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.
In this study, we propose a novel shape-based traffic sign detection method which consists of two stages. First, a rotational symmetry voting scheme is proposed to detect the centers and boundary sets of the candidate polygons in the image. Second, a Link Distribution (LD) model, which considers a polygon as the collection of links between center and boundary points, is proposed to refine the detection...
Automatic segmentation of the left ventricle (LV) can become a useful tool in echocardiography, for instance to provide automatic ejection fraction measurements or to initialize deformation imaging algorithms. Deep neural networks have recently shown very promising results for improving image classification and segmentation. These methods learn using only a set of input and output data, but require...
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...
Forensic odontology is one method of determining the identity of the individuals who use it as a base dental identification. Teeth can provide information about the individual's identity because of its distinctive. Currently, the process of forensic identification through dental radiography is performed manually so it took a long time to match the teeth with human identity. Therefore, we need a system...
Traffic sign recognition is an important step for integrating smart vehicles into existing road transportation systems. In this paper, an NVIDIA Jetson TX1-based traffic sign recognition system is introduced for driver assistance applications. The system incorporates two major operations, traffic sign detection and recognition. Image color and shape based detection is used to locate potential signs...
From the empirical studies, it is quite difficult for the license plate recognition to perform 100% accuracy in a real world environment. Nevertheless, it is common that only a few characters are misread from a license plate recognition system. In this paper, license plate matching is used for vehicle re-identification. We evaluate several approximate string matching techniques to determine an applicable...
In this paper, we propose a new person re-identification algorithm based on bi-directional superpixel earth mover's distance (BD-SP-EMD). To address the viewpoint change issue, the human body segmentation is first extracted based on background modeling and saliency maps. A bi-directional scheme is then applied to obtain the forward and backward SP-EMD distances. Based on these two distances, pedestrians...
In this paper, we address the problem of gender classification based on facial images. The Speeded Up Robust Feature (SURF) algorithm descriptors are used as features to built dictionaries and a multi-task Sparse Representation Classification (SRC) is used as classifier to determine the gender of an individual face. Our approach uses smaller and compact dictionaries by removing the redundant atoms...
In this paper, we propose a two-step textural feature extraction method, which utilizes the feature learning ability of Convolutional Neural Networks (CNN) to extract a set of low level primitive filter kernels, and then generalizes the discriminative power by forming a histogram based descriptor. The proposed method is applied to a practical medical diagnosis problem of classifying different stages...
In many countries, robots and automation techniques are being introduced in agriculture farms to reduce the human labour and to improve the yield. However, such technological initiatives are still lacking in India, although it is the leading producer of many vegetables and fruits, for example, coconuts. Some of the activities carried out in a coconut farm that requires human labor are coconut dehusking,...
Parametrisation of the shape of deformable objects is of paramount importance in many computer vision applications. Many state-of-the-art statistical deformable models perform landmark localisation via optimising an objective function over a certain parametrisation of the object's shape. Arguably, the most popular way is by employing statistical techniques. The points of shape samples of an object...
We propose a real-time algorithm for the generic classification of humans and objects in 3D scenes. The algorithm does not depend on color information and works with depth data alone, making it very flexible for a wide area of applications. Further, we will show that it is very resistant to occlusion and will give correct classification results even in cases, where only a fraction of a full human...
In order to better learn the distributions of 2D and 3D faces and the mapping between them with limited training samples, a new 3D face reconstruction method based on progressive cascade regression is proposed. Firstly, it learns the mapping between 2D and 3D facial landmarks to estimate the initial 3D facial landmarks with a coupled space learning method. Secondly, a deformed space is constructed...
In this work, we present a novel method for capturing human body shape from a single scaled silhouette. We combine deep correlated features capturing different 2D views, and embedding spaces based on 3D cues in a novel convolutional neural network (CNN) based architecture. We first train a CNN to find a richer body shape representation space from pose invariant 3D human shape descriptors. Then, we...
Current object detection approaches predict bounding boxes that provide little instance-specific information beyond location, scale and aspect ratio. In this work, we propose to regress directly to objects shapes in addition to their bounding boxes and categories. It is crucial to find an appropriate shape representation that is compact and decodable, and in which objects can be compared for higher-order...
We study the problem of learning generative models of 3D shapes. Voxels or 3D parts have been widely used as the underlying representations to build complex 3D shapes, however, voxel-based representations suffer from high memory requirements, and parts-based models require a large collection of cached or richly parametrized parts. We take an alternative approach: learning a generative model over multi-view...
Shape models provide a compact parameterization of a class of shapes, and have been shown to be important to a variety of vision problems, including object detection, tracking, and image segmentation. Learning generative shape models from grid-structured representations, aka silhouettes, is usually hindered by (1) data likelihoods with intractable marginals and posteriors, (2) high-dimensional shape...
Generation of 3D data by deep neural network has been attracting increasing attention in the research community. The majority of extant works resort to regular representations such as volumetric grids or collection of images, however, these representations obscure the natural invariance of 3D shapes under geometric transformations, and also suffer from a number of other issues. In this paper we address...
There have been remarkable improvements in the semantic labelling task in the recent years. However, the state of the art methods rely on large-scale pixel-level annotations. This paper studies the problem of training a pixel-wise semantic labeller network from image-level annotations of the present object classes. Recently, it has been shown that high quality seeds indicating discriminative object...
We present a transformation-grounded image generation network for novel 3D view synthesis from a single image. Our approach first explicitly infers the parts of the geometry visible both in the input and novel views and then casts the remaining synthesis problem as image completion. Specifically, we both predict a flow to move the pixels from the input to the novel view along with a novel visibility...
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.