با سلام خدمت کاربران عزیز، به اطلاع می رساند ترجمه مقالاتی که سال انتشار آن ها زیر 2008 می باشد رایگان بوده و میتوانید با وارد شدن در صفحه جزییات مقاله به رایگان ترجمه را دانلود نمایید.
Synaptic Specificity, Recognition Molecules, and Assembly of Neural Circuits
ویژگی سیناپسی ، مولکولهای تشخیص و مونتاژ مدارهای عصبی-2020
Developing neurons connect in specific and stereotyped ways to form the complex circuits that underlie brain function. By comparison to earlier steps in neural development, progress has been slow in identifying the cell surface recognition molecules that mediate these synaptic choices, but new high-throughput imaging, genetic, and molecular methods are accelerating progress. Over the past decade, numerous large and small gene families have been implicated in target recognition, including members of the immunoglobulin, cadherin, and leucine-rich repeat superfamilies. We review these advances and propose ways in which combinatorial use of multifunctional recognition molecules enables the complex neuron-neuron interactions that underlie synaptic specificity.
کمترین از دست دادن حاشیه برای تشخیص چهره عمیق
سال انتشار: 2020 - تعداد صفحات فایل pdf انگلیسی: 9 - تعداد صفحات فایل doc فارسی: 24
تشخیص چهره موفقیت بزرگی به دست آورده است که دلیل اصلی آن توسعه سریع شبکه های عصبی عمیق (DNN) در سال های اخیر است. کارکردهای مختلف ازدست دادن (اتلاف) در یک شبکه عصبی عمیق قابل استفاده است که منجر به عملکرد متفاوتی می شود. اخیراً برخی از کارکردهای تلفات پیشنهاد داده شده است. با این حال، آن ها نمی توانند مساله جهت گیری حاشیه ای را که در مجموعه داده های غیر متعادل وجود دارد حل کنند. در این مقاله حل مساله تمایل حاشیه ای را با تعیین یک حاشیه حداقلی برای تمامی زوج کلاس ها پیشنهاد می دهیم. ما تابع اتلاف جدیدی به نام حداقل اتلاف حاشیه ای (MML) پیشنهاد می دهیم که هدف آن گسترش محدوده آن هایی است که به زوج های مرکزی دسته بیش از حد نزدیک می شوند تا قابلیت متمایز کننده ویژگی های عمیق را ارتقاء دهد. تابع MML همراه با توابع Softmax Loss و Centre Loss بر فرآیند آموزش نظارت می کنند تا حاشیه های تمامی دسته ها را صرف نظر از توزیع دسته آن ها مورد نظارت قرار دهند. ما تابع MML را در پلتفورم Inception-ResNet-v1 پیاده سازی می کنیم و آزمایش های گسترده ای را بر روی هفت مجموعه داده تشخیص چهره انجام می دهیم که شامل MegaFace، FaceScrub، LFW، SLLFW، YTF، IJB-B و IJB-C است. نتایج تجربی نشان می دهد که تابع از دست دادن MML پیشنهادی منجر به حالت جدیدی در تشخیص چهره می شود و اثر منفی جهت گیری حاشیه ای را کاهش می دهد.
کلید واژه ها :یادگیری عمیق | شبکه های عصبی باز رخدادگر (CNN) | تشخیص چهره| کمترین از دست دادن حاشیه ای (MML)
|مقاله ترجمه شده|
Discriminant Deep Feature Learning based on joint supervision Loss and Multi-layer Feature Fusion for heterogeneous face recognition
Discriminant Deep Feature Learning based on joint supervision Loss and Multi-layer Feature Fusion for heterogeneous face recognition-2019
Heterogeneous face recognition (HFR) is still a challenging problem in computer vision community due to large appearance difference between near infrared (NIR) and visible light (VIS) modalities. Recently, breakthroughs have been made for traditional face recognition by applying deep learning on a huge amount of labeled VIS face samples. However, the same deep learning approach cannot be simply applied to HFR task due to large domain difference as well as insufficient pairwise images in different modalities during training. In general, the pooling layer of deep network can play the role of feature reduction, but also lead to the loss of useful face information, resulting in a decrease in the performance of HFR problem. It is important to eliminate modal-related information and retain more facial identity information. In this paper, we propose a novel method called Discriminant Deep Feature Learning Based on Joint Supervision Loss and Multi-layer Feature Fusion (DDFLJM) for HFR task. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new loss function called Scatter Loss (SL), which embeds both interand intra-class information for effectively training the deep model. To make full use of the various layers of the deep network, a Dimension Reduction Block (DRB) is designed to effectively extract the auxiliary features on multiple mid-level layers. An orthogonality constraint is introduced to the DRB block to reduce spectrum variations of two different modalities. The proposed SL is applied to multiple layers of network for joint supervision training, which enables multiple layers of the network to obtain discriminative identity features. Moreover, a Modified Gate Two-stream Neural Network (MGTNN) is adopted to fuse multiple-layer features. Extensive experiments are carried out on two challenging NIR-VIS HFR datasets CASIA NIR-VIS 2.0 and Oulu-CASIA NIR-VIS, demonstrating the superiority of the proposed method.
