Optical Coherence Tomography (OCT) is an emerging medical imaging modality for luminal organ diagnosis. The non-constant rotation speed of optical components in the OCT catheter tip causes rotational distortion in OCT volumetric scanning. By improving the scanning process, this instability can be partially reduced. To further correct the rotational distortion in the OCT image, a volumetric data stabilization algorithm is proposed. The algorithm first estimates the Non-Uniform Rotational Distortion (NURD) for each B-scan by using a Convolutional Neural Network (CNN). A correlation map between two successive B-scans is computed and provided as input to the CNN. To solve the problem of accumulative error in iterative frame stream processing, we deploy an overall rotation estimation between reference orientation and actual OCT image orientation. We train the network with synthetic OCT videos by intentionally adding rotational distortion into real OCT images. As part of this article we discuss the proposed method in two different scanning modes: the first is a conventional pullback mode where the optical components move along the protection sheath, and the second is a self-designed scanning mode where the catheter is globally translated by using an external actuator. The efficiency and robustness of the proposed method are evaluated with synthetic scans as well as real scans under two scanning modes.
The goal of this work is to efficiently identify visually similar patterns from a pair of images, e.g. identifying an artwork detail copied between an engraving and an oil painting, or matching a night-time photograph with its daytime counterpart. Lack of training data is a key challenge for this co-segmentation task. We present a simple yet surprisingly effective approach to overcome this difficulty: we generate synthetic training pairs by selecting object segments in an image and copy-pasting them into another image. We then learn to predict the repeated object masks. We find that it is crucial to predict the correspondences as an auxiliary task and to use Poisson blending and style transfer on the training pairs to generalize on real data. We analyse results with two deep architectures relevant to our joint image analysis task: a transformer-based architecture and Sparse Nc-Net, a recent network designed to predict coarse correspondences using 4D convolutions. We show our approach provides clear improvements for artwork details retrieval on the Brueghel dataset and achieves competitive performance on two place recognition benchmarks, Tokyo247 and Pitts30K. We then demonstrate the potential of our approach by performing object discovery on the Internet object discovery dataset and the Brueghel dataset. Our code and data are available at http://imagine.enpc.fr/~shenx/SegSwap/.
In order to transmit electrical energy in a continuous and quality manner, it is necessary to control it from the point of production to the point of consumption. Therefore, protection of transmission and distribution lines is essential at every stage from production to consumption. The main function of the protection relays in electrical installations should be deactivated as soon as possible in the event of short circuits in the system. The most important part of the system is energy transmission lines and distance protection relays that protect these lines. An accurate error location technique is required to make fast and efficient work. Transformer neutral point grounding in transmission lines affects the operation of the zero component current during the single phase to ground short circuit failure of a power system. Considering the relationship between the grounding system and protection systems, an appropriate grounding choice should be made. Artificial neural network (ANN) has been used in order to accurately locate short circuit faults in different grounding systems in transmission lines. Compared with support vector machines (SVM) for testing inside ANN The transmission line model is made in the PSCAD-EMTDC simulation program. Data sets were created by recording the image of the impedance change of the R-X impedance diagram of the distance protection relay in short circuit faults created in different grounding systems. The related focal points in the images are given as an introduction to different ANN models using feature extraction and image processing techniques and the ANN model with the highest fault location estimation accuracy was chosen.
Optical Projection Tomography (OPT) is a powerful tool for 3D imaging of mesoscopic samples, thus of great importance to image whole organs for the study of various disease models in life sciences. OPT is able to achieve resolution at a few tens of microns over a large sample volume of several cubic centimeters. However, the reconstructed OPT images often suffer from artifacts caused by different kinds of physical miscalibration. This work focuses on the refractive index (RI) mismatch between the rotating object and the surrounding medium. We derive a 3D cone beam forward model to approximate the effect of RI mismatch and implement a fast and efficient reconstruction method to correct the induced seagull-shaped artifacts on experimental images of fluorescent beads.
Physical computing infrastructure, data gathering, and algorithms have recently had significant advances to extract information from images and videos. The growth has been especially outstanding in image captioning and video captioning. However, most of the advancements in video captioning still take place in short videos. In this research, we caption longer videos only by using the keyframes, which are a small subset of the total video frames. Instead of processing thousands of frames, only a few frames are processed depending on the number of keyframes. There is a trade-off between the computation of many frames and the speed of the captioning process. The approach in this research is to allow the user to specify the trade-off between execution time and accuracy. In addition, we argue that linking images, videos, and natural language offers many practical benefits and immediate practical applications. From the modeling perspective, instead of designing and staging explicit algorithms to process videos and generate captions in complex processing pipelines, our contribution lies in designing hybrid deep learning architectures to apply in long videos by captioning video keyframes. We consider the technology and the methodology that we have developed as steps toward the applications discussed in this research.
