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 propose a novel measure of visual similarity for image retrieval that incorporates both structural and aesthetic (style) constraints. Our algorithm accepts a query as sketched shape, and a set of one or more contextual images specifying the desired visual aesthetic. A triplet network is used to learn a feature embedding capable of measuring style similarity independent of structure, delivering...
Face alignment has witnessed substantial progress in the last decade. One of the recent focuses has been aligning a dense 3D face shape to face images with large head poses. The dominant technology used is based on the cascade of regressors, e.g., CNNs, which has shown promising results. Nonetheless, the cascade of CNNs suffers from several drawbacks, e.g., lack of end-to-end training, handcrafted...
This paper presents a serious game designed for children suffering from profound intellectual and multiple disabilities (PIMD) also know as multihandicap, for their evaluation and cognitive training. The specificities of these children must be taken into account for the choice of both the game feedbacks and interfaces.
This paper presents a new discriminative learning framework to associate the relationship between the objects and the words in an image and perform template matching scheme for complex association patterns. The problem is first formulated as a bipartite graph matching problem. Thereafter, structural support vector machine (SVM) is employed to obtain the optimal compatibility function to encode the...
Playing building blocks has good features such as growing up children's intellect and finger manipulation abilities. To enhance good features in playing with building blocks, various mechatronic toys inspired by building block have been developed and released. We have developed mechatro-tsumiki, a kind of building blocks made of cube shape wood materials in which a mechatronics system is embedded...
Segmentation of biomedical images is a challenging task, especially when there is low quality or missing data. The use of prior information can provide significant assistance for obtaining more accurate results. In this paper we propose a new approach for dendritic spine segmentation from microscopic images over time, which is motivated by incorporating shape information from previous time points...
Introducing features that better represent the visual information of speakers during the speech production is still an open issue that highly affects the quality of the lip-reading and Audio Visual Speech Recognition (AVSR) tasks. In this paper, three different types of visual features from both the image-based and model-based ones are investigated inside a professional lip reading task. The simple...
Inappropriate medication use such as wrong drug or wrong dose intake can be harmful to patients. In this work we present a method to automatically identify a pill from a single image using Convolutional Neural Network (CNN). We first localize the pill in the image by detecting the region with the highest concentration of edges. To overcome the challenge of minimal labeled training data and domain...
The detection of cells and nuclei is a crucial step for the automatic analysis of digital pathology slides and as such for the quantification of the phenotypic information contained in tissue sections. This task is however challenging because of high variability in size, shape and textural appearance of the objects to be detected and of the high variability of tissue appearance. In this work, we propose...
Learning visual attributes is an effective approach for zero-shot recognition. However, existing methods are restricted to learning explicitly nameable attributes and cannot tell which attributes are more important to the recognition task. In this paper, we propose a unified framework named Grouped Simile Ensemble (GSE). We claim our contributions as follows. 1) We propose to substitute explicit attribute...
We present an approach for unsupervised computation of local shape descriptors, which relies on the use of linear autoencoders for characterizing local regions of complex shapes. The proposed approach responds to the need for a robust scheme to index binary images using local descriptors, which arises when only few examples of the complete images are available for training, thus making inaccurate...
This research extends the Hierarchical Temporal Memory (HTM) algorithm and applies it to gait recognition. The gait sequence first is decomposed into temporal sub-sequences of spatial sub-regions. The sub-sequence are defined as the period of one step and half step, and the sub-regions are defined as the areas that correspond to body parts. Each sub-area will learn the temporal variation of the body...
This paper presents a new representation for handwritten math formulae: a Line-of-Sight (LOS) graph over handwritten strokes, computed using stroke convex hulls. Experimental results using the CROHME 2012 and 2014 datasets show that LOS graphs capture the visual structure of handwritten formulae better than commonly used graphs such as Time-series, Minimum Spanning Trees, and k-Nearest Neighbor graphs...
Sketch-based image retrieval (SBIR) is a challenging task due to the ambiguity inherent in sketches when compared with photos. In this paper, we propose a novel convolutional neural network based on Siamese network for SBIR. The main idea is to pull output feature vectors closer for input sketch-image pairs that are labeled as similar, and push them away if irrelevant. This is achieved by jointly...
Significant progress has been made in recent years for computer-aided diagnosis of abnormal pulmonary textures from computed tomography (CT) images. Similar initiatives in chest radiographs (CXR), the common modality for pulmonary diagnosis, are much less developed. CXR are fast, cost effective and low-radiation solution to diagnosis over CT. However, the subtlety of textures in CXR makes them hard...
In open-ended domains, autonomous robots must have the ability to continuously process visual information, and execute learning and recognition in a concurrent and interleaved fashion. Because the set of categories to be learned is not predefined, it is not feasible to assume that one can pre-program all object categories required by service robots. Topic modelling approaches usually construct the...
Children suffering from prelingual hearing impairments have difficulty in speech acquisition due to lack of auditory feedback. They can benefit by speech training aids providing corrective feedback, especially those providing visual feedback of key articulatory efforts. These aids should enable a comparison between the articulatory efforts of the student and that of a teacher or a reference speaker...
Many of object detection methods are based on training phase. Theses methods are constrained to a known object. In this paper, we present a free training method for object detection that can deal with large viewpoint change. We exploit Dempster theory to combine between multiple descriptors in a multi stage method. To show the effectiveness of the technique, we apply it on multiple images from Coil100...
The current work proposes an approach for the recognition of plants from their digital leaf images using multiple visual features to handle heterogeneous plant types. Recognizing the fact that plant leaves can have a variety of recognizable features like color (green and non-green) and shape (simple and compound) and texture (vein structure patterns), a single set of features may not be efficient...
We introduce a new mono-camera system with multi-infrared lights for human posture recognition, which is based on the 3D body shape recovered from the body silhouette and cast shadows. We propose a new voxelization method inspired from the Shape From Silhouettes (SFS) approach for Visual Hull (VH) reconstruction. Our setup consists of 4 infrared lights installed in the different upper corners of a...
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.