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.
A pectoral muscle usually resembles a salient dense region, which is roughly triangular shape, in mediolateral oblique (MLO) position mammography. Similarly, masses usually appear to be salient dense in mammograms. Therefore, first of all, most computer-aided detection (CAD) systems remove the pectoral muscle region in order to reduce the number of false positives. In this study, a method is proposed...
Cardiovascular disease is one of today's major health problems. These diseases are the result of constriction or blockage of coronary vessels feeding heart. Diagnosis of Cardiovascular contraction is determined visually by physicians with angio imaging method. Visually defined vascular diseases may give subjective results. Vessel constrictions in angiograms are automatically determined by vascular...
Recent work in terrain recognition for outdoor mobile robots mainly focused on several typical pure terrain sample classification, and only one terrain feature is extracted for terrain sample description. In this paper, a segmentation scheme for complex terrain samples is designed for the terrain recognition process. The segmentation scheme is achieved using the graph segmentation followed by the...
Lineage tracing, the joint segmentation and tracking of living cells as they move and divide in a sequence of light microscopy images, is a challenging task. Jug et al. [21] have proposed a mathematical abstraction of this task, the moral lineage tracing problem (MLTP), whose feasible solutions define both a segmentation of every image and a lineage forest of cells. Their branch-and-cut algorithm,...
We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression and lighting. To perform this mapping, we use convolutional neural networks trained to capture the appearance of the target identity from an unstructured collection of his/her photographs. This approach is enabled by framing the face swapping problem...
Most of the prior works summarize videos by either exploring different heuristically designed criteria in an unsupervised way or developing fully supervised algorithms by leveraging human-crafted training data in form of video-summary pairs or importance annotations. However, unsupervised methods are blind to the video category and often fail to produce semantically meaningful video summaries. On...
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations. The source and target classes might share similar appearance (e.g. bear fur is similar to cat fur) or appear against similar background (e.g. horse and sheep appear against grass). To exploit this,...
Despite the recent success of deep-learning based semantic segmentation, deploying a pre-trained road scene segmenter to a city whose images are not presented in the training set would not achieve satisfactory performance due to dataset biases. Instead of collecting a large number of annotated images of each city of interest to train or refine the segmenter, we propose an unsupervised learning approach...
The ability to predict and therefore to anticipate the future is an important attribute of intelligence. It is also of utmost importance in real-time systems, e.g. in robotics or autonomous driving, which depend on visual scene understanding for decision making. While prediction of the raw RGB pixel values in future video frames has been studied in previous work, here we introduce the novel task of...
Creating road maps is essential for applications such as autonomous driving and city planning. Most approaches in industry focus on leveraging expensive sensors mounted on top of a fleet of cars. This results in very accurate estimates when exploiting a user in the loop. However, these solutions are very expensive and have small coverage. In contrast, in this paper we propose an approach that directly...
Object part segmentation is a challenging and fundamental problem in computer vision. Its difficulties may be caused by the varying viewpoints, poses, and topological structures, which can be attributed to an essential reason, i.e., a specific object is a 3D model rather than a 2D figure. Therefore, we conjecture that not only 2D appearance features but also 3D geometric features could be helpful...
Manually annotating object bounding boxes is central to building computer vision datasets, and it is very time consuming (annotating ILSVRC [53] took 35s for one high-quality box [62]). It involves clicking on imaginary comers of a tight box around the object. This is difficult as these comers are often outside the actual object and several adjustments are required to obtain a tight box. We propose...
Plenoptic images captured from plenoptic cameras provide angular information as well as conventional spatial information of the scene. Using the angular information, plenoptic imaging can generate multiview images. In this paper, we developed approaches for object segmentation on 4D hyper volume represented with the multiview images. Our approaches are based on graph cut algorithms and applied connected...
A contourn descriptor generator algorithm implemented in embedded system of new generation to obtain shape characterization of manufactured rigid objects is presented in the paper. Acquisition and processing stages to obtain information about the shape of rigid object by way of a descriptor vector are shown in order to be implemented in a single hardware piece processor embedded system to obtain parallel...
This paper presents a method to detect small flooded areas from images which contain also vegetation zones. So, two classes are considered: flood class and vegetation. For the learning phase a supervised technique based on small patches is used. Based on efficiency analysis, the Histograms of Oriented Gradients on H colour channel and mean intensity on gray level are selected as discriminated features...
Geographic mapping of coffee crops by using remote sensing images and supervised classification has been a challenging research subject. Besides the intrinsic problems caused by the nature of multi-spectral information, coffee crops are non-seasonal and usually planted in mountains, which requires encoding and learning a huge diversity of patterns during the classifier training. In this paper, we...
A digital image may contain objects that can be made up of multiple regions concerning different material properties, physical or chemical attributes. Thus, segmented simplicial meshes with non-manifold boundaries are generated to represent the partitioned regions. We focus on repairing non-manifold boundaries. Current methods modify the topology, geometry or both, using their own data structures...
Biometrics, previously used only in human identification, can help experts in the analysis of biological images. Flies of the genus Drosophila have become model organisms by almost global presence and short life cycle. Facial recognition techniques and geometric morphometry can be used in image processing for classification. The latter requires human interaction. This work details a methodology based...
In view of the close relationship between insulator fault and surface temperature distribution, a detection method for insulator string is proposed combined infrared image segmentation and artificial neural network, which is based on the analysis of infrared image processing and fault diagnosis of artificial neural network. Firstly, the steel cap and the disk of insulator string are extracted according...
Leukemia is a worldwide disease. In this paper we demonstrate that it is possible to build an automated, efficient and rapid leukemia diagnosis system. We demonstrate that it is possible to improve the precision of current techniques from the literature using the description power of well-known Convolutional Neural Networks (CNNs). We extract features from a blood smear image using pre-trained CNNs...
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.