Keywords: Heterogeneous face recognition | Deep learning | Joint supervision loss | Feature fusion
A survey on deep learning based face recognition
مروری بر شناخت چهره مبتنی بر یادگیری عمیق-2019
Deep learning, in particular the deep convolutional neural networks, has received increasing interests in face recognition recently, and a number of deep learning methods have been proposed. This paper summarizes about 330 contributions in this area. It reviews major deep learning concepts pertinent to face image analysis and face recognition, and provides a concise overview of studies on specific face recognition problems, such as handling variations in pose, age, illumination, expression, and heterogeneous face matching. A summary of databases used for deep face recognition is given as well. Finally, some open challenges and directions are discussed for future research.
Keywords: Deep learning | Face recognition | Artificial Neural Network | Convolutional Neural Networks | Autoencoder | Generative Adversarial Networks
Local polynomial contrast binary patterns for face recognition
الگوهای باینری کنتراست چند جمله ای محلی برای تشخیص چهره-2019
We propose a novel face representation model, called the polynomial contrast binary patterns (PCBP), based on the polynomial filters, for robust face recognition. It is assumed that the discrete array of pixel values comes about by sampling an underlying smooth surface in an image. The proposed method effi- ciently estimates the underlying local surface information, which is approximately represented as linear projection coefficients of the pixels in a local patch. The decomposition using polynomial filters can cap- ture rich image information at multiple orientations and frequency bands. This guarantees its robustness to illumination and expression variations. The weighting scheme embeds different discriminative pow- ers of each filter response image. We also propose to carry out a subsequent Fisher linear Discriminant (FLD) on each decomposed image for dimension reduction of features. Our extensive experiments on the public FERET and LFW databases demonstrate that the non-weighted Polynomial contrast binary patterns performs better than most of methods and the weighting scheme further improves the recognition rates. WPCBP + FLD(CD) and WPCBP + FLD(HI) can achieve much competitive or even better recognition perfor- mance compared with the state-of-the-art face recognition methods.
Keywords: Face recognition | Polynomial filters | Local binary patterns | Surface fitting
The affective facial recognition task: The influence of cognitive styles and exposure times
وظیفه شناختی چهره عاطفی: تأثیر سبک های شناختی و زمان مواجهه با آنها-2019
The main task of emotional facial recognition is to understand human emotion expression through the recognition of facial expressions, so as to achieve more effective communication and interpersonal communication. Therefore, facial recognition plays an important role in people’s daily lives. In addition, the research of facial recognition is also helpful to understand the human perception processing mode, and promote the development of pattern recognition, cognitive science, neural network and other fields. With the development of cognitive science, facial recognition technology has been continuously improved, and emotional facial recognition tasks have received attention in the fields of pattern recognition and artificial intelligence, and have become a research hotspot. Among them, pattern recognition is a cognitive system applied to many fields. For the first time, we confirmed the effects of facial memory time, personal cognitive style, and emotions associated with the target face on facial recognition patterns. This study measured the impact of time, cognitive style, and emotional type of 62 qualified college students. The research results show that cognitive style and facial emotional content are of great significance for face pattern recognition. Specifically, students classified as ‘‘dependent” have achieved good results in face pattern recognition, and positive and negative strong emotional faces have left behind those who show neutral emotions. A deeper impression. Finally, an unusual phenomenon was discovered, which indicates that the shorter the time spent on the face of the memory, the higher the recognition score.
Keywords: Face recognition | Pattern recognition | Cognitive style | Face emotion
Sparse deep feature learning for facial expression recognition
یادگیری ویژگی های عمیق پراکنده برای تشخیص چهره صورت-2019
While weight sparseness-based regularization has been used to learn better deep features for image recognition problems, it introduced a large number of variables for optimization and can easily con- verge to a local optimum. The L2-norm regularization proposed for face recognition reduces the impact of the noisy information, while expression information is also suppressed during the regularization. A feature sparseness-based regularization that learns deep features with better generalization capability is proposed in this paper. The regularization is integrated into the loss function and optimized with a deep metric learning framework. Through a toy example, it is showed that a simple network with the proposed sparseness outperforms the one with the L2-norm regularization. Furthermore, the proposed approach achieved competitive performances on four publicly available datasets, i.e., FER2013, CK + , Oulu-CASIA and MMI. The state-of-the-art cross-database performances also justify the generalization capability of the proposed approach.
Keywords: Expression recognition | Feature sparseness | Deep metric learning | Fine tuning | Generalization capability
Nanoscale measurement with pattern recognition of an ultra-precision diamond machined polar microstructure
اندازه گیری نانو با تشخیص الگوی ریزساختار قطبی ماشینکاری شده با الماس بسیار دقیق-2019
Due to the low resolution of pattern recognition and disorganized textures of the surfaces of most natural objects observed under a microscope, computer vision technology has not been widely applied in precision positioning measurement on machine tools, which needs high resolution and accuracy. This paper presents a systematic method to solve the surface recognition problem which makes use of ultra