Searcharxiv⌕ Search

arXiv subjects

Fariborz Taherkhani

Publications and source records attributed to Fariborz Taherkhani.

26 records · Page 2Linked to original sources
arXiv2018

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound

Unsupervised image-to-image translation is a class of computer vision problems which aims at modeling conditional distribution of images in the target domain, given a set of unpaired images in the source and target domains. An image in the source domain might have multiple representations in the target domain. Therefore, ambiguity in modeling of the conditional distribution arises, specially when the images in the source and target domains come from different modalities. Current approaches mostly rely on simplifying assumptions to map both domains into a shared-latent space. Consequently, they are only able to model the domain-invariant information between the two modalities. These approaches usually fail to model domain-specific information which has no representation in the target domain. In this work, we propose an unsupervised image-to-image translation framework which maximizes a domain-specific variational information bound and learns the target domain-invariant representation of the two domain. The proposed framework makes it possible to map a single source image into multiple images in the target domain, utilizing several target domain-specific codes sampled randomly from the prior distribution, or extracted from reference images.

cs.CV↗
arXiv2018

Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis

Face sketch-photo synthesis is a critical application in law enforcement and digital entertainment industry where the goal is to learn the mapping between a face sketch image and its corresponding photo-realistic image. However, the limited number of paired sketch-photo training data usually prevents the current frameworks to learn a robust mapping between the geometry of sketches and their matching photo-realistic images. Consequently, in this work, we present an approach for learning to synthesize a photo-realistic image from a face sketch in an unsupervised fashion. In contrast to current unsupervised image-to-image translation techniques, our framework leverages a novel perceptual discriminator to learn the geometry of human face. Learning facial prior information empowers the network to remove the geometrical artifacts in the face sketch. We demonstrate that a simultaneous optimization of the face photo generator network, employing the proposed perceptual discriminator in combination with a texture-wise discriminator, results in a significant improvement in quality and recognition rate of the synthesized photos. We evaluate the proposed network by conducting extensive experiments on multiple baseline sketch-photo datasets.

cs.CV↗
arXiv2018

A Deep Face Identification Network Enhanced by Facial Attributes Prediction

In this paper, we propose a new deep framework which predicts facial attributes and leverage it as a soft modality to improve face identification performance. Our model is an end to end framework which consists of a convolutional neural network (CNN) whose output is fanned out into two separate branches; the first branch predicts facial attributes while the second branch identifies face images. Contrary to the existing multi-task methods which only use a shared CNN feature space to train these two tasks jointly, we fuse the predicted attributes with the features from the face modality in order to improve the face identification performance. Experimental results show that our model brings benefits to both face identification as well as facial attribute prediction performance, especially in the case of identity facial attributes such as gender prediction. We tested our model on two standard datasets annotated by identities and face attributes. Experimental results indicate that the proposed model outperforms most of the current existing face identification and attribute prediction methods.

cs.CV↗
arXiv2017

Permutation, Multiscale and Modified Multiscale Entropies a Natural Complexity for Low-High Infection Level Intracellular Viral Reaction Kinetics

Viral infectious diseases, such as HIV virus growth, cause an important health concern. Study of intracellular viral processes can provide us to develop drug and understanding the drug dose to decrease the HIV virus in during growth. Kinetics Monte Carlo simulation has been done for solving Master equation about dynamics of intracellular viral reaction kinetics. Scaling relationship between equilibrium time and initial population of template has been found as power low, , where N , are the number of initial population of template species , equilibrium time, a = 163.1 , b = -0.1429 respectively. Stochastic dynamics shows that increasing initial population of template decreases the time of equilibrium. Entropy generation has been considered in low, intermediate and high infection level of intracellular viral kinetics reaction in during dynamical process. Permutation, multi scaling and modified multiscaling entropies have been calculated for three kinds of species in intracellular reaction dynamics, genome, structural protein, and template. Our result shows that presence of noise in dynamical process of intracellular reaction will change order of permutation entropy for the mentioned of three species. In addition to multiscaling entropy is computed for mentioned model and it has the following order: template > structural protein> genome. Dependency of permutation entropy result to permutation order becomes small in high infection level in intracellular viral kinetics dynamics. At short time scale in intracellular reaction dynamics, convergency of permutation entropy occurs with medium permutation order value. In the big time scale of intracellular dynamics, permutation entropy scale with permutation order n as a scaling relation .

q-bio.OT↗
arXiv2017

Restoring highly corrupted images by impulse noise using radial basis functions interpolation

Preserving details in restoring images highly corrupted by impulse noise remains a challenging problem. We proposed an algorithm based on radial basis functions (RBF) interpolation which estimates the intensities of corrupted pixels by their neighbors. In this algorithm, first intensity values of noisy pixels in the corrupted image are estimated using RBFs. Next, the image is smoothed. The proposed algorithm can effectively remove the highly dense impulse noise. Experimental results show the superiority of the proposed algorithm in comparison to the recent similar methods both in noise suppression and detail preservation. Extensive simulations show better results in measure of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), especially when the image is corrupted by very highly dense impulse noise.

cs.MM↗
arXiv2016

An ensemble learning method for scene classification based on Hidden Markov Model image representation

Low level images representation in feature space performs poorly for classification with high accuracy since this level of representation is not able to project images into the discriminative feature space. In this work, we propose an efficient image representation model for classification. First we apply Hidden Markov Model (HMM) on ordered grids represented by different type of image descriptors in order to include causality of local properties existing in image for feature extraction and then we train up a separate classifier for each of these features sets. Finally we ensemble these classifiers efficiently in a way that they can cancel out each other errors for obtaining higher accuracy. This method is evaluated on 15 natural scene dataset. Experimental results show the superiority of the proposed method in comparison to some current existing methods

cs.CV↗
arXiv2016

A probabilistic patch based image representation using Conditional Random Field model for image classification

In this paper we proposed an ordered patch based method using Conditional Random Field (CRF) in order to encode local properties and their spatial relationship in images to address texture classification, face recognition, and scene classification problems. Typical image classification approaches work without considering spatial causality among distinctive properties of an image for image representation in feature space. In this method first, each image is encoded as a sequence of ordered patches, including local properties. Second, the sequence of these ordered patches is modeled as a probabilistic feature vector by CRF to model spatial relationship of these local properties. And finally, image classification is performed on such probabilistic image representation. Experimental results on several standard image datasets indicate that proposed method outperforms some of existing image classification methods.

cs.CV↗