Search results for "artificial intelligence"
showing 10 items of 6122 documents
Views selection for SIFT based object modeling and recognition
2016
In this paper we focus on automatically learning object models in the framework of keypoint based object recognition. The proposed method uses a collection of views of the objects to build the model. For each object the collection is composed of N×M views obtained rotating the object around its vertical and horizontal axis. As keypoint based object recognition using a complete set of views is computationally expensive, we focused on the definition of a selection method that creates, for each object, a subset of the initial views that visually summarize the characteristics of the object and should be suited for recognition. We select the views by determining maxima and minima of a function, …
An enhanced random walk algorithm for delineation of head and neck cancers in PET studies
2017
An algorithm for delineating complex head and neck cancers in positron emission tomography (PET) images is presented in this article. An enhanced random walk (RW) algorithm with automatic seed detection is proposed and used to make the segmentation process feasible in the event of inhomogeneous lesions with bifurcations. In addition, an adaptive probability threshold and a k-means based clustering technique have been integrated in the proposed enhanced RW algorithm. The new threshold is capable of following the intensity changes between adjacent slices along the whole cancer volume, leading to an operator-independent algorithm. Validation experiments were first conducted on phantom studies:…
Anam-Net: Anamorphic Depth Embedding-Based Lightweight CNN for Segmentation of Anomalies in COVID-19 Chest CT Images.
2021
Chest computed tomography (CT) imaging has become indispensable for staging and managing coronavirus disease 2019 (COVID-19), and current evaluation of anomalies/abnormalities associated with COVID-19 has been performed majorly by the visual score. The development of automated methods for quantifying COVID-19 abnormalities in these CT images is invaluable to clinicians. The hallmark of COVID-19 in chest CT images is the presence of ground-glass opacities in the lung region, which are tedious to segment manually. We propose anamorphic depth embedding-based lightweight CNN, called Anam-Net, to segment anomalies in COVID-19 chest CT images. The proposed Anam-Net has 7.8 times fewer parameters …
A mutual GrabCut method to solve co-segmentation
2013
Publised version of an article from the journal:Eurasip Journal on Image and Video Processing. Also available on SpringerLink:http://dx.doi.org/10.1186/1687-5281-2013-20. Open Access Co-segmentation aims at segmenting common objects from a group of images. Markov random field (MRF) has been widely used to solve co-segmentation, which introduces a global constraint to make the foreground similar to each other. However, it is difficult to minimize the new model. In this paper, we propose a new Markov random field-based co-segmentation model to solve co-segmentation problem without minimization problem. In our model, foreground similarity constraint is added into the unary term of MRF model ra…
PORE Algorithm for Object Recognition in Photo Layers based on Parametric Characteristics of the Object Edges
2016
PORE stands for Photo-Object Recognition based on the Edges. Coincidentally, PORE means to examine something carefully and with due attention, so "we pore over the object layers in search for information about their characteristics with the aim at improving image recognition process". Therefore, this study presents a novel approach to object recognition based on the pattern by using photo layers and by defining the objects' specific characteristics. We select and introduce the parameters which determine a higher efficiency of image retrieval of the image objects. In this paper, we describe how the same photos are recognized in a process of classical retrieval compared to our model by analyz…
Perception of illusory surfaces and contours in goldfish
2007
Goldfish(Carassius auratus)were trained to discriminate triangles and squares using a two choice procedure. In the first experiment, three goldfish were trained with food reward on a black outline triangle on a white background, while a black outline square was shown for comparison. In transfer tests, a Kanizsa triangle and a Kanizsa square were presented, perceived by humans as an illusory triangle- or square-shaped surface of slightly higher brightness than the background. The choice behavior in this situation indicates that goldfish are able to discriminate between both figures in almost the same way as in the training situation. In control experiments goldfish did not discriminate betwe…
Comparison of Intensity-based B-splines and Point-to-Pixel Tracking Techniques for Motion Reduction in Optical Mapping
2016
Suppression of motion artifacts (MA) in cardiac optical mapping usually requires uncoupling of cardiac contraction by restriction techniques, which are known to have important effects on cardiac physiology deteriorating the quality of acquisitions and their interpretation. In this study, we propose to assess the performance of two independent intensity-based post-processing strategies to minimize MAs during registration. A point-to-pixel block-matching classical similarity-based tracking with displacement interpolation is compared to a well-known non-rigid registration algorithm where the deformation field is obtained using cubic splines. Both strategies were tested on synthetic and real op…
A Coupled Schema of Probabilistic Atlas and Statistical Shape and Appearance Model for 3D Prostate Segmentation in MR Images
2012
International audience; A hybrid framework of probabilistic atlas and statistical shape and appearance model (SSAM) is proposed to achieve 3D prostate segmentation. An initial 3D segmentation of the prostate is obtained by registering the probabilistic atlas to the test dataset with deformable Demons registration. The initial results obtained are used to initialize multiple SSAMs corresponding to the apex, central and base regions of the prostate gland to incorporate local variabilities. Multiple mean parametric models of shape and appearance are derived from principal component analysis of prior shape and intensity information of the prostate from the training data. The parameters are then…
An Online Metric Learning Approach through Margin Maximization
2011
This work introduces a method based on learning similarity measures between pairs of objects in any representation space that allows to develop convenient recognition algorithms. The problem is formulated through margin maximization over distance values so that it can discriminate between similar (intra-class) and dissimilar (inter-class) elements without enforcing positive definiteness of the metric matrix as in most competing approaches. A passive-aggressive approach has been adopted to carry out the corresponding optimization procedure. The proposed approach has been empirically compared to state of the art metric learning on several publicly available databases showing its potential bot…
Trademarks recognition based on local regions similarities
2010
This paper deals with content based image retrieval. We propose a logo recognition algorithm based on local regions, where the trademark (or logo) image is segmented by the clustering of points of interest obtained by Harris corners detector. The minimum rectangle surrounding each cluster is detected forming the regions of interest. Global features such as Hu moments and histograms of each local region are combined to find similar logos in the database. Similarity is measured based on the integrated minimum average distance of the individual components. The results obtained demonstrate tolerance to logos distortions such as rotation, occlusion and noise.