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.
Semi-supervised clustering has been widely explored in the last years. In this paper, we present HCAC-ML (Hierarchical Confidence-based Active Clustering with Metric Learning), an innovative approach for this task which employs distance metric learning through cluster-level constraints. HCAC-ML is based on the HCAC algorithm, an state-of-the-art algorithm for hierarchical semi-supervised clustering...
This paper describes an algorithm usable for automatic determination of optimal length of casting steel blocks, of different shapes and sizes, in the context of an imprecise manufacturing due to an unpredictable end-user demand, meaning a supply order of steel blocks that is constantly changing. The proposed algorithm is a general solution that takes into account the technological limitation of a...
Detection and segmentation of small renal mass (SRM) in renal CT images are important pre-processing for computer-aided diagnosis of renal cancer. However, the task is known to be challenging due to its variety of size, shape, and location. In this paper, we propose an automated method for detecting and segmenting SRM in contrast-enhanced CT images using texture and context feature classification...
We present a learning based fully automatic method to detect and segment the prostate in T2 weighted MR scans. It consists of a localization stage which uses a learned global context to detect the prostate location. This is followed by a segmentation stage which uses a learned local context using prostatic segment specific discriminative classifiers, to compute the probability of a point being on...
Cervical nuclei carry substantial diagnostic information for cervical cancer. Therefore, in automation-assisted reading of cervical cytology, automated and accurate segmentation of nuclei is essential. This paper proposes a novel approach for segmentation of cervical nuclei that combines fully convolutional networks (FCN) and graph-based approach (FCNG). FCN is trained to learn the nucleus high-level...
Many researchers use convolutional neural networks with small rectangular filters for music (spectrograms) classification. First, we discuss why there is no reason to use this filters setup by default and second, we point that more efficient architectures could be implemented if the characteristics of the music features are considered during the design process. Specifically, we propose a novel design...
This study presents articulation data of American English laterals and rhotics captured by combining real-time 3D ultrasound, digitized 3D palate impressions, and time-aligned audio recordings. While articulation of laterals and rhotics has long been of interest, traditional two-dimensional imaging techniques are subject to limitations because the vocal tract is three-dimensional. The technological...
Research on visual material recognition has traditionally been based on texture analysis. Whereas older work has focused on uncluttered scenes, more recent contributions allowed for material recognition 'in the wild'. Quite some objects have untextured surfaces, however. Especially man-made examples are legion. The most obvious cue to use in such cases would be reflection information. Yet, methods...
We extend a novel 2D shape descriptor called Distance Interior Ratio (DIR) [4] to describe a 3D shape represented by a volumetric model, called 3DDIR. The 3DDIR is defined as follow: Given a segment ab between two points a and b on the surface of an object O, the DIR of ab is the ratio of the total length of its fragments O ∩ ab to the length |ab|. To find the fragments O ∩ ab, we apply a simple ray...
Paper presents the Shape Movement Pattern (ShaMP) algorithm, an algorithm for extracting Movement Patterns (MPs) from network data, and a prediction mechanism whereby the identified MPs can be used to predict the nature of movement in a previously unseen network. The principal advantage offered by ShaMP is that it lends itself to parallelisation. The reported evaluation was conducted using both Massage...
Using shape context descriptors in the distance uneven grouping and its more extensive description of the shape feature, so this descriptor has the target contour point set deformation invariance. However, the twisted adhesions verification code have more outliers and more serious noise, the above-mentioned invariance of the shape context will become very bad, in order to solve the above descriptors'...
Co-registration of point clouds is critical when a scene is measured several times. We present a novel feature based solution, where features are described by combining local shape context and local intensity (or image) context. The Euclidean distances of such shape and intensity combined context descriptors are used to identify candidate correspondences, which are then used as input to the final...
In the context of tree species recognition, botanists knowledge was used in different works specially when recognising tree species through leaves. In this paper, two sub-classification strategies for tree species recognition are proposed. For each sub-classification strategy, Basic belief assignment (Bba) was determined and obtained data were fused thanks to a totally adaptive fusion system implemented...
The Levy Walk (or Levy flight) is a concept fromBiomathematics to describe the hunting–behaviour of manypredatory species. It is a very efficient way to find prey in avery short time frame. We now want to use this concept ina clustering–context to – if you so will – "hunt" for clusters. We describe how we convert this concept into an efficient wayto find cluster centres by linking the data...
Concepts of 3-dimensional (3D) Geometry are challenging to grasp for school students. The skill of manipulating 3D objects and interpreting their structure and properties are difficult. Traditionally to teach topics that have three dimensions, 3D artifacts have been used. However the opportunity of the learner to interact during the construction and manipulation of 3D objects is desirable. In this...
User Experience Design (UXD) addresses the increasing importance of emotional aspects in user product interaction and aims at creating holistic experiences. While UXD is a rather young field within product development, other disciplines outside engineering design (e.g. gaming, sports) traditionally focus on fascinating their users. Based on the approach of transferring insights from experience focused...
Hand activity is a critical monitoring component in understanding a driver's behavior within the car. Current vision-based hand detection algorithms perform poorly in naturalistic settings, due to various challenges such as global illumination changes and constant hand deformation and occlusion. To achieve a more accurate and robust hand detection system, this paper presents a hierarchical context-aware...
Attributes are the way we describe the world. A simple classification on attributes' object host or event host is not enough for explaining appearance of both object attributes and event attributes. Thus we propose a presentation and explanation for attributes which introduce single and group host criterion for object attributes and linguistic valence for event attributes. Especially, we argue that...
Image contains repetitive patterns always cause the point ambiguity, which makes the local descriptors less discriminative. The descriptor which is combined scale-invariant feature transform (SIFT) with the global context (GC) is used to solve the problem widely. But this descriptor is invalid when the variation of viewpoint is large. In this paper, an affine invariant matching method for image contains...
We propose a novel approach for multi-view object detection in 3D scenes reconstructed from RGB-D sensor. We utilize shape based representation using local shape context descriptors along with the voting strategy which is supported by unsupervised object proposals generated from 3D point cloud data. Our algorithm starts with a single-view object detection where object proposals generated in 3D space...
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.