structure arrangement in transparent active-matrix organic light-emitting diode displays.

Transparent display is one of the main technologies in next-generation displays, especially for augmented reality applications. An aperture structure is attached on each display pixel to partition them into transparent and black regions. However, diffraction blurs caused by the aperture structure typically degrade the transparent image when the light from a background object passes through finite aperture window. In this paper, the diffraction effect of an active-matrix organic light-emitting diode display (AMOLED) is studied. Several aperture structures have been proposed and implemented. Based on theoretical analysis and simulation, the appropriate aperture structure will effectively reduce the blur. The analysis data are also consistent with the experimental results. Compared with the various transparent aperture structure on AMOLED, diffraction width (zero energy position of diffraction pattern) of the optimize aperture structure can be reduced 63% and 31% in the x and y directions in CASE 3. Associated with a lenticular lens on the aperture structure, the improvement could reach to 77% and 54% of diffraction width in the x and y directions. Modulation transfer function and practical images are provided to evaluate the improvement of image blurs.

Biopsy Diagnosis of Oral Carcinoma by the Combination of Morphological and Spectral Methods Based on Embedded Relay Lens Microscopic Hyperspectral Imaging System.

Cytopathological examination through biopsy is very important for carcinoma detection. The embedded relay lens microscopic hyperspectral imaging system (ERL-MHIS) provides a morphological image of a biopsy sample and the spectrum of each pixel in the image simultaneously. Based on the ERL-MHIS, this work develops morphological and spectral methods to diagnose oral carcinoma biopsy. In morphological discrimination, the fractal dimension method is applied to differentiate between normal and abnormal tissues. In spectral identification, normal and cancerous cells are distinguished using five methods. However, the spectra of normal and cancerous cells vary with patient. The diagnostic performances of the five methods are thus not ideal. Hence, the proposed cocktail approach is used to determine the effectiveness of the spectral methods in correlating with the sampling conditions. And then we use a combination of effective spectral methods according to the sample conditions for diagnosing a sample. A total of 68 biopsies from 34 patients are analyzed using the ERL-MHIS. The results demonstrate a sensitivity of 90 ± 4.53 % and a specificity of 87.8 ± 5.21 %. Furthermore, in our survey, this system is the first time utilized to study oral carcinoma biopsies.

Design and analysis of wearable pupillometer for autonomic neuropathy of diabetic patients.

Diabetes is a familiar disease in modern society. In the early stage of diabetes, symptoms are unobvious, but they usually induce diabetic autonomic neuropathy or, worse, cardiovascular autonomic neuropathy. Pupillometers are effective instruments for observing human pupils. This article presents a novel wearable pupillometer design, without external light artifacts, and an embedded algorithm with blinking elimination, which investigates autonomic neuropathy through recording pupil dynamics triggered by an external sensitive invisible light source. The pupillometer is experimented on 36 healthy subjects and 10 diabetic patients under four different colors (white, red, green, and blue) as well as two different light intensities: 50 and 500 mcd. Ten parameters derived from pupil diameter, pupil response time, and pupil response speed will be evaluated for the healthy subjects and diabetic patients. The results show that three in four parameters related to pupil diameters, one in four related to light intensities, and one in two related to pupil response speed could have significant differences (p<0.05) between healthy subjects and diabetic patients. These parameters obtain over 85% sensitivity, 83% specificity, and 88% accuracy. The pupillometer is proven reliable, effective, portable, and inexpensive for diagnosing diabetes in an early stage.

Research of accommodative microfluctuations caused by visual fatigue based on liquid crystal and laser displays.

Different levels of visual fatigue in the human eye depend on different color-formation methods and image quality. This paper uses the high-frequency component of the spectral power of accommodative microfluctuations as a major objective indicator for analyzing the effects of visual fatigue based on various displays, such as color-formation displays and 3D displays. Also, a questionnaire is used as a subjective indicator. The results are that 3D videos cause greater visual fatigue than 2D videos (p<0.001), the shutter-type 3D display causes visual fatigue more than the polarized type (p=0.012), the display of the time-sharing method causes greater visual fatigue than the spatial-formation method (p=0.008), and there is no significance between various light source modules of displays (p=0.162). In general, people with normal color discrimination have more visual fatigue than those with good color discrimination (p<0.001). Therefore, this paper uses the high-frequency component of accommodative microfluctuations to evaluate the physiological stress or strain by overexerting the visual system, and can compare the level of visual fatigue between various displays.

Separating spectral mixtures in hyperspectral image data using independent component analysis: validation with oral cancer tissue sections.

Recently, hyperspectral imaging (HSI) systems, which can provide 100 or more wavelengths of emission autofluorescence measures, have been used to delineate more complete spectral patterns associated with certain molecules relevant to cancerization. Such a spectral fingerprint may reliably correspond to a certain type of molecule and thus can be treated as a biomarker for the presence of that molecule. However, the outcomes of HSI systems can be a complex mixture of characteristic spectra of a variety of molecules as well as optical interferences due to reflection, scattering, and refraction. As a result, the mixed nature of raw HSI data might obscure the extraction of consistent spectral fingerprints. Here we present the extraction of the characteristic spectra associated with keratinized tissues from the HSI data of tissue sections from 30 oral cancer patients (31 tissue samples in total), excited at two different wavelength ranges (330 to 385 and 470 to 490 nm), using independent and principal component analysis (ICA and PCA) methods. The results showed that for both excitation wavelength ranges, ICA was able to resolve much more reliable spectral fingerprints associated with the keratinized tissues for all the oral cancer tissue sections with significantly higher mean correlation coefficients as compared to PCA (p<0.001).

