Search

Leaf abscission of rose (Rosa hybrida L. ‘Baby Love’) cultured in vitro due to ethylene gas accumulation and enzymatic hydrolytic activity, is one of the abnormal phenomena affecting the shoots quality. In this study, silver nanoparticles (AgNPs) and cobalt nanoparticles (CoNPs) were used to overcome leaves abscission as well as, the effect of shoot mass propagation, rooting and acclimatization at the nursery stage. The results showed that shoots cultured on MS (Murashige and Skoog, in Physiol Plantarum 15(3):473–497, 10.1111/j.1399-3054.1962.tb08052.x, 1962) medium supplemented with 2 mg/L AgNPs gave the highest shoot multiplication coefficient, shoot height, fresh weight, dry weight and chlorophyll index (5.33 shoots; 3.06 cm; 451.00 mg; 58.33 mg; 32.28; respectively) than CoNPs (replace CoCl2 in the MS medium) and basal MS medium. Meanwhile in the rooting stage, MS medium added of 4.65 µg/L CoNPs was the most optimal with dry mass ratio (10.28%), number of roots (5.67 roots), root length (2.17 cm) and SPAD (41.07 nmol/cm2) as well as reduced the ethylene gas content (0.11 ppm) and enzymes activity such as pectinase (0.07 UI/mL) and cellulase (0.25 UI/mL) in comparision to the other treatments after 4 weeks culture. The plantlets derived from in vitro culture on medium added 4.65 µg/L CoNPs gave the highest survival rate (96.67%) as well as growth and development at the nursery stage. Cobalt and silver nanoparticles (CoNPs, AgNPs) were used to overcome leaf abscission, enhance growth and increase the survival rate of plantlets at the nursery stage. CoNPs helps reduce the ethylene gas content, enzymatic hydrolytic activity such as pectinase and cellulase. AgNPs was the most suitable factor for shoots mass propagation.

Diabetic retinopathy is one of the leading causes of blindness among the working age population world-wide due to late detection and intervention. This study pilots the application of deep learning models to automatically diagnose the occurrence and severity of diabetic retinopathy. With color fundus photography as input, this study tested the performance of transfer learning based on the most recent architectures of Convolutional Neural Network (CNN) models, the EfficientNets, claimed to be superior than many current well-performing network architectures.

There are two goals of modeling, including interpretation that is to extract information about how the response variables are associated to the input variables, and prediction that is to predict what the responses are going to be. The dilemma is that interpretable algorithms such as linear regression or logistic regression are often not accurate for prediction, while complex algorithms for better prediction are much more accurate but not easy to interpret1. Risk could be in the forms of cyber security risk, credit risk, investment risk, operational risk, etc. In this paper, we propose an interpretable method in evaluating risk using Deep Learning.

We propose the so-called Bundled Transfer Learning approach with multiple large architectures for automated detection of Coronavirus using X-Ray and CT images Extracted features from each pretrained model in the bundle are gathered for training new deep layers The dataset includes CT scan images of COVID-19 and normal classes and X-Ray images of COVID-19, Pneumonia, and normal classes © 2020 SPIE

This study aims to investigate an automated approach using Convolutional Neural Network (CNN) to efficiently classify COVID-19 cases vs healthy cases using chest CT images. Convolutional Neural Network (CNN) is a class of deep neural networks, usually applied to analyzing image data, and can learn features effectively from images in comparison to the traditional method with image segmentation, feature extraction/selection and classification steps. Several models using pre-trained weights, including VGG16, VGG19, InceptionV3, InceptionResNetV2, Xception, DenseNet121, DenseNet169, and DenseNet201 were investigated. Overfitting was handled by randomly dropping nodes during training, augmenting training data, as well as using the validation set. We concluded that a CNN approach can detect COVID-19 using CT features, and DenseNet201is the highest performing model.

