Search results for " artificial intelligence"
showing 10 items of 1992 documents
Knowledge representation for robotic vision based on conceptual spaces and attentive mechanisms
1995
A new cognitive architecture for artificial vision is proposed. The architecture is aimed for an autonomous intelligent system, as several cognitive hypotheses have been postulated as guidelines for its design. The design is based on a conceptual representation level between the subsymbolic level processing the sensory data, and the linguistic level describing scenes by means of a high-level language. The architecture is also based on the active role of a focus of attention mechanism in the link between the conceptual and the linguistic level. The link between the conceptual level and the linguistic level is modelled as a time-delay attractor neural network.
Collocation Method for Linear BVPs via B-spline Based Fuzzy Transform
2018
The paper is devoted to an application of a modified F-transform technique based on B-splines in solving linear boundary value problems via the collocation method. An approximate solution is sought as a composite F-transform of a discrete function (which allows the solution to be compactly stored as the values of this discrete function). We demonstrate the effectiveness of the described technique with numerical examples, compare it with other methods and propose theoretical results on the order of approximation when the fuzzy partition is based on cubic B-splines.
Improving color correction across camera and illumination changes by contextual sample selection
2012
International audience; In many tasks of machine vision applications, it is important that recorded colors remain constant, in the real world scene, even under changes of the illuminants and the cameras. Contrary to the human vision system, a machine vision system exhibits inadequate adaptability to the variation of lighting conditions. Automatic white bal- ance control available in commercial cameras is not sufficient to pro- vide reproducible color classification. We address this problem of color constancy on a large image database acquired with varying digi- tal cameras and lighting conditions. A device-independent color repre- sentation may be obtained by applying a chromatic adaptation…
A Gamut Preserving Color Image Quantization
2007
International audience; We propose a new approach for color image quantization which preserves the shape of the color gamut of the studied image. Quantization consists to find a set of color representative of the color distribution of the image. We are looking here for an optimal LUT (look up table) which contains information on the image's gamut and on the color distribution of this image. The main motivation of this work is to control the reproduction of color images on different output devices in order to have the same color feeling, coupling intrinsic informations on the image gamut and output device calibration. We have developped a color quantization algorithm based on an image depend…
Color and Flow Based Superpixels for 3D Geometry Respecting Meshing
2014
We present an adaptive weight based superpixel segmentation method for the goal of creating mesh representation that respects the 3D scene structure. We propose a new fusion framework which employs both dense optical flow and color images to compute the probability of boundaries. The main contribution of this work is that we introduce a new color and optical flow pixel-wise weighting model that takes into account the non-linear error distribution of the depth estimation from optical flow. Experiments show that our method is better than the other state-of-art methods in terms of smaller error in the final produced mesh.
Perceptual similarity between color images using fuzzy metrics
2016
A method to measure the similarity between color images is proposed.Correlation among the color image channels is taken into account.Proposed similarity measure is based on fuzzy metrics because of their advantages.The proposal matches well with the perceptual visual similarity between color images. In many applications of the computer vision field measuring the similarity between (color) images is of paramount importance. However, the commonly used pixelwise similarity measures such as Mean Absolute Error, Peak Signal to Noise Ratio, Mean Squared Error or Normalized Color Difference do not match well with perceptual similarity. Recently, it has been proposed a method for gray-scale image s…
THE INFLUENCE OF CHROMATIC ABERRATION ON DEMOSAICKING
2014
International audience; The wide deployment of colour imaging devices owes much to the use of colour filter array (CFA). A CFA produces a mosaic image, and normally a subsequent CFA demosaick-ing algorithm interpolates the mosaic image and estimates the full-resolution colour image. Among various types of optical aberrations from which a mosaic image may suffer, chromatic aberration (CA) influences the spatial and spectral correlation through the artefacts such as blur and mis-registration, which demosaicking also relies on. In this paper we propose a simulation framework aimed at an investigation of the influence of CA on demosaicking. Results show that CA benefits de-mosaicking to some ex…
Tighter Relations between Sensitivity and Other Complexity Measures
2014
The sensitivity conjecture of Nisan and Szegedy [12] asks whether the maximum sensitivity of a Boolean function is polynomially related to the other major complexity measures of Boolean functions. Despite major advances in analysis of Boolean functions in the past decade, the problem remains wide open with no positive result toward the conjecture since the work of Kenyon and Kutin from 2004 [11].
Lower and Upper Probability Bounds for Some Conjunctions of Two Conditional Events
2018
In this paper we consider, in the framework of coherence, four different definitions of conjunction among conditional events. In each of these definitions the conjunction is still a conditional event. We first recall the different definitions of conjunction; then, given a coherent probability assessment (x, y) on a family of two conditional events \(\{A|H,B|K\}\), for each conjunction \((A|H) \wedge (B|K)\) we determine the (best) lower and upper bounds for the extension \(z=P[(A|H) \wedge (B|K)]\). We show that, in general, these lower and upper bounds differ from the classical Frechet-Hoeffding bounds. Moreover, we recall a notion of conjunction studied in recent papers, such that the res…
Towards artificial intelligence : advances, challenges, and risks
2019
This text contains some reflections on artificial intelligence (AI). First, I differentiate between strong and weak AI, as well as the concepts related to general and specific AI. Following this, I briefly describe the main current AI models and discuss the need to provide common-sense knowledge to machines in order to advance towards the goal of a general AI. Next, I talk about the current trends in AI based on the analysis of large amounts of data, which has recently allowed experts to make spectacular progress. Finally, I discuss other topics which, now and in the future, will continue to be key in AI, before closing with a brief reflection on the risks of AI.