429 Hits in 1.5 sec

Quality Guided Sketch-to-Photo Image Synthesis [article]

Uche Osahor, Hadi Kazemi, Ali Dabouei, Nasser Nasrabadi
2020 arXiv   pre-print
Facial sketches drawn by artists are widely used for visual identification applications and mostly by law enforcement agencies, but the quality of these sketches depend on the ability of the artist to clearly replicate all the key facial features that could aid in capturing the true identity of a subject. Recent works have attempted to synthesize these sketches into plausible visual images to improve visual recognition and identification. However, synthesizing photo-realistic images from
more » ... s proves to be an even more challenging task, especially for sensitive applications such as suspect identification. In this work, we propose a novel approach that adopts a generative adversarial network that synthesizes a single sketch into multiple synthetic images with unique attributes like hair color, sex, etc. We incorporate a hybrid discriminator which performs attribute classification of multiple target attributes, a quality guided encoder that minimizes the perceptual dissimilarity of the latent space embedding of the synthesized and real image at different layers in the network and an identity preserving network that maintains the identity of the synthesised image throughout the training process. Our approach is aimed at improving the visual appeal of the synthesised images while incorporating multiple attribute assignment to the generator without compromising the identity of the synthesised image. We synthesised sketches using XDOG filter for the CelebA, WVU Multi-modal and CelebA-HQ datasets and from an auxiliary generator trained on sketches from CUHK, IIT-D and FERET datasets. Our results are impressive compared to current state of the art.
arXiv:2005.02133v1 fatcat:nmwjpfolafcnjkwuqks2jllmwi

Style and Content Disentanglement in Generative Adversarial Networks [article]

Hadi Kazemi, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
2018 arXiv   pre-print
Disentangling factors of variation within data has become a very challenging problem for image generation tasks. Current frameworks for training a Generative Adversarial Network (GAN), learn to disentangle the representations of the data in an unsupervised fashion and capture the most significant factors of the data variations. However, these approaches ignore the principle of content and style disentanglement in image generation, which means their learned latent code may alter the content and
more » ... tyle of the generated images at the same time. This paper describes the Style and Content Disentangled GAN (SC-GAN), a new unsupervised algorithm for training GANs that learns disentangled style and content representations of the data. We assume that the representation of an image can be decomposed into a content code that represents the geometrical information of the data, and a style code that captures textural properties. Consequently, by fixing the style portion of the latent representation, we can generate diverse images in a particular style. Reversely, we can set the content code and generate a specific scene in a variety of styles. The proposed SC-GAN has two components: a content code which is the input to the generator, and a style code which modifies the scene style through modification of the Adaptive Instance Normalization (AdaIN) layers' parameters. We evaluate the proposed SC-GAN framework on a set of baseline datasets.
arXiv:1811.05621v1 fatcat:7be3u3agxzftxkmkp6uiyy7k3y

Identity-Aware Deep Face Hallucination via Adversarial Face Verification [article]

Hadi Kazemi, Fariborz Taherkhani, Nasser M. Nasrabadi
2019 arXiv   pre-print
In this paper, we address the problem of face hallucination by proposing a novel multi-scale generative adversarial network (GAN) architecture optimized for face verification. First, we propose a multi-scale generator architecture for face hallucination with a high up-scaling ratio factor, which has multiple intermediate outputs at different resolutions. The intermediate outputs have the growing goal of synthesizing small to large images. Second, we incorporate a face verifier with the original
more » ... GAN discriminator and propose a novel discriminator which learns to discriminate different identities while distinguishing fake generated HR face images from their ground truth images. In particular, the learned generator cares for not only the visual quality of hallucinated face images but also preserving the discriminative features in the hallucination process. In addition, to capture perceptually relevant differences we employ a perceptual similarity loss, instead of similarity in pixel space. We perform a quantitative and qualitative evaluation of our framework on the LFW and CelebA datasets. The experimental results show the advantages of our proposed method against the state-of-the-art methods on the 8x downsampled testing dataset.
arXiv:1909.08130v1 fatcat:k4xkuinqj5g4zd4s5huplebfyy

Unsupervised Facial Geometry Learning for Sketch to Photo Synthesis [article]