In this paper, we take the very first step in using Neural Style Transfer and Generative Adversarial Networks for the task of 3D image augmentation. With this approach, more data may be generated for object recognition and visualization purposes without having to fully reconstruct 3D objects. To the best of our knowledge, this is the first report that describes image augmentation in the 3D domain using Integral Imaging and Deep Learning. The author assumes that readers have some knowledge regarding Deep Learning.

A typical issue with development of 3D image recognition models and systems is that 3D images often come with large volumes of data and require expensive computational cost for image reconstruction and model training. Transfer learning is a machine learning technique where a model trained on one task is reused on another related task. In this research, we propose a Transfer Learning method that allows training a 3D object recognition model with very limited training data, so requires much fewer reconstructed image slices, and help reduce the computational cost of both image reconstruction and training such models. To the best of our knowledge, this is the first report regarding Transfer Learning for 3D object recognition using integral imaging.

By the time of the abstract, the coronavirus COVID-19 is affecting 213 countries with more than 9.4 million cases, and more than 480 thousand deaths. In the US it has been confirmed that there are more than 2.4 million COVID-19 cases and approximately 123 thousand related deaths, according to Worldometer. The Wuhan originated COVID-19 has become a global challenge since late December 2019. As control measures lift, life and businesses start going to open, the coronavirus pandemic continues to grow. In this research, we propose a Deep Learning model that recognizes COVID-19 cases using X-ray images (DeepCOVID-19). The model would help physicians to be more confident by having a second opinion in assessing patients. An implementation of the model would help countries where there is shortage of test kits, while X-ray devices are widely available.

BACKGROUND Hepatitis B virus (HBV) infection is a significant public health issue in Vietnam. Our goal was to understand the determinants of attitudes towards and practices of hepatitis B vaccine birth dose (HepB-BD) in certain regions of Vietnam. METHOD A rapid qualitative assessment was conducted in three geographically diverse provinces that reported low coverage (

Background Hand-foot-and-mouth disease (HFMD) is a significant public health issue in Asia-pacific countries. Numerous studies have examined the relationship between socio-ecological factors and HFMD however the research findings were inconsistent. This study examined the association between socio-ecologic factors and HFMD in multiple provinces across Vietnam. Methods We applied a spatial autoregressive model using a Bayesian framework to examine the relationship between HFMD and socio-demographic factors. We used a Generalized Linear Model (GLD) with Poisson family to examine the province-specific association between monthly HFMD and climatic factors while controlling for spatial lag, seasonality and long-term trend of HFMD. Then, we used a random-effect meta-analysis to generate pooled effect size of climate-HFMD association for regional and country scale. Results One percent increase in newborn breastfed within 1 h of birth, households with permanent houses, and households accessed to safe water resulted in 1.57% (95% CI: − 2.25, − 0.93), 0.96% (− 1.66, − 0.23), and 1.13% (− 2.16, − 0.18) reduction in HFMD incidence, respectively. At the country-level, HFMD increased 7% (RR: 1.07; 95%CI: 1.052–1.088) and 3.1% (RR: 1.031, 95%CI: 1.024–1.039) for 1 °C increase in monthly temperature above 26 °C and 1% increase in monthly humidity above 76%. Whereas, HFMD decreased 3.1% associated with 1 mm increase in monthly cumulative rainfalls. The climate-HFMD relationship was varied by regions and provinces across the country. Conclusions The findings reflect an important implication for the climate change adaptation strategies and public-health decision, of which development of weather-based early warning systems should be considered to strengthen communicable disease prevention system.

