Connected Component Trees for Multivariate Image Processing and Applications in Astronomy

Some special topics in multivariate image analysis

A simple imaging system has been developed for acquiring multivariate images in order to characterise the heterogeneity of food materials. The objective of the present work is, first, to demonstrate the capability of this acquisition system to discriminate food products of different natures. Secondly, our goal is to apply Partial Least Squares regression on these multivariate images and to evaluate the interest of various strategies of classification. A data set containing 24 images (702 × 524) acquired at different wavelengths for four food products is analysed. After the establishment of the PLS2 models employed for predicting the indicator variables, four strategies of classification of observations are tested. The first classification is done by selecting the largest component of the indicator variables. The others are based on the measurement of distances to the barycentres of the qualitative groups. Distances calculated can be either Euclidian distances or Mahalonobis distances. Except the strategy based on the Euclidian distance on scores, the strategies are rather equivalent, with a slight advantage to the Euclidian distance on predicted indicators. Another possibility addressed by the use of linear discriminant analysis (LDA) on multivariate images is to represent the qualitative groups as artificial images. The largest confusion appears between both cereal products while others are well classified. Copyright © 2006 John Wiley & Sons, Ltd.

Acousto-optic tunable filters (AOTFs) can be used as spectral filters in multispectral imaging applications. Acousto-optic crystals diffract a single wavelength from a broadband light beam, depending on the applied radio frequency signal. However, experimental measurements show that the actual performance is far from the expected behavior. We present an experimental characterization of several commercial off-the-shelf AOTFs for the implementation of multispectral imaging instruments. The diffraction performance of three bare crystals is compared, while a fourth AOTF crystal is mounted on the optical path of a multispectral imager to evaluate its performance. The experiments show that the behavior of all the analyzed AOTFs differs from the theoretical expectations and presents uneven diffraction efficiency, a Gaussian dependency with the applied power, and a strong nonlinear relationship with the driving signal frequency. The different behavior of each AOTF in terms of all the analyzed parameters shows the necessity for an in-depth characterization of the AOTF performance once mounted on a multispectral imaging device if quantitative measurements are required. Finally, several recommendations for use are derived from these experimental results.

Fast infrared imaging spectroscopy technique (FIIST)

2D-Discrete Fourier Transform: Generalization of the MIA-QSAR strategy in molecular modeling

Improving heterogeneous classification accuracy based on the MDFAT and the combination feature information of multi-spectral transmission images

Appearances and qualities of remote sensing images are affected by different atmospheric conditions, quality of sensors, and radiometric calibrations. This heavily challenges the generalization ability of a deep learning or other machine learning model: the performance of a model pretrained on a source remote sensing data set can significantly decrease when applied to a different target data set. The popular generative adversarial networks (GANs) can realize style or appearance transfer between a source and target data sets, which may boost the performance of a deep learning model through generating new target images similar to source samples. In this study, we comprehensively evaluate the performance of GAN-based image-level transfer methods on convolutional neural network (CNN) based image processing models that are trained on one dataset and tested on another one. Firstly, we designed the framework for the evaluation process. The framework consists of two main parts, the GAN-based image-level domain adaptation, which transfers a target image to a new image with similar probability distribution of source image space, and the CNN-based image processing tasks, which are used to test the effects of GAN-based domain adaptation. Second, the domain adaptation is implemented with two mainstream GAN methods for style transfer, the CycleGAN and the AgGAN. The image processing contains two major tasks, segmentation and object detection. The former and the latter are designed based on the widely applied U-Net and Faster R-CNN, respectively. Finally, three experiments, associated with three datasets, are designed to cover different application cases, a change detection case where temporal data is collected from the same scene, a two-city case where images are collected from different regions and a two-sensor case where images are obtained from aerial and satellite platforms respectively. Results revealed that, the GAN-based image transfer can significantly boost the performance of the segmentation model in the change detection case, however, it did not surpass conventional methods; in the other two cases, the GAN-based methods obtained worse results. In object detection, almost all the methods failed to boost the performance of the Faster R-CNN and the GAN-based methods performed the worst.

