An official website of the United States government
Compressive Sensing enables improvement of acquisition of a variety of signals in various applications with little to no discernible loss in terms of recovered image quality. The current work proposes a signal processing framework for the acquisition and fast reconstruction of compressively sampled hyperspectral images using an artificial neural network architecture. This ANN-based approach is capable of performing a fast reconstruction by avoiding the requirement of solving a computationally intensive image-specific optimization problem. The proposed framework contributes to advance single-pixel hyperspectral imaging device methodologies, which enable a significant reduction in device mechanical complexity, imaging rate, and cost. Our experiments demonstrate that a hyperspectral image can be reconstructed using only 10% of the samples without compromising classification performance. Specifically, the results show that classification performance of the compressively sampled hyperspectral image recovered using artificial neural networks is equal or higher to that of those obtained using current scanning hyperspectral imaging platforms.
more »
« less
RCMDD: A Denoising Architecture for Improved Recovery of Reflectance Confocal Microscopy Images of Skin from Compressive Samples
he Compressive Sensing (CS) framework has demonstrated improved acquisition efficiency on a variety of clinical applications. Of interest to this work is Reflectance Confocal Microscopy (RCM), where CS can influence a drastic reduction in instrumentation complexity and image acquisition times. However, CS introduces the disadvantage of requiring a time consuming and computationally intensive process for image recovery. To mitigate this, the current document details our preliminary work on expanding a Deep-Learning architecture for the acquisition and fast recovery of RCM images using CS. We show preliminary recoveries of RCM images of both a synthetic target and heterogeneous skin tissue using a state-of-the-art network architecture from compressive measurements at various undersampling rates. In addition, we propose an application-specific addition to an established network architecture, and evaluate its ability to further increase the accuracy of recovered CS RCM images and remove visual artifacts. Our initial results show that it is possible to recover compressively sampled images at near-real time rates with comparable quality to established computationally intensive and time-consuming optimization-based methods common in CS applications
more »
« less
- Award ID(s):
- 1750970
- PAR ID:
- 10155757
- Date Published:
- Journal Name:
- 2019 IEEE International Conference on E-health Networking, Application & Services (HealthCom)
- Page Range / eLocation ID:
- 1 to 6
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
End-to-end data-driven image compressive sensing reconstruction (EDCSR) frameworks achieve state-of-the-art reconstruction performance in terms of reconstruction speed and accuracy. However, due to their end-to-end nature, existing EDCSR frameworks can not adapt to a variable compression ratio (CR). For applications that desire a variable CR, existing EDCSR frameworks must be trained from scratch at each CR, which is computationally costly and time-consuming. This paper presents a generic compression ratio adapter (CRA) framework that addresses the variable compression ratio (CR) problem for existing EDCSR frameworks with no modification to given reconstruction models nor enormous rounds of training needed. CRA exploits an initial reconstruction network to generate an initial estimate of reconstruction results based on a small portion of the acquired measurements. Subsequently, CRA approximates full measurements for the main reconstruction network by complementing the sensed measurements with resensed initial estimate. Our experiments based on two public image datasets (CIFAR10 and Set5) show that CRA provides an average of 13.02 dB and 5.38 dB PSNR improvement across the CRs from 5 to 30 over a naive zero-padding approach and the AdaptiveNN approach(a prior work), respectively. CRA addresses the fixed-CR limitation of existing EDCSR frameworks and makes them suitable for resource-constrained compressive sensing applications.more » « less
-
Extracting roads in aerial images has numerous applications in artificial intelligence and multimedia computing, including traffic pattern analysis and parking space planning. Learning deep neural networks, though very successful, demands vast amounts of high-quality annotations, of which acquisition is time-consuming and expensive. In this work, we propose a semi-supervised approach for image-based road extraction where only a small set of labeled images are available for training to address this challenge. We design a pixel-wise contrastive loss to self-supervise the network training to utilize the large corpus of unlabeled images. The key idea is to identify pairs of overlapping image regions (positive) or non-overlapping image regions (negative) and encourage the network to make similar outputs for positive pairs or dissimilar outputs for negative pairs. We also develop a negative sampling strategy to filter false negative samples during the process. An iterative procedure is introduced to apply the network over raw images to generate pseudo-labels, filter and select high-quality labels with the proposed contrastive loss, and re-train the network with the enlarged training dataset. We repeat these iterative steps until convergence. We validate the effectiveness of the proposed methods by performing extensive experiments on the public SpaceNet3 and DeepGlobe Road datasets. Results show that our proposed method achieves state-of-the-art results on public image segmentation benchmarks and significantly outperforms other semi-supervised methods.more » « less
-
This paper addresses the single-image compressive sensing (CS) and reconstruction problem. We propose a scalable Laplacian pyramid reconstructive adversarial network (LAPRAN) that enables high-fidelity, flexible and fast CS images reconstruction. LAPRAN progressively reconstructs an image following the concept of the Laplacian pyramid through multiple stages of reconstructive adversarial networks (RANs). At each pyramid level, CS measurements are fused with a contextual latent vector to generate a high-frequency image residual. Consequently, LAPRAN can produce hierarchies of reconstructed images and each with an incremental resolution and improved quality. The scalable pyramid structure of LAPRAN enables high-fidelity CS reconstruction with a flexible resolution that is adaptive to a wide range of compression ratios (CRs), which is infeasible with existing methods. Experimental results on multiple public datasets show that LAPRAN offers an average 7.47dB and 5.98dB PSNR, and an average 57.93% and 33.20% SSIM improvement compared to model-based and data-driven baselines, respectively.more » « less
-
Virtual Staining of Defocused Autofluorescence Images of Unlabeled Tissue Using Deep Neural NetworksDeep learning-based virtual staining was developed to introduce image contrast to label-free tissue sections, digitally matching the histological staining, which is time-consuming, labor-intensive, and destructive to tissue. Standard virtual staining requires high autofocusing precision during the whole slide imaging of label-free tissue, which consumes a significant portion of the total imaging time and can lead to tissue photodamage. Here, we introduce a fast virtual staining framework that can stain defocused autofluorescence images of unlabeled tissue, achieving equivalent performance to virtual staining of in-focus label-free images, also saving significant imaging time by lowering the microscope’s autofocusing precision. This framework incorporates a virtual autofocusing neural network to digitally refocus the defocused images and then transforms the refocused images into virtually stained images using a successive network. These cascaded networks form a collaborative inference scheme: the virtual staining model regularizes the virtual autofocusing network through a style loss during the training. To demonstrate the efficacy of this framework, we trained and blindly tested these networks using human lung tissue. Using 4× fewer focus points with 2× lower focusing precision, we successfully transformed the coarsely-focused autofluorescence images into high-quality virtually stained H&E images, matching the standard virtual staining framework that used finely-focused autofluorescence input images. Without sacrificing the staining quality, this framework decreases the total image acquisition time needed for virtual staining of a label-free whole-slide image (WSI) by ~32%, together with a ~89% decrease in the autofocusing time, and has the potential to eliminate the laborious and costly histochemical staining process in pathology.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/HealthCom46333.2019.9009434