The effects of heatwaves on morbidity in developing and tropical countries have not been well explored. The purpose of this study was to examine the relationship between heatwaves and hospitalization and the potential influence of socio-economic factors on this relationship in Vietnam. Generalized Linear Models (GLM) with Poisson family and Distributed Lag Models (DLM) were applied to evaluate the effect of heatwaves for each province (province-level effect). A random-effects meta-analysis was applied to calculate the pooled estimates (country-level effects) for ‘all causes’, infectious, cardiovascular, and respiratory admissions queried by lag days, regions, sex, and ages. We used random-effects meta-regression to explore the potential influence of socio-economic factors on the relationship between heatwaves and hospitalization. The size of province-level effects varied across provinces. The pooled estimates show that heatwaves were significantly associated with a 2.5% (95%CI: 0.8–4.3) and 3.8% (95%CI, 1.5–6.2) increase in all causes and infectious admissions at lag 0. Cardiovascular and respiratory admissions (0.8%, 95%CI: −1.6–3.3; 2.2%, 95%CI: −0.7–5.2) were not significantly increased after a heatwave event. The risk of hospitalization due to heatwaves was higher in the North than in the South for all causes (5.4%, 95%CI: −0.1–11.5 versus 1.3%, 95%CI: 0.1–2.6), infectious (11.2%, 95%CI: 3.1–19.9 versus 3.2%, 95%CI: 0.7–5.7), cardiovascular (7.5%, 95%CI: 1.1–14.4 versus −1.2%, 95%CI: −2.6–2.3), and respiratory diseases (2.7%, 95%CI: −5.4–11.5 versus 2.1%, 95%CI: −0.8–1.2). A non-significant influence of socio-economic factors on the relationship between heatwave and hospitalization was observed. This study provides important evidence and suggests implications for the projected impacts of climate change related extreme weather. Climate change adaptation programs of the health sector should be developed to protect residents from the effects of extreme weather events such as heatwaves in Vietnam.

Objective: The Vision Zero initiative pursues the goal of eliminating all traffic fatalities and severe injuries. Today’s advanced driver assistance systems (ADAS) are an important part of the strategy toward Vision Zero. In Germany in 2018 more than 26,000 people were killed or severely injured by traffic accidents on motorways and rural roads due to road accidents. Focusing on collision avoidance, a simulative evaluation can be the key to estimating the performance of state-of-the-art ADAS and identifying resulting potentials for system improvements and future systems. This project deals with the effectiveness assessment of a combination of ADAS for longitudinal and lateral intervention based on German accident data. Considered systems are adaptive cruise control (ACC), autonomous emergency braking (AEB), and lane keeping support (LKS). Methods: As an approach for benefit estimation of ADAS, the method of prospective effectiveness assessment is applied. Using the software rateEFFECT, a closed-loop simulation is performed on accident scenario data from the German In-Depth Accident Study (GIDAS) precrash matrix (PCM). To enable projection of results, the simulative assessment is amended with detailed single case studies of all treated cases without PCM data. Results: Three categories among today’s accidents on German rural roads and motorways are reported in this study: Green, grey, and white spots. Green spots identify accidents that can be avoided by state-of-the-art ADAS ACC, AEB, and LKS. Grey spots contain scenarios that require minor system modifications, such as reducing the activation speed or increasing the steering torque. Scenarios in the white category cannot be addressed by state-of-the-art ADAS. Thus, which situations demand future systems are shown. The proportions of green, grey, and white spots are determined related to the considered data set and projected to the entire GIDAS. Conclusions: This article describes a systematic approach for assessing the effectiveness of ADAS using GIDAS PCM data to be able to project results to Germany. The closed-loop simulation run in rateEFFECT covers ACC, AEB, and LKS as well as relevant sensors for environment recognition and actuators for longitudinal and lateral vehicle control. Identification of green spots evaluates safety benefits of state-of-the-art level 0–2 functions as a baseline for further system improvements to address grey spots. Knowing which accidents could be avoided by standard ADAS helps focus the evolution of future driving functions on white spots and thus aim for Vision Zero.