Probing or fine-tuning (large-scale) pre-trained models results in state-of-the-art performance for many NLP tasks and, more recently, even for computer vision tasks when combined with image data. Unfortunately, these approaches also entail severe risks. In particular, large image datasets automatically scraped from the web may contain derogatory terms as categories and offensive images, and may also underrepresent specific classes. Consequently, there is an urgent need to carefully document datasets and curate their content. Unfortunately, this process is tedious and error-prone. We show that pre-trained transformers themselves provide a methodology for the automated curation of large-scale vision datasets. Based on human-annotated examples and the implicit knowledge of a CLIP based model, we demonstrate that one can select relevant prompts for rating the offensiveness of an image. In addition to e.g. privacy violation and pornographic content previously identified in ImageNet, we demonstrate that our approach identifies further inappropriate and potentially offensive content.
Coarse-to-fine models and cascade segmentation architectures are widely adopted to solve the problem of large scale variations in medical image segmentation. However, those methods have two primary limitations: the first-stage segmentation becomes a performance bottleneck; the lack of overall differentiability makes the training process of two stages asynchronous and inconsistent. In this paper, we propose a differentiable two-stage network architecture to tackle these problems. In the first stage, a localization network (L-Net) locates Regions of Interest (RoIs) in a detection fashion; in the second stage, a segmentation network (S-Net) performs fine segmentation on the recalibrated RoIs; a RoI recalibration module between L-Net and S-Net eliminating the inconsistencies. Experimental results on the public dataset show that our method outperforms state-of-the-art coarse-to-fine models with negligible computation overheads.
In the last few years, large improvements in image clustering have been driven by the recent advances in deep learning. However, due to the architectural complexity of deep neural networks, there is no mathematical theory that explains the success of deep clustering techniques. In this work we introduce Projected-Scattering Spectral Clustering (PSSC), a state-of-the-art, stable, and fast algorithm for image clustering, which is also mathematically interpretable. PSSC includes a novel method to exploit the geometric structure of the scattering transform of small images. This method is inspired by the observation that, in the scattering transform domain, the subspaces formed by the eigenvectors corresponding to the few largest eigenvalues of the data matrices of individual classes are nearly shared among different classes. Therefore, projecting out those shared subspaces reduces the intra-class variability, substantially increasing the clustering performance. We call this method Projection onto Orthogonal Complement (POC). Our experiments demonstrate that PSSC obtains the best results among all shallow clustering algorithms. Moreover, it achieves comparable clustering performance to that of recent state-of-the-art clustering techniques, while reducing the execution time by more than one order of magnitude. In the spirit of reproducible research, we publish a high quality code repository along with the paper.
The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The process of creating and curating such a dataset is a monumental undertaking, demanding extensive effort and labelling expense and necessitating careful navigation of technical and social issues such as label accuracy, copyright ownership, and content bias. What if we had a way to harness the power of large image datasets but with few or none of the major issues and concerns currently faced? This paper extends the recent work of Kataoka et. al. (2020), proposing an improved pre-training dataset based on dynamically-generated fractal images. Challenging issues with large-scale image datasets become points of elegance for fractal pre-training: perfect label accuracy at zero cost; no need to store/transmit large image archives; no privacy/demographic bias/concerns of inappropriate content, as no humans are pictured; limitless supply and diversity of images; and the images are free/open-source. Perhaps surprisingly, avoiding these difficulties imposes only a small penalty in performance. Leveraging a newly-proposed pre-training task -- multi-instance prediction -- our experiments demonstrate that fine-tuning a network pre-trained using fractals attains 92.7-98.1\% of the accuracy of an ImageNet pre-trained network.
Lesion detection is a fundamental problem in the computer-aided diagnosis scheme for mammography. The advance of deep learning techniques have made a remarkable progress for this task, provided that the training data are large and sufficiently diverse in terms of image style and quality. In particular, the diversity of image style may be majorly attributed to the vendor factor. However, the collection of mammograms from vendors as many as possible is very expensive and sometimes impractical for laboratory-scale studies. Accordingly, to further augment the generalization capability of deep learning model to various vendors with limited resources, a new contrastive learning scheme is developed. Specifically, the backbone network is firstly trained with a multi-style and multi-view unsupervised self-learning scheme for the embedding of invariant features to various vendor-styles. Afterward, the backbone network is then recalibrated to the downstream task of lesion detection with the specific supervised learning. The proposed method is evaluated with mammograms from four vendors and one unseen public dataset. The experimental results suggest that our approach can effectively improve detection performance on both seen and unseen domains, and outperforms many state-of-the-art (SOTA) generalization methods.