Determination of optimal converting point of color temperature conversion complied with ANSI C78. 377 for indoor solid-state lighting and display applications.

In recent years, displays and lighting require color temperature (CT) conversion function because observers have different preferences. This paper proposes effective methods to determine the optimal converting point of CT conversion for display and lighting application. For display application, the concepts of center of gravity and isotemperature line are applied to determine the optimal converting point. The maximal enhancement of luminance between the optimal and average is 18%. For lighting application, this paper proposes two methods to determine the optimal converting point in the CT quadrangle which complies with ANSI C78. 377. The enhancement of luminance in two CT modes (5700K and 6500K) are 14.2% and 23.6%, respectively.

Improvement of bit error rate and page alignment in the holographic data storage system by using the structural similarity method.

Although widely recognized as a promising candidate for the next generation of data storage devices, holographic data storage systems (HDSS) incur adverse effects such as noise, misalignment, and aberration. Therefore, based on the structural similarity (SSIM) concept, this work presents a more accurate locating approach than the gray level weighting method (GLWM). Three case studies demonstrate the effectiveness of the proposed approach. Case 1 focuses on achieving a high performance of a Fourier lens in HDSS, Cases 2 and 3 replace the Fourier lens with a normal lens to decrease the quality of the HDSS, and Case 3 demonstrates the feasibility of a defocus system in the worst-case scenario. Moreover, the bit error rate (BER) is evaluated in several average matrices extended from the located position. Experimental results demonstrate that the proposed SSIM method renders a more accurate centering and a lower BER, lower BER of 2 dB than those of the GLWM in Cases 1 and 2, and BER of 1.5 dB in Case 3.

Finite conjugate embedded relay lens hyperspectral imaging system (ERL-HIS).

We present a novel embedded relay lens hyperspectral imaging system (ERL-HIS) with high spectral resolution (nominal spectral resolution of 2.8 nm) and spatial resolution (30 µm×8 µm) that transfers the scanning plane to an additional imaging plane through the internal relay lens so as to alleviate all outside moving parts for the scanning mechanism used in the traditional HIS, where image scanning is achieved by the relative movement between the object and hyperspectrometer. The ERL-HIS also enables high-speed scanning and can attach to a variety of optical modules for versatile applications. Here, we also demonstrate an application of the proposed ERL-HIS attached to a microscopic system for observing autofluorescent images of sliced cancer tissue samples.

Design and analysis of radial imaging capsule endoscope (RICE) system.

In this study, a radial imaging capsule endoscope (RICE) system is designed, which differs from a conventional front imaging capsule endoscope (FICE) system. To observe the wrinkled intima of the intestine, which spreads without folding around the circumference of the capsule when a capsule endoscope with a diameter that slightly exceeds that of the intestine passes through it, the RICE uses a cone mirror, a radial window shell, and a focus optical module that comprise the radial imaging system. This concept was demonstrated in a packaged optical simulator. The RICE optical model also has been established and verified by many simulations and experiments. In minimizing the sagittal and tangential aberrations, the optical module of the RICE has achieved an F-number of 4.2, a viewing angle of 65.08°, and an RMS radius of the 4th to 6th fields of less than 17 um. A comparison of these characteristics with those of the focus optical module that is used in FICE lenses reveals that the spot size is 50% larger for each field, and the modulation transfer function (MTF) is remarkably improved from 7% to 36% at 100 lp/mm on the 5th field of the sagittal plane.

Gamut boundary description for one dependent primary color.

The gamut boundary description (GBD) of multiprimary color displays (MPD) is important for color gamut mapping. Dependent primary color (DPC) is the color stimulus of a controllable color channel represented by an additive mixture of positive amounts of other primary colors. We propose a method to obtain the GBD of a MPD with one DPC. Further, the ideal color volume in CIE xyY and CIE L*a*b* color space with complete-controlling white channel is about 218.8% and 144% compared with the one of digital light processing with incomplete-controlling white channel. The white channel with complete control will not only increase brightness, but also expand color volume.

Determination of Gamut Boundary Description for multi-primary color displays.

Displays with a larger color gamut to represent the images of the small color gamut are emphasized in the display development trend recently. Resulting from the vigorous development of Light Emitting Diodes (LEDs), the solutions to enlarge the color gamut which is formed a polygon area by adding multiple primary colors are possible, easier and inexpensive considerably. Therefore, how to determine the Gamut Boundary Description (GBD) plays a significant role for the applications of the multiple primary color displays, where the primaries form a convex polygon in CIE xy space. The paper proposed a method to construct the three-dimension color volume of GBD from the two-dimension polygon gamut area precisely regardless of that how many multiple primary colors the displays have. The method is examined in detail by the simulations and experiments, and proved it to fulfill from tri-primary color device to Nprimary color device.