Hasil untuk "eess.IV"

Théo Ladune, Pierrick Philippe, Gordon Clare et al.

This paper summarises the design of the Cool-Chic candidate for the Challenge on Learned Image Compression. This candidate attempts to demonstrate that neural coding methods can lead to low complexity and lightweight image decoders while still offering competitive performance. The approach is based on the already published overfitted lightweight neural networks Cool-Chic, further adapted to the human subjective viewing targeted in this challenge.

Maliha Hossain, Charles A. Bouman, Brendt Wohlberg

Flash X-ray computed tomography (CT) is an important imaging modality for characterization of high-speed dynamic events, such as Kolsky bar impact experiments for the study of mechanical properties of materials subjected to impulsive forces. Due to experimental constraints, the number of X-ray views that can be obtained is typically very sparse in both space and time, requiring strong priors in order to enable a CT reconstruction. In this paper, we propose an effective method for exploiting the cylindrical symmetry inherent in the experiment via a variant of total variation (TV) regularization that operates in cylindrical coordinates, and demonstrate that it outperforms competing approaches.

Jerome Gilles

In this paper, we propose to improve image decomposition algorithms in the case of noisy images. In \cite{gilles1,aujoluvw}, the authors propose to separate structures, textures and noise from an image. Unfortunately, the use of separable wavelets shows some artefacts. In this paper, we propose to replace the wavelet transform by the contourlet transform which better approximate geometry in images. For that, we define contourlet spaces and their associated norms. Then, we get an iterative algorithm which we test on two noisy textured images.

Jerome Gilles

In this paper, we investigate theoretically the behavior of Meyer's image cartoon + texture decomposition model. Our main results is a new theorem which shows that, by combining the decomposition model and a well chosen Littlewood-Paley filter, it is possible to extract almost perfectly a certain class of textures. This theorem leads us to the construction of a parameterless multiscale texture separation algorithm. Finally, we propose to extend this algorithm into a directional multiscale texture separation algorithm by designing a directional Littlewood-Paley filter bank. Several experiments show the efficiency of the proposed method both on synthetic and real images.

Amir Said

We propose a new class of kernels to simplify the design of filters for image interpolation and resizing. Their properties are defined according to two parameters, specifying the width of the transition band and the height of a unique sidelobe. By varying these parameters it is possible to efficiently explore the space with only the filters that are suitable for image interpolation and resizing, and identify the filter that is best for a given application. These two parameters are also sufficient to obtain very good approximations of many commonly-used interpolation kernels. We also show that, because the Fourier transforms of these kernels have very fast decay, these filters produce better results when time-stretched for image downsizing.

Tatiana Latychevskaia

Conventional three-dimensional (3D) imaging methods require multiple measurements of the sample in different orientation or scanning. When the sample is probed with coherent waves, a single two-dimensional (2D) intensity measurement is sufficient as it contains all the information of the 3D sample distribution. We show a method that allows reconstruction of 3D sample distribution from a single 2D intensity measurement, at the z-resolution exceeding the classical limit. The method can be practical for radiation-sensitive materials, or where the experimental setup allows only one intensity measurement.

Christian Herglotz, Elisabeth Walencik, André Kaup

This paper presents a method to accurately estimate the required decoding energy for a given HEVC software decoding solution. We show that the decoder's processing time as returned by common C++ and UNIX functions is a highly suitable parameter to obtain valid estimations for the actual decoding energy. We verify this hypothesis by performing an exhaustive measurement series using different decoder setups and video bit streams. Our findings can be used by developers and researchers in the search for new energy saving video compression algorithms.

Josef Lorenz Rumberger, Elias Baumann, Peter Hirsch et al.

We describe here the panoptic segmentation method we devised for our participation in the CoNIC: Colon Nuclei Identification and Counting Challenge at ISBI 2022. Key features of our method are a weighted loss specifically engineered for semantic segmentation of highly imbalanced cell types, and a state-of-the art nuclei instance segmentation model, which we combine in a Hovernet-like architecture.

Vi Thi-Tuong Vo, Soo-Hyung Kim, Taebum Lee

Nuclei Identification and Counting is the most important morphological feature of cancers, especially in the colon. Many deep learning-based methods have been proposed to deal with this problem. In this work, we construct an extension of Hovernet for nuclei identification and counting to address the problem named MF-Hovernet. Our proposed model is the combination of multiple filer block to Hovernet architecture. The current result shows the efficiency of multiple filter block to improve the performance of the original Hovernet model.

Pranath Reddy

The primary goal of this work is to study the effectiveness of an unsupervised domain adaptation approach for various applications such as binary classification and anomaly detection in the context of Alzheimer's disease (AD) detection for the OASIS datasets. We also explore image reconstruction and image synthesis for analyzing and generating 3D structural MRI data to establish performance benchmarks for anomaly detection. We successfully demonstrate that domain adaptation improves the performance of AD detection when implemented in both supervised and unsupervised settings. Additionally, the proposed methodology achieves state-of-the-art performance for binary classification on the OASIS-1 dataset.

