Search results for " processing"
showing 10 items of 7549 documents
Combination Of Handcrafted And Deep Learning-Based Features For 3d Mesh Quality Assessment
2020
We propose in this paper a novel objective method to evaluate the perceived visual quality of 3D meshes. The proposed method in no-reference, it relies only on the distorted mesh for the quality estimation. It is based on a pre-trained convolutional neural network (i.e VGG to extract features from the distorted mesh) and handcrafted features extracted directly from the 3D mesh (i.e curvature and dihedral angle). A General Regression Neural Network (GRNN) is used to learn the statistical parameters of the feature vectors and estimate the quality score. Experimental results from for subjective databases (LIRIS masking, LIRIS/EPFL generalpurpose, UWB compression and LEETA simplification) and c…
No-reference mesh visual quality assessment via ensemble of convolutional neural networks and compact multi-linear pooling
2020
Abstract Blind or No reference quality evaluation is a challenging issue since it is done without access to the original content. In this work, we propose a method based on deep learning for the mesh visual quality assessment without reference. For a given 3D model, we first compute its mesh saliency. Then, we extract views from the 3D mesh and the corresponding mesh saliency. After that, the views are split into small patches that are filtered using a saliency threshold. Only the salient patches are selected and used as input data. After that, three pre-trained deep convolutional neural networks are employed for feature learning: VGG, AlexNet, and ResNet. Each network is fine-tuned and pro…
Design Space Exploration for a Custom VLIW Architecture: Direct Photo Printer Hardware Setting Using VEX Compiler
2008
Increasingly more computing power is demanded for contemporary applications such as multimedia, 3D visualization, and telecommunication. This paper presents a design space exploration (DSE) experience for an embedded VLIW processor that allows finding out the best architecture for given application. The proposed method has been implemented and tested using an image processing chain for direct photo printer. Our results show a considerable improvement in hardware cost and performance. After the best architecture is identified, we applied a technique to optimize the code in VEX system that uses ?inlining? function in order to reduce execution time.
Towards General Purpose Object Detection: Deep Dense Grid Based Object Detection
2020
Object detection is one of the most challenging and very important branch of computer vision. Some of the challenging aspect of a detection network is the fact that an object can appear anywhere in the image, be partially occluded by another object, might appear in crowd or have greatly varying scales. Consequently, we propose a fine grained and equally spaced dense grid cells throughout an input image be responsible of detecting an object. We re-purpose an already existing deep state-of-the-art detector or classifier into deep and dense detector. Our dense object detector uses binary class encoding and hence suitable for very large multi-class object detector. We also propose a more flexib…
Affine Illumination Compensation on Hyperspectral/Multiangular Remote Sensing Images
2011
The huge amount of information some of the new optical satellites developed nowadays will create demands to quickly and reliably compensate for changes in the atmospheric transmittance and varying solar illumination conditions. In this paper three different forms of affine transformation models (general, particular and diagonal) are considered as candidates for rapid compensation of illumination variations. They are tested on a group of three pairs of CHRISPROBA radiance images obtained in a test field in Barrax (Spain), and where there is a difference in the atmospheric as well as in the geometrical acquisition conditions. Results indicate that the proposed methodology is satisfactory for …
Deep Learning for Resource-Limited Devices
2020
In recent years, deep neural networks have revolutionized the development of intelligent systems and applications in many areas. Despite their numerous advantages and potentials, these intelligent models still suffer from several issues. Among them, the fact that they became very complex with millions of parameters. That is, requiring more resources and time, and being unsuitable for small restricted devices. To contribute in this direction, this paper presents (1) some state-of-the-art lightweight architectures that were specifically designed for small-sized devices, and (2) some recent solutions that have been proposed to optimize/compress classical deep neural networks to allow their dep…
The Application of Optimal Topic Sequence in Adaptive e-Learning Systems
2016
In an adaptive e-learning system an opportunity to choose a course topic sequence is given to ensure personalization. The topic sequence can be obtained from three sources: teacher-offered topic sequence that is based on teacher’s pedagogical experience; learner’s free choice that is based on indicated links between topics, and, finally, the optimal topic sequence acquisition method described in this article. The optimal topic sequence is based on previous learners’ experience. With the help of the optimal topic sequence method, data about previous learners’ course topic sequence and course results are obtained. After the data analysis the optimal topic sequence for the specific course is o…
Features extraction on complex images
2005
The accessibility of inexpensive and powerful computers has allowed true digital holography to be used for industrial inspection using microscopy. This technique allows the capture of a complex image (i.e., one containing magnitude and phase), and the reconstruction of the phase and magnitude information. Digital holograms give a new dimension to texture analysis, since the topology information can be used as an additional way to extract features. This new technique can be used to extend previous work on the image segmentation of patterned wafers for defect detection. The paper presents a comparison between the features obtained using Gabor filtering on complex images under illumination and…
Improving distance based image retrieval using non-dominated sorting genetic algorithm
2015
Image retrieval is formulated as a multiobjective optimization problem.A multiobjective genetic algorithm is hybridized with distance based search.A parameter balances exploration (genetic search) or exploitation (nearest neighbors).Extensive comparative experimentation illustrate and assess the proposed methodology. Relevance feedback has been adopted as a standard in Content Based Image Retrieval (CBIR). One major difficulty that algorithms have to face is to achieve and adequate balance between the exploitation of already known areas of interest and the exploration of the feature space to find other relevant areas. In this paper, we evaluate different ways to combine two existing relevan…
The Expressibility of Languages and Relations by Word Equations
1997
Classically, several properties and relations of words, such as being a power of a same word, can be expressed by using word equations. This paper is devoted to study in general the expressive power of word equations. As main results we prove theorems which allow us to show that certain properties of words are not expressible as components of solutions of word equations. In particular, the primitiveness and the equal length are such properties, as well as being any word over a proper subalphabet.