This study examined the short-term effects of temperature on cardiovascular hospital admissions (CHA) in the largest tropical city in Southern Vietnam. We applied Poisson time-series regression models with Distributed Lag Non-Linear Model (DLNM) to examine the temperature-CHA association while adjusting for seasonal and long-term trends, day of the week, holidays, and humidity. The threshold temperature and added effects of heat waves were also evaluated. The exposure-response curve of temperature-CHA reveals a J-shape relationship with a threshold temperature of 29.6 °C. The delayed effects temperature-CHA lasted for a week (0-5 days). The overall risk of CHA increased 12.9% (RR, 1.129; 95%CI, 0.972-1.311) during heatwave events, which were defined as temperature ≥ the 99th percentile for ≥2 consecutive days. The modification roles of gender and age were inconsistent and non-significant in this study. An additional prevention program that reduces the risk of cardiovascular disease in relation to high temperatures should be developed.

This study examined the temporal and spatial patterns of hand, foot, and mouth disease (HFMD) in the Mekong Delta region in Vietnam. A time-series analysis was used to examine the temporal patterns of HFMD in relation to climate factors while a retrospective space-time scan was used to detect the high-risk space-time clusters of this disease. A 1°C increase in average temperature was associated with 5.6% increase in HFMD rate at lag 5days (95% CI 0.3-10.9). A 1% increase in humidity had equal influence of 1.7% increases on HFMD rate at both lag 3days and 6days (95% CI 0.7-2.7 and 95% CI 0.8-2.6, respectively). An increase in 1 unit of rainfall was associated with a 0.5% increase of HFMD rate on the lag 1 and 6days (95% CI 0.2-0.9 and 95% CI 0.1-0.8, respectively). The predictive model indicated that the peak of HFMD was from October to December - the rainy season in the Mekong Delta region. Most high-risk clusters were located in areas with high population density and close to transport routes. The findings suggest that HFMD is influenced by climate factors and is likely to increase in the future due to climate change related weather events.

The association between heavy rainfall and infectious intestinal diseases (IID) has not been well described and little research has been conducted in developing countries. This study examines the association between heavy rainfall and hospital admissions for IID in Ho Chi Minh City, the most populous city in Vietnam. An interrupted time-series method was used to examine the effect of each individual heavy rainfall event (HRE) on IID. The percentage changes in post-HRE level and trends of IID were estimated for 30 days following each HRE. Then a random-effect meta-analysis was used to quantify the pooled estimate of effect sizes of all HREs on IID. The pooled estimates were calculated over a 21 day lag period. The effects of a HRE on IID varied across individual HREs. The pooled estimates indicate that the levels of IID following a HRE increased from 7.3% to 13.5% for lags from 0 to 21 days, however statistically significant increases were only observed for lags from 4 to 6 days (13.5%, 95%CI: 1.4–25.4; 13.3%, 95%CI: 1.5–25.0; and 12.9%, 95%CI: 1.6–24.1 respectively). An average decrease of 0.11% (95%CI: − 0.55–0.33) per day was observed for the post-HRE trend. This finding has important implications for the projected impacts on residents living in this city which is highly vulnerable to increased heavy rainfall associated with climate change. Adaptation and intervention programs should be developed to prevent this additional burden of disease and to protect residents from the adverse impacts of extreme weather events.

We explore algorithms of independent component analysis and K-means applied to 3D reconstruction of occluded objects using integral imaging. 3D reconstruction of occluded objects is implemented using the elemental images of the separated objects from occlusion. Experimental and theoretical results are presented. We show that the 3D reconstructed images using the proposed method may perform better than those using the conventional method in terms of contrast, sharpness and average normalized rms error (RMSE) metrics.

