The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Insulator is an important guarantee for the safe operation of electrified railway, but because of working conditions, the insulator would face long-term effects of wind, snow and rain. Insulator surface would easily accumulate filth and pollution flashover occurs, which often leads to blackouts and threatens the safe operation of the railway. Therefore, detection of the insulator working state is...
The classification and identification of the bird species from the visual image is complex compared by using audio song. The knowledge of the features species type is very important as to ensure it is classified to the correct species. Color-based feature extraction is one of the procedure in extracting the color properties from the bird which to represent the species of the bird. However, it is a...
Because there are many false targets in the seabed imaging of SAS (synthetic aperture sonar), it is difficult for the automatic alarm of buried column targets. An automatic alarm method for buried targets based on membership classification is proposed in this paper. Firstly, the mean-standard deviation maximum entropy segmentation is used to segment seabed image. Then the area and posture ratio of...
Lung cancer is a disease that caused by uncontrolled cell growth in lung. Lung cancer is still the first worldwide killer. CT Scan Thorax is a method for early detection of lung cancer patients. However, cancer detection in lung CT-Scan image still done manually. In this paper, the segmentation of lung image is proposed. Cancer segmentation will process the lung CT-Scan as an image input with watershed...
Stress echocardiography is an ultrasound imaging technique to assess the functionality of wall segments of the left ventricle (LV). However, image quality is inadequate in up to 30% of patients, requiring the administration of contrast agents. Coherence-based beamforming methods have shown promise in improving image quality by mitigating clutter, a major source of image degradation. In a previous...
An airborne ultrasound imaging system using 16 ultrasonic sensors surrounding a region of interest (ROI) was introduced in previous work. It allows reconstructing reflectivity images of multiple objects in 2D using a synthetic aperture focusing technique. The aim of this work is to automatically segment objects from these images to determine their positioning and allow classification.
Realization of automated reading and video processing to study efficient algorithms for tracking the dynamics of growth and spread of spores of mesophilic and thermophilic microorganisms were studied. The basic steps based on the algorithm of automatic counting and tracking spore colonies in real time were investigated.
Accuracy in segmenting of brain vessels from medical angiographic data is crucial for further modelling and assessment of the human vasculature. It was demonstrated that the level set (LS) approach enhanced by the implementation of the vesselness function (VF) provides a robust segmentation framework enabling the high-quality vessel network extracted from CT and MR images. This work investigates the...
Defect detection and recognition of bare PCB plays a significant role in computer vision applications. An accurate and efficient approach is implemented in this paper. The approach is based on the comparison between the standard PCB image and the target image. Multiple images of the qualified PCBs are acquired at the same position. We take an average of the images and consider it to be an initial...
We propose a multigrid extension of convolutional neural networks (CNNs). Rather than manipulating representations living on a single spatial grid, our network layers operate across scale space, on a pyramid of grids. They consume multigrid inputs and produce multigrid outputs, convolutional filters themselves have both within-scale and cross-scale extent. This aspect is distinct from simple multiscale...
Most current semantic segmentation methods rely on fully convolutional networks (FCNs). However, their use of large receptive fields and many pooling layers cause low spatial resolution inside the deep layers. This leads to predictions with poor localization around the boundaries. Prior work has attempted to address this issue by post-processing predictions with CRFs or MRFs. But such models often...
This paper proposes an algorithm that turns a regular video capturing urban scenes into a high-quality endless animation, known as a Cinemagraph. The creation of a Cinemagraph usually requires a static camera in a carefully configured scene. The task becomes challenging for a regular video with a moving camera and objects. Our approach first warps an input video into the viewpoint of a reference camera...
One of recent trends [31, 32, 14] in network architecture design is stacking small filters (e.g., 1x1 or 3x3) in the entire network because the stacked small filters is more efficient than a large kernel, given the same computational complexity. However, in the field of semantic segmentation, where we need to perform dense per-pixel prediction, we find that the large kernel (and effective receptive...
Target segmentation of synthetic aperture radar (SAR) images is one of the challenging problems in SAR image interpretation, which often serves as a processing step for SAR target recognition. Target segmentation tries to separate the target from the background thus eliminating the interference of background noises or clutters. However, the segmentation may also discard a part of the target characteristics...
As the urinary sediment images have low contrast and blur edges meanwhile the visible components are complicated and there are a lot of overlapped cells in them, it is difficult to perform accurate and efficient segmentation. This paper proposes a urinary sediment image segmentation method based on standard deviation gradient with dual-threshold. First the morphological filtering is done to the image,...
This paper proposes a scattering model based segmentation technique for polarimetric synthetic aperture radar (PolSAR) images. The method is composed of two main parts: merging predicate and merging order. The merging predicate is based on the idea of the fractal network evolution algorithm (FNEA). The heterogeneity of the scattering characteristics between adjacent regions is calculated to judge...
We introduce a novel loss max-pooling concept for handling imbalanced training data distributions, applicable as alternative loss layer in the context of deep neural networks for semantic image segmentation. Most real-world semantic segmentation datasets exhibit long tail distributions with few object categories comprising the majority of data and consequently biasing the classifiers towards them...
State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g...
This paper proposes an efficient algorithm for noise level estimation in still images. The images are assumed to be corrupted by additive white Gaussian noise. The proposed method relies on block-based image segmentation and Gaussian filtering to estimate the standard deviation of Gaussian noise. The proposed method employs adaptive image segmentation, where the size of segmentation blocks is derived...
Histopathology plays a role as the gold standard in clinic for disease diagnosis. The identification and segmentation of histological structures are the prerequisite to disease diagnosis. With the advent of digital pathology, researchers' attention is attracted by the analysis of digital pathology images. In order to relieve the workload on pathologists, a robust segmentation method is needed in clinic...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.