Vidit Gautam

Advance in medical imaging is an important part in deep learning research. One of the goals of computer vision is development of a holistic, comprehensive model which can identify tumors from histology slides obtained via biopsies. A major problem that stands in the way is lack of data for a few cancer-types. In this paper, we ascertain that data augmentation using GANs can be a viable solution to reduce the unevenness in the distribution of different cancer types in our dataset. Our demonstration showed that a dataset augmented to a 50% increase causes an increase in tumor detection from 80% to 87.5%

Vassillen Chizhov, Joachim Weickert

Harmonic inpainting with optimised data is very popular for inpainting-based image compression. We improve this approach in three important aspects. Firstly, we replace the standard finite differences discretisation by a finite element method with triangle elements. This does not only speed up inpainting and data selection, but even improves the reconstruction quality. Secondly, we propose highly efficient algorithms for spatial and tonal data optimisation that are several orders of magnitude faster than state-of-the-art methods. Last but not least, we show that our algorithms also allow working with very large images. This has previously been impractical due to the memory and runtime requirements of prior algorithms.

Michael Drob

With the proliferation of Wi-Fi devices in the environment, our surroundings are increasingly illuminated with low-level RF scatter. This scatter illuminates objects in the environment much like radar or LIDAR. We show that a novel unsupervised network, based on the PIX2PIX GAN architecture, can recover and visually reconstruct scene information solely from Wi-Fi background energy; in contrast to a significantly less accurate approach by Kefayati (et. all) which requires careful object labeling to recover object location from a scene. This is accomplished by learning a more robust mapping function between the channel state information (CSI) from Wi-Fi packets and Video image sample distributions.

Théo Ladune, Pierrick Philippe

In 2021, a new track has been initiated in the Challenge for Learned Image Compression~: the video track. This category proposes to explore technologies for the compression of short video clips at 1 Mbit/s. This paper proposes to generate coded videos using the latest standardized video coders, especially Versatile Video Coding (VVC). The objective is not only to measure the progress made by learning techniques compared to the state of the art video coders, but also to quantify their progress from years to years. With this in mind, this paper documents how to generate the video sequences fulfilling the requirements of this challenge, in a reproducible way, targeting the maximum performance for VVC.

Sheng Cao, Chao-Yuan Wu, Philipp Krähenbühl

We introduce a simple and efficient lossless image compression algorithm. We store a low resolution version of an image as raw pixels, followed by several iterations of lossless super-resolution. For lossless super-resolution, we predict the probability of a high-resolution image, conditioned on the low-resolution input, and use entropy coding to compress this super-resolution operator. Super-Resolution based Compression (SReC) is able to achieve state-of-the-art compression rates with practical runtimes on large datasets. Code is available online at https://github.com/caoscott/SReC.

Abhisha Mano

The segmentation of Lamina Cribrosa(LC) is a challenging task to detect the glaucomatous damage. In this paper a new method of segmenting the LC using bat optimized Watershed segmentation is done. By using wavelet transform LC structures are decomposed. Then, the decomposed image is optimized using Bat algorithm and by applying histogram equalization the optimized image is normalized. Watershed algorithm is used to segment the Lamina Cribrosa from its outer layer. Using some parameters like PSNR, MSE, F-Measure, rand index, sensitivity, specificity, SSIM and accuracy, the performance of the proposed system is calculated. The results show that the proposed method provides higher accuracy of 99.29%.

Stefano Zorzi, Friedrich Fraundorfer

In this paper we present a method for building boundary refinement and regularization in satellite images using a fully convolutional neural network trained with a combination of adversarial and regularized losses. Compared to a pure Mask R-CNN model, the overall algorithm can achieve equivalent performance in terms of accuracy and completeness. However, unlike Mask R-CNN that produces irregular footprints, our framework generates regularized and visually pleasing building boundaries which are beneficial in many applications.

Hoai-Thu Nguyen, Pierre Croisille, Magalie Viallon et al.

In this study, segmentation of quadriceps muscle heads of ultra-endurance athletes was done using a multi-atlas segmentation and corrective leaning framework where the registration based multi-atlas segmentation step was replaced with weakly supervised U-Net. For the case with remarkably different morphology, our method produced improved accuracy, while reduced significantly the computation time.

Mario A. Beltran, David M. Paganin

We study generalized dark-field imaging systems. These are a subset of linear shift-invariant optical imaging systems, that exhibit arbitrary aberrations, and for which normally-incident plane-wave input yields zero output. We write down the theory for the forward problem of imaging coherent scalar optical fields using such arbitrarily-aberrated dark-field systems, and give numerical examples. The associated images may be viewed as a form of dark-field Gabor holography, utilizing arbitrary outgoing Green functions as generalized Huygens-type wavelets, and with the Young-type boundary wave forming the holographic reference.

Suman Kunwar

Malaria is mosquito-borne blood disease caused by parasites of the genus Plasmodium. Conventional diagnostic tool for malaria is the examination of stained blood cell of patient in microscope. The blood to be tested is placed in a slide and is observed under a microscope to count the number of infected RBC. An expert technician is involved in the examination of the slide with intense visual and mental concentration. This is tiresome and time consuming process. In this paper, we construct a new mage processing system for detection and quantification of plasmodium parasites in blood smear slide, later we develop Machine Learning algorithm to learn, detect and determine the types of infected cells according to its features.