Hadi Kazemi, Fariborz Taherkhani, Nasser M. Nasrabadi
2018 arXiv   pre-print
Hadi Kazemi et al. Hadi Kazemi et al. Hadi Kazemi et al.  ...  Kazemi et al.  ... 
arXiv:1810.05361v1 fatcat:4ljmmk4jo5cttjdis66hvqfcfm

Deep Cross Polarimetric Thermal-to-visible Face Recognition [article]

Seyed Mehdi Iranmanesh, Ali Dabouei, Hadi Kazemi, Nasser M. Nasrabadi
2018 arXiv   pre-print
In this paper, we present a deep coupled learning frame- work to address the problem of matching polarimetric ther- mal face photos against a gallery of visible faces. Polariza- tion state information of thermal faces provides the miss- ing textural and geometrics details in the thermal face im- agery which exist in visible spectrum. we propose a coupled deep neural network architecture which leverages relatively large visible and thermal datasets to overcome the problem of overfitting and
more » ... ually we train it by a polarimetric thermal face dataset which is the first of its kind. The pro- posed architecture is able to make full use of the polari- metric thermal information to train a deep model compared to the conventional shallow thermal-to-visible face recogni- tion methods. Proposed coupled deep neural network also finds global discriminative features in a nonlinear embed- ding space to relate the polarimetric thermal faces to their corresponding visible faces. The results show the superior- ity of our method compared to the state-of-the-art models in cross thermal-to-visible face recognition algorithms.
arXiv:1801.01486v1 fatcat:wc2wyc3kw5fnnlxidtrvgiy76i

Fingerprint Distortion Rectification using Deep Convolutional Neural Networks [article]

Ali Dabouei, Hadi Kazemi, Seyed Mehdi Iranmanesh, Jeremi Dawson, Nasser M. Nasrabadi
2018 arXiv   pre-print
Elastic distortion of fingerprints has a negative effect on the performance of fingerprint recognition systems. This negative effect brings inconvenience to users in authentication applications. However, in the negative recognition scenario where users may intentionally distort their fingerprints, this can be a serious problem since distortion will prevent recognition system from identifying malicious users. Current methods aimed at addressing this problem still have limitations. They are often
more » ... not accurate because they estimate distortion parameters based on the ridge frequency map and orientation map of input samples, which are not reliable due to distortion. Secondly, they are not efficient and requiring significant computation time to rectify samples. In this paper, we develop a rectification model based on a Deep Convolutional Neural Network (DCNN) to accurately estimate distortion parameters from the input image. Using a comprehensive database of synthetic distorted samples, the DCNN learns to accurately estimate distortion bases ten times faster than the dictionary search methods used in the previous approaches. Evaluating the proposed method on public databases of distorted samples shows that it can significantly improve the matching performance of distorted samples.
arXiv:1801.01198v1 fatcat:vushxzimrje37er6ybphpkjy3a

A data-driven proxy to Stoke's flow in porous media [article]

Ali Takbiri-Borujeni and Hadi Kazemi and Nasser Nasrabadi
2019 arXiv   pre-print
The objective for this work is to develop a data-driven proxy to high-fidelity numerical flow simulations using digital images. The proposed model can capture the flow field and permeability in a large verity of digital porous media based on solid grain geometry and pore size distribution by detailed analyses of the local pore geometry and the local flow fields. To develop the model, the detailed pore space geometry and simulation runs data from 3500 two-dimensional high-fidelity Lattice
more » ... nn simulation runs are used to train and to predict the solutions with a high accuracy in much less computational time. The proposed methodology harness the enormous amount of generated data from high-fidelity flow simulations to decode the often under-utilized patterns in simulations and to accurately predict solutions to new cases. The developed model can truly capture the physics of the problem and enhance prediction capabilities of the simulations at a much lower cost. These predictive models, in essence, do not spatio-temporally reduce the order of the problem. They, however, possess the same numerical resolutions as their Lattice Boltzmann simulations equivalents do with the great advantage that their solutions can be achieved by significant reduction in computational costs (speed and memory).
arXiv:1905.06327v1 fatcat:lls72jxa4zbm5d4f7bdzu6wzee

Deep Sketch-Photo Face Recognition Assisted by Facial Attributes [article]

