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.
We present a technique for optic cup segmentation and outlining based on Kåsa's circle fit model. The outlining problem is posed as a task of fitting a circle to the sparse set of optic cup boundary points. For automatic localization of the optic disc, we use the matched filtering technique. We clear-off the non-optic disc area by drawing a circle with point of optic disc localization as the coordinates...
This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos. The proposed SegFlow has two branches where useful information of object segmentation and optical flow is propagated bidirectionally in a unified framework. The segmentation branch is based on a fully convolutional network, which has been proved effective...
We report single-measurement, full-range imaging of local polarization properties in the human anterior segment in vivo with polarization-sensitive optical coherence tomography (PS-OCT). Off-pivot galvanometer-mirror phase shifting used to extend the system's axial imaging range sufficiently to reconstruct local polarization properties of the anterior segment.
The optic disc (OD) segmentation in an retinal image is prerequisite for an computerized detection of diabetic retinopathy and also for monitoring changes due to diseases such as glaucoma. The OD segmentation is also used for the detection of other anatomical structures like fovea and vascular tree. Many algorithms based on thresholding, active contour model, GVF snake and clustering have been proposed...
The article describes some questions of functioning of digital cameras with purpose to increase optical resolution of the photos. The presented work includes detailed analysis and comparison of options, possible for nowadays, of improvements of optical resolution. The first offered option — use of the software. In the second option use of other different filters instead of Bayer filter is considered...
In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very lit- tle extra computational cost. This module is called Net- Warp and we demonstrate its use for a range of network architectures. The main design principle is to use opti- cal flow...
Video deblurring is a challenging problem as the blur is complex and usually caused by the combination of camera shakes, object motions, and depth variations. Optical flow can be used for kernel estimation since it predicts motion trajectories. However, the estimates are often inaccurate in complex scenes at object boundaries, which are crucial in kernel estimation. In this paper, we exploit semantic...
A temporal superpixel algorithm based on proximity-weighted patch matching (TS-PPM) is proposed in this work. We develop the proximity-weighted patch matching (PPM), which estimates the motion vector of a superpixel robustly, by considering the patch matching distances of neighboring superpixels as well as the target superpixel. In each frame, we initialize superpixels by transferring the superpixel...
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision. With dual-lens smart phones, such as iPhone 7+ and Huawei P9, coming into the market, two images of slightly different views provide us new information to unify the two topics. We propose a joint method to tackle them simultaneously via a joint fully connected conditional random...
Pixel-level annotations are expensive and timeconsuming to obtain. Hence, weak supervision using only image tags could have a significant impact in semantic segmentation. Recent years have seen great progress in weakly-supervised semantic segmentation, whether from a single image or from videos. However, most existing methods are designed to handle a single background class. In practical applications,...
We introduce an approach to integrate segmentation information within a convolutional neural network (CNN). This counter-acts the tendency of CNNs to smooth information across regions and increases their spatial precision. To obtain segmentation information, we set up a CNN to provide an embedding space where region co-membership can be estimated based on Euclidean distance. We use these embeddings...
General human action recognition requires understanding of various visual cues. In this paper, we propose a network architecture that computes and integrates the most important visual cues for action recognition: pose, motion, and the raw images. For the integration, we introduce a Markov chain model which adds cues successively. The resulting approach is efficient and applicable to action classification...
Comprehensive utilization of SAR image and optical satellite photograph is a vital yet challenging task in remote sensing detection field. For this purpose, multisensory image registration is a conceivable approach. This paper presents an automatic registration method for SAR and optical images based on line extraction and control points selection. To begin with, line extraction is implemented with...
Detection of optic disc in retinal images is an important step in disease diagnosis and patient follow-up. Optic disc detection is a Preprocess step for the diagnosis of many diseases, such as glaucoma and DP (Diabetic Retinopathy), which are vital for the eye. In this study, a hybrid approach is proposed for fully automatic segmentation of Optic Disc (OD). The first phase of the study consists of...
Intravascular photoacoustic (IVPA) imaging is being developed to improve and guide treatment of atherosclerotic vulnerable plaques. While lipid has been successfully imaged, current studies have not determined how many or which optical wavelength(s) will accurately characterize atherosclerotic plaques. We leverage Monte Carlo (MC) optical modeling to determine the optimal dual-wavelength combination...
Organizing and rearranging library books in appropriate order requires attention and care of librarians. The book indexing and organizing algorithm will detect misplaced library books and suggest a proper position to the user. It can be implemented in a smartphone or a server or an autonomous embedded system. It first segments the captured image to find proper tag area in the book. Then crops that...
A method is proposed using image processing techniques, which is an automated method for detection of suspected glaucoma. In this paper an algorithm is proposed to detect suspected glaucoma by using the presence or absence of hemorrhages in a particular region, near the optic disc, in fundus image. Unlike existing methods, which only uses cup to disc ratio as a deciding parameter to detect glaucoma,...
We propose an end-to-end learning framework for segmenting generic objects in videos. Our method learns to combine appearance and motion information to produce pixel level segmentation masks for all prominent objects in videos. We formulate this task as a structured prediction problem and design a two-stream fully convolutional neural network which fuses together motion and appearance in a unified...
Surveillance video parsing, which segments the video frames into several labels, e.g., face, pants, left-leg, has wide applications [41, 8]. However, pixel-wisely annotating all frames is tedious and inefficient. In this paper, we develop a Single frame Video Parsing (SVP) method which requires only one labeled frame per video in training stage. To parse one particular frame, the video segment preceding...
We propose a novel superpixel-based multi-view convolutional neural network for semantic image segmentation. The proposed network produces a high quality segmentation of a single image by leveraging information from additional views of the same scene. Particularly in indoor videos such as captured by robotic platforms or handheld and bodyworn RGBD cameras, nearby video frames provide diverse viewpoints...
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.