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 describe an efficient contour generation scheme implemented on a general purpose graphics processing unit (GPU) which extracts multiple contours in parallel from a high resolution multivalued image or depth map. In this paper, we describe an extension of a two stage crack based contour generation on GPU whose performance is hampered by horizontal dependencies generated when a contour crosses a...
This paper is devoted to investigation of features that will be the most appropriate for description of high resolution satellite imagery. We developed an image description model which is based on the distribution of image object classes. Proposed model could be used for image similarity estimation.
In most convolutional neural networks (CNNs), the output is a single classification result by combining all the neuron activations in the last layer. As we know, local connectivity is an important characteristic of CNNs. Each neuron in the network corresponds to a local region in the original image. Hence, it is possible to simultaneously obtain local visibility of a target object by analyzing neuron...
In the paper, a rough spatial kernelized fuzzy c-means clustering (RSKFCM) based medical image segmentation algorithm is proposed. This technique is a combination of rough set and spatial kernelized fuzzy c-means clustering (SKFCM). SKFCM is failed to remove the indistinct knowledge that is associated with each data set during the process of its assignment to a particular cluster. The rough set is...
A new color image segmentation of noisy images based on spatial information with the Generalized Dirichlet mixture model is presented. The methodology uses Markov Random Field distribution with a novel factor that is induced in mixture model. The model is learned using Expectation Maximization (EM) algorithm based on Newton-Raphson approach. The obtained results using real images are more encouraging...
The presence of outliers, noise, corrupt pieces of data and great quantity of samples in a multispectral image, makes the segmentation analysis work tedious. The fuzzy clustering approach, specially, is susceptible to inhomogeneity of characteristics. Furthermore, many algorithms such us FCM, PFCM, FCC, FWCM and modification aim to solve these problems by integrating spacial information. This process...
Data clustering methods have been used extensively for image segmentation in the past decade. In our previous work, we had established that combining the traditional clustering algorithms with a meta-heuristic like Firefly Algorithm improves the stability of the output as well as the speed of convergence. In this paper, we have replaced the Euclidean distance formula with kernels. We have combined...
Most state-of-the-art text detection methods are specific to horizontal Latin text and are not fast enough for real-time applications. We introduce Segment Linking (SegLink), an oriented text detection method. The main idea is to decompose text into two locally detectable elements, namely segments and links. A segment is an oriented box covering a part of a word or text line, A link connects two adjacent...
We propose an index of textural feature for oil spill segmentation based on X-band marine radar image. The radar image used in this paper were acquired on July 21, 2010, from the teaching-training ship, “YUKUN”, of Dalian Maritime University. Using adaptive median filter and Fields-of-Experts model, co-channel interference and small objects are cleaned separately. An index calculated by textural features...
Segmenting 3D objects from a set of disordered point cloud is always one challenge work in Bin-pi cking systems. In this paper, an easy and valid algorithm is proposed to solve this problem. The point data set obtained from a low-cost depth camera, RealSense, can be quickly filtered to be a much clean compact one, significantly saving the computing resources. The filtered points set is next divided...
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...
While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance segmentation is very important in a variety of applications, such as autonomous driving, image captioning, and visual question answering. Techniques that combine...
Pleiades-HR is a high resolution remote sensing system developed by the French Space Agency (CNES) for civil and military users. The constellation is composed of two identical satellites PHR1A launched on 2011, December 17th and PHR1B launched one year after, on 2012, December 2nd. More than 600 images can be daily acquired by each satellite in various viewing angles conditions: the satellites are...
A map-guided superpixel segmentation method for hyperspectral imagery is developed and introduced. The proposed approach develops a hyperspectral version of the SLIC superpixel algorithm, leverages map information to guide segmentation, and incorporates the semi-supervised Partial Membership Latent Dirichlet Allocation (sPM-LDA) to obtain a final segmentation. The proposed method is applied to two...
In this paper, a novel human activity recognition method is presented. The proposed solution uses a single stationary camera in order to detect common human activities like: hand waving, walking, running etc. Unlike other methods which use different kinds of characteristic point descriptors in order to describe human poses, the proposed solution uses a CDVS descriptor which is part of the MPEG-7 standard...
The availability of finger-touch mobile devices has provided a feasible platform for drawing based image retrieval. While text labels represent a sematic description of an image, drawings represent a visual description of the image. In this paper, we describe the development and preliminary design of a game with a purpose that with potential to build a dataset for drawing based image retrieval field...
In biology and medicine, it is critical to study the amount, distribution, movement, status, and behavior of cells. To do this, one should well segment cells from three dimensional (3D) cell images in prior and precisely extract the moving path of each cell. In this work, an advanced 3D cell segmentation and tracing algorithm is proposed. It applies local histograms to perform adaptive thresholding...
Object-Based Image Analysis (OBIA) has gained swift popularity in remote sensing area mainly due to the increasing availability of very high resolution imagery. Image segmentation is a major step within OBIA process. Image segmentation quality remarkably influences the subsequent image classification accuracy. It is necessary to implement advanced and robust methods to increase image segmentation...
Globally, the oil palm industry leads the supply of oils and fats, and is a very dynamic sector thanks to its wide use and applications in different products. However, some studies have shown that oil palm cultivation causes enormous damage to the environment by the destruction of existing forests, or by excessive use of fertilizers and pesticides, making crude palm oil uncompetitive and strong constraints...
The study of flower classification system is a very important subject in the field of Botany. A classifier of flowers with high accuracy will also bring a lot of fun to people's lives. However, because of the complex background of flowers, the similarity between the different species of flowers, and the differences among the same species of flowers, there are still some challenges in the recognition...
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.