Seyed Mehdi Iranmanesh, Hadi Kazemi, Sobhan Soleymani, Ali Dabouei, Nasser M. Nasrabadi
2018 arXiv   pre-print
In this paper, we present a deep coupled framework to address the problem of matching sketch image against a gallery of mugshots. Face sketches have the essential in- formation about the spatial topology and geometric details of faces while missing some important facial attributes such as ethnicity, hair, eye, and skin color. We propose a cou- pled deep neural network architecture which utilizes facial attributes in order to improve the sketch-photo recognition performance. The proposed
more » ... e-Assisted Deep Con- volutional Neural Network (AADCNN) method exploits the facial attributes and leverages the loss functions from the facial attributes identification and face verification tasks in order to learn rich discriminative features in a common em- bedding subspace. The facial attribute identification task increases the inter-personal variations by pushing apart the embedded features extracted from individuals with differ- ent facial attributes, while the verification task reduces the intra-personal variations by pulling together all the fea- tures that are related to one person. The learned discrim- inative features can be well generalized to new identities not seen in the training data. The proposed architecture is able to make full use of the sketch and complementary fa- cial attribute information to train a deep model compared to the conventional sketch-photo recognition methods. Exten- sive experiments are performed on composite (E-PRIP) and semi-forensic (IIIT-D semi-forensic) datasets. The results show the superiority of our method compared to the state- of-the-art models in sketch-photo recognition algorithms
arXiv:1808.00059v1 fatcat:aacadvlctbfrpkttkj2lgvt6qi

Overview of Agents Used for Emergency Hemostasis

Hadi Khoshmohabat, Shahram Paydar, Hossein Mohammad Kazemi, Behnam Dalfardi
2016 Trauma Monthly  
FootnoteAuthors' Contribution:Study concept and design: Hadi Khoshmohabat , Shahram Paydar, Hossein Mohammad Kazemi, and Behnam Dalfardi; drafting of the manuscript: Hossein Mohammad Kazemi and Behnam  ...  Kazemi, and Behnam Dalfardi.  ... 
doi:10.5812/traumamon.26023 pmid:27218055 pmcid:PMC4869418 fatcat:p6zf3vuo7be3dbpom2arectdmy

The Role of Dopamine Receptors during Brain Development

Sajad Sahab Negah, Zabihollah Khaksar, Hadi Kazemi, Hadi Aligholi, Maryam Safahani, Mostafa Modarres Mousavi, Shahin Mohammad Sadeghi
2014 The Neuroscience Journal of Shefaye Khatam  
doi:10.18869/acadpub.shefa.2.3.65 fatcat:27xuz2awxbfexjemm7q4l72czy

Robust Facial Landmark Detection via Aggregation on Geometrically Manipulated Faces [article]

Seyed Mehdi Iranmanesh, Ali Dabouei, Sobhan Soleymani, Hadi Kazemi, Nasser M. Nasrabadi
2020 arXiv   pre-print
In this work, we present a practical approach to the problem of facial landmark detection. The proposed method can deal with large shape and appearance variations under the rich shape deformation. To handle the shape variations we equip our method with the aggregation of manipulated face images. The proposed framework generates different manipulated faces using only one given face image. The approach utilizes the fact that small but carefully crafted geometric manipulation in the input domain
more » ... n fool deep face recognition models. We propose three different approaches to generate manipulated faces in which two of them perform the manipulations via adversarial attacks and the other one uses known transformations. Aggregating the manipulated faces provides a more robust landmark detection approach which is able to capture more important deformations and variations of the face shapes. Our approach is demonstrated its superiority compared to the state-of-the-art method on benchmark datasets AFLW, 300-W, and COFW.
arXiv:2001.03113v1 fatcat:dqbbzyof35bl7j5tvk2r224sm4

Attribute-Centered Loss for Soft-Biometrics Guided Face Sketch-Photo Recognition [article]