ObjectiveTo examine the effects of socioecological factors on multiple communicable diseases across Vietnam.MethodsWe used the Moran's I tests to evaluate spatial clusters of diseases and applied multilevel negative binomial regression models using the Bayesian framework to analyse the association between socioecological factors and the diseases queried by oral, airborne, vector-borne, and animal transmission diseases.Results and significanceThe study found that oral-transmission diseases were spatially distributed across the country; whereas, the airborne-transmission diseases were more clustered in the Northwest and vector-borne transmission diseases were more clustered in the South. Most of diseases were sensitive with climatic factors. For instance, a 1 degrees C increase in average temperature is significantly associated with 0.4% ( 95CI, 0.3 +/- 0.5), 2.5% ( 95% CI, 1.4 +/- 3.6), 0.9% ( 95% CI, 0.6 +/- 1.4), 1.1% ( 95% CI), 5% ( 95% CI, 3-.7.4), 0.4% ( 95% CI, 0.2 +/- 0.7), and 2% ( 95% CI, 1.5 +/- 2.8) increase in risk of diarrhoea, shigellosis, mumps, influenza, dengue, malaria, and rabies respectively. The influences of socio-economic factors on risk of communicable diseases are varied by factors with the biggest influence of population density. The research findings reflect an important implication for the climate change adaptation strategies of health sectors. A development of weather-based early warning systems should be considered to strengthen communicable disease prevention in Vietnam.

We present computational holographic three-dimensional imaging and automated object recognition based on independent component analysis (ICA). Three-dimensional sensing of the scene is performed by computational holographic imaging of the objects using phase-shifting digital holography. We used principal components analysis to reduce data dimension and ICA to recognize the three-dimensional objects. In this paper, kurtosis maximization-based algorithm is used. To the best of our knowledge, this paper is the first to report using ICA in three-dimensional imaging technology.

We present multifocus holographic 3-D image fusion based on independent component analysis (ICA). In this paper, the ICA technique is used to fuse multiple reconstructed holographic images at different distances from the image sensor. A hologram of two dice located at distances of 315 and 345 mm, respectively, from the sensor is recorded using phase-shifting digital holography and used in our experiments. The resulting reconstructed fused holographic image shows both dice objects clearly in focus. This is compared with a single reconstructed holographic image in which only one of the die objects is in focus at a particular reconstruction distance.

Flooding causes significant public health issues. The Mekong Delta has been considered the region to be the most vulnerable to flooding in Vietnam. This study assessed the spatial vulnerability of the health impacts of flooding in the Mekong Delta region, Vietnam. This study applied a vulnerability assessment framework which was computed as the function of three dimensions: exposure, sensitivity, and adaptive capacity. The indicators for each dimension were derived from the relevant literature, consultations with experts, and data availability. An analytic hierarchy process (AHP) and a principal component analysis (PCA) were used to determine the weight of indicators. Vulnerability indexes (VIs) were then computed for each province. A total of 29 indicators (sensitivity index, 14; adaptive capacity index, 13; and exposure index, 2) were employed to evaluate the vulnerability to the health impacts of flooding at a provincial level. The results of AHP revealed that the highest VIs were found in the Dong Thap and An Giang provinces (VI, 1.948 and 1.574, respectively). VIs were distributed with higher indexes in upstream provinces close to a river than in coastal provinces. PCA generated three components from the 29 indicators, and the VIs computed from the PCA method are in substantial agreement with the AHP method (ICC = 0.71, p

SUMMARYThis study examined the temporal and spatial patterns of diarrhoea in relation to hydro-meteorological factors in the Mekong Delta area in Vietnam. A time-series design was applied to examine the temporal pattern of the climate–diarrhoea relationship using Poisson regression models. Spatial analysis was applied to examine the spatial clusters of diarrhoea using Global Moran'sIand local indicators of spatial autocorrelation (LISA). The temporal pattern showed that the highest peak of diarrhoea was from weeks 30–42 corresponding to August–October annually. A 1 cm increase in river water level at a lag of 1 week was associated with a small [0·07%, 95% confidence interval (CI) 0·01–0·1] increase in the diarrhoeal rate. A 1 °C increase in temperature at lag of 2 and 4 weeks was associated with a 1·5% (95% CI 0·3−2·7) and 1·1% (95% CI 0·1−2·3) increase in diarrhoeal risk, respectively. Relative humidity and diarrhoeal risk were in nonlinear relationship. The spatial analysis showed significant clustering of diarrhoea, and the LISA map shows three multi-centred diarrhoeal clusters and three single-centred clusters in the research location. The findings suggest that climatic conditions projected to be associated with climate change have important implication for human health impact in the Mekong Delta region.