Chapter 5 - Hyperspectral imaging applications

Object localization and detection is the emerging area of computer vision and image processing that finds out the location of the object in the video frames or in the digital images. Object localization and detection have many challenges like occlusion, scale variations, intraclass similarities, illumination conditions, pose variations, etc. Multi-view object detection focuses on different views of objects like the top, bottom, side view, etc. We aim to discuss the different Object detection models based on Machine learning and Deep neural network approaches in a multi-view environment. We also discuss different datasets used for object detections and their applications. We apply some object detection models like SSD and Faster R-CNN to specific object categories of Open Image Dataset V6 and compare the results based on mAP (Mean Average Precision).KeywordsObject detectionConvolution neural networksR-CNNFast R-CNNFaster R-CNNEfficientDetCenterNet

A multispectral imaging system for automated inspection of wholesome and systemically diseased chickens was developed and demonstrated. The disease of septicemia was selected as the detection target because it is the most common chicken disease in US. From visible/near-infrared reflectance spectra of poultry carcasses, average CIELAB L*(lightness), a*(redness), and b*(yellowness) values were analyzed. The difference of lightness between wholesome and septicemic chickens was significant. The multispectral imaging system consisted of a backilluminated CCD camera and a spectrometer with four narrow-band interference filters for 488, 540, 580, and 610 nm wavelengths, respectively. The 16-bit multispectral images of chicken carcasses were collected for image processing and analysis. Image processing algorithms, including image registration, flat-field correction, image segmentation, region of interest identification, feature measurement, and symptom recognition, were developed to differentiate septicemic chickens from wholesome ones. The image from 610-nm wavelength was used to create a mask to extract chicken images from background. The average reflectance intensities at 488, 540, 580, and 610 nm from different parts of the carcass in the front side were calculated. Moreover, four normalization methods and four normalized differentiation methods between two wavelengths were also calculated for comparison. Decision tree was applied to generate thresholds for differentiation between wholesome and septicemic chickens. Images were collected at three time frames. The images from the first time frame were used to generate first thresholds that were tested by the images from the second time frames. Then, the images from the first and second time frames were used together to generate second thresholds. The first and second thresholds were tested by the images from the third time frame, respectively. The results showed that using average intensity at 580 nm from the region of interest, 98.6% of septicemic chickens and 96.3% of wholesome chickens could be differentiated from each other. More training data could help to generate more appropriate thresholds used at different time frames.

8 - Nanoparticles for biomedical imaging advancements

High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms

A deep analysis of the image and video processing techniques using nanoscale quantum-dots cellular automata

Data fusion technique can produce fused images with high spatial resolution and abundant spectral information. A new image fusion algorithm based on two-dimension PCA and Curvelet transform will be proposed according to image process models specialities in this paper. First of all, we performed 2DPCA on the MS image to get the 1st principle component (PC1); then we applied Curvelet transform in Pan Image and PC1; lastly decomposition coefficients obtained was processed according to certain rules to get fused coefficients, and afterwards, we performed inverse Curvelet transform on them to acquire fused sub-images. Then we performed inverse 2DPCA transform on the other components and the fused sub-images to get fused images. Experiments will be carried out via application of multispectral and panchromatic images, and it turns out that this new algorithm can improve spatial resolution greatly while maintaining spectral information.

In recent years, deep learning algorithm has been used in many applications mainly in image processing of object detection and classification. The use of image processing techniques is becoming more interesting with the existence of drone technology with the employ of deep learning in aerial view image processing because of the high resolution and heaps of images taken. This paper aims to review neural networks specifically on the aerial view image by drones and to discuss the work principles and classic architectures of convolutional neural networks, its latest research trend and typical models along with target detection in object detection, image classification and semantic segmentation. In addition, this study also provided a specific application in the aerial image. Finally, the limitations of the convolutional network and expected future development trends were also discussed. Based on the findings, the deep learning algorithm was observed to provide high accuracy, it outperformed other generally image processing-based techniques.