Hadi Kazemi, Sobhan Soleymani, Ali Dabouei, Mehdi Iranmanesh, Nasser M. Nasrabadi
2018 arXiv   pre-print
Face sketches are able to capture the spatial topology of a face while lacking some facial attributes such as race, skin, or hair color. Existing sketch-photo recognition approaches have mostly ignored the importance of facial attributes. In this paper, we propose a new loss function, called attribute-centered loss, to train a Deep Coupled Convolutional Neural Network (DCCNN) for the facial attribute guided sketch to photo matching. Specifically, an attribute-centered loss is proposed which
more » ... ns several distinct centers, in a shared embedding space, for photos and sketches with different combinations of attributes. The DCCNN simultaneously is trained to map photos and pairs of testified attributes and corresponding forensic sketches around their associated centers, while preserving the spatial topology information. Importantly, the centers learn to keep a relative distance from each other, related to their number of contradictory attributes. Extensive experiments are performed on composite (E-PRIP) and semi-forensic (IIIT-D Semi-forensic) databases. The proposed method significantly outperforms the state-of-the-art.
arXiv:1804.03082v1 fatcat:kn7z4mvajbe73l5rneq2f5y5oi

Familial hemiplegic migraine and spreading depression

Hadi Kazemi, Erwin-Josef Speckmann, Ali Gorji
2014 Iranian journal of child neurology  
Familial hemiplegic migraine (FHM) is an autosomal dominantly inherited subtype of migraine with aura, characterized by transient neurological signs and symptoms. Typical hemiplegic migraine attacks start in the first or second decade of life. Some patients with FHM suffer from daily recurrent attacks since childhood. Results from extensive studies of cellular and animal models have indicated that gene mutations in FHM increase neuronal excitability and reduce the threshold for spreading
more » ... ion (SD). SD is a transient wave of profound neuronal and glial depolarization that slowly propagates throughout the brain tissue and is characterized by a high amplitude negative DC shift. After induction of SD, S218L mutant mice exhibited neurological signs highly reminiscent of clinical attacks in FHM type 1 patients carrying this mutation. FHM1 with ataxia is attributable to specific mutations that differ from mutations that cause pure FHM1 and have peculiar consequences on cerebellar Cav2.1 currents that lead to profound Purkinje cell dysfunction and neuronal loss with atrophy. SD in juvenile rats produced neuronal injury and death. Hormonal factors involved in FHM affect SD initiation and propagation. The data identify SD as a possible target of treatment of FHM. In addition, FHM is a useful model to explore the mechanisms of more common types of migraine.
pmid:25143767 pmcid:PMC4135274 fatcat:l4yjvtahkzdnxfolt7ig5f655y

Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound [article]

Hadi Kazemi, Sobhan Soleymani, Fariborz Taherkhani, Seyed Mehdi Iranmanesh, Nasser M. Nasrabadi
2018 arXiv   pre-print
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
more » ... y 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.
arXiv:1811.11979v1 fatcat:je437prgjfb2ropj5eludjgjnq

ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction [article]

Ali Dabouei, Sobhan Soleymani, Hadi Kazemi, Seyed Mehdi Iranmanesh, Jeremy Dawson, Nasser M. Nasrabadi
2018 arXiv   pre-print
Performing recognition tasks using latent fingerprint samples is often challenging for automated identification systems due to poor quality, distortion, and partially missing information from the input samples. We propose a direct latent fingerprint reconstruction model based on conditional generative adversarial networks (cGANs). Two modifications are applied to the cGAN to adapt it for the task of latent fingerprint reconstruction. First, the model is forced to generate three additional maps
more » ... o the ridge map to ensure that the orientation and frequency information is considered in the generation process, and prevent the model from filling large missing areas and generating erroneous minutiae. Second, a perceptual ID preservation approach is developed to force the generator to preserve the ID information during the reconstruction process. Using a synthetically generated database of latent fingerprints, the deep network learns to predict missing information from the input latent samples. We evaluate the proposed method in combination with two different fingerprint matching algorithms on several publicly available latent fingerprint datasets. We achieved the rank-10 accuracy of 88.02\% on the IIIT-Delhi latent fingerprint database for the task of latent-to-latent matching and rank-50 accuracy of 70.89\% on the IIIT-Delhi MOLF database for the task of latent-to-sensor matching. Experimental results of matching reconstructed samples in both latent-to-sensor and latent-to-latent frameworks indicate that the proposed method significantly increases the matching accuracy of the fingerprint recognition systems for the latent samples.
arXiv:1808.00035v1 fatcat:unvcdjgkvnezpgh6zmik22l25q
« Previous Showing results 1 — 15 out of 429 results