We present multi-spectral holographic three-dimensional image fusion using the discrete wavelet transform (DWT). The fusion results are compared with those of the Gaussian and Laplacian pyramid fusion methods. The advantage of the DWT over other methods is that it has more flexibility in controlling high frequency components as well as low frequency components, which improves the fused image quality. A wavelength tunable solid-state pumped laser is used to record up to 11 holograms with wavelengths from 567 to 613 nm. We present the fused reconstructed holographic images including multi-spectral fused images from the recorded multiple holograms. Fused multi-wavelength reconstructed holographic images provide multi-spectral information about the objects

Background The Mekong Delta is the most vulnerable region to climate change in South-East Asia; however, the association between climate and children9s health has rarely been studied in this region. Objective We examined the short-term association between daily temperature and hospital admissions for all causes, gastrointestinal and respiratory infection, among young children in the Mekong Delta area in Vietnam. Methods Daily paediatric hospital admissions and meteorological data were obtained from January 2008 to December 2012. A time-series approach was used with a combination of a Poisson regression and constrained distributed lag models to analyse the data. The long-term and seasonal trends, as well as other time-varying covariates, were adjusted using spline functions. Temperature—pediatric admission relationship was evaluated by age-specific (0–2 and 3–5-year-olds) and cause of admission groupings. Results A 1°C increase in the 2-day moving average temperature was significantly associated with a 3.4% (95% CI 1.2% to 5.5%), 4.6% (95% CI 2.2% to 7.3%), 2.6% (95% CI 0.6% to 4.6%), 4.4% (95% CI 0.6% to 8.2%) and 3.8%(95% CI 0.4% to 7.2%) increase in hospital admissions with 0–2-year-old children, 3–5-year-old children, all causes, gastrointestinal infection and respiratory infection, respectively. The cumulative effects from 1-day to 6-day moving average temperature on hospital admissions were greater for 3–5-year-old children and gastrointestinal infection than for 0–2-year-old children and other causes. Conclusions Temperature was found to be significantly associated with hospital admissions in young children with the highest association between temperature and gastrointestinal infection. The government agencies of Mekong Delta should implement measures to protect children from the changing temperature conditions related to climate change.

The present study is an evaluation of temporal/spatial variations of surface water quality using multivariate statistical techniques, comprising cluster analysis (CA), principal component analysis (PCA), factor analysis (FA) and discriminant analysis (DA). Eleven water quality parameters were monitored at 38 different sites in Can Tho City, a Mekong Delta area of Vietnam from 2008 to 2012. Hierarchical cluster analysis grouped the 38 sampling sites into three clusters, representing mixed urban-rural areas, agricultural areas and industrial zone. FA/PCA resulted in three latent factors for the entire research location, three for cluster 1, four for cluster 2, and four for cluster 3 explaining 60, 60.2, 80.9, and 70 % of the total variance in the respective water quality. The varifactors from FA indicated that the parameters responsible for water quality variations are related to erosion from disturbed land or inflow of effluent from sewage plants and industry, discharges from wastewater treatment plants and domestic wastewater, agricultural activities and industrial effluents, and contamination by sewage waste with faecal coliform bacteria through sewer and septic systems. Discriminant analysis (DA) revealed that nephelometric turbidity units (NTU), chemical oxygen demand (COD) and NH3 are the discriminating parameters in space, affording 67 % correct assignation in spatial analysis; pH and NO2 are the discriminating parameters according to season, assigning approximately 60 % of cases correctly. The findings suggest a possible revised sampling strategy that can reduce the number of sampling sites and the indicator parameters responsible for large variations in water quality. This study demonstrates the usefulness of multivariate statistical techniques for evaluation of temporal/spatial variations in water quality assessment and management.

A model of three-dimensional (3D) object recognition using integral imaging is presented. Multiple elemental images (EIs) are captured at different perspectives for reconstruction and recognition. Computational results are presented and discussed for performance evaluation.

We propose a novel method for the classification of breast tumors (malignant versus benign) based on principal component analysis (PCA) following single-frequency microwave imaging. For initial evaluation, a simplified model of the biological tissue was developed in a frequency-domain finite-element framework. The model incorporated various combinations of dielectric constant and conductivity. A double-level classification scheme allows classifying a tumor with high accuracy.

An overview of three-dimensional (3D) image recognition using photon-counting integral imaging is presented. A Poisson distribution model is used to generate photon-counting elemental images and reconstruct 3D images. Slices of 3D reconstructed images are the image source for recognition purpose. Experimental and computational results are shown to evaluate the performance of the method.

An overview of three-dimensional (3D) object recognition using neural networks is presented. Three dimensional sensing and imaging of 3D objects is performed using an integral imaging optical set up. Neural network technique is applied to recognize 3D objects. Experimental results are presented together with computational results for performance assessment.

The author presents an overview of 3D object recognition with photon-counting integral imaging using Independent Component Analysis (ICA). High resolution elemental images of 3D objects are captured at different angles to allow object recognition at different orientations using synthetic aperture integral imaging (SAII). Generated photon-counting elemental images are used to reconstruct the 3D images at different distances from the camera lens using a maximum a posteriori estimation method. The kurtosis maximization-based algorithm is applied as a non-gaussian maximization method to extract the independent features from the training data set. High dimensional data is pre-processed using Principal Component Analysis (PCA) to reduce the number of dimensions. The author demonstrates how this method can effectively recognize 3D objects despite a small expected number of photons. This may be important for low light applications in medical or other settings.

The author presents the maximum a posteriori (MAP) estimation method to estimate irradiance elemental images and reconstruct 3D images using photon-counting integral imaging. Elemental images are captured using the synthetic aperture integral imaging (SAII) technique. Photon-counting elemental images are generated using the Poisson distribution. The method can reconstruct 3D images more accurately than the one using maximum likelihood (MLE) estimation. This may be important in medical imaging as well as other photon-level applications.

A method for distortion-tolerant recognition of objects in water using three-dimensional (3D) integral imaging with a neural network classification architecture is presented. Recognition algorithms are developed and experimental results are presented with rotation-variable 3D objects. To test the robustness of the system, objects are placed under a variety of water conditions, including variable Maalox-induced scattering levels and occlusion using pine needles. Neural networks have long been used for two-dimensional recognition and have recently been used for 3D digital holographic recognition. To the best of our knowledge, this is the first use of neural networks for passive 3D integral imaging and recognition of underwater objects.

We present an overview of a method using Independent Component Analysis (ICA) and 3D Integral Imaging (II) technique to recognize 3D objects at different orientations. This method has been successfully applied to the recognition and classification of 3D scenes.

We present a fusion method for multi-wavelengths holographic images using Discrete Wavelet transform (DWT). The advantage of DWT is more control on high as well as low frequencies to get better quality. Fusion results include monochromatic fused images and color fused images from holographic images reconstructed from holograms recorded with multiple wavelengths from 567nm to 613nm.

Independent component analysis (ICA) aims at extracting unknown components from multivariate data assuming that the underlying components are mutually independent. This technique has been successfully applied to the recognition and classification of objects. We present a method that combines the benefits of ICA and the ability of the integral imaging technique to obtain 3D information for the recognition of 3D objects with different orientations. Our recognition is also possible when the 3D objects are partially occluded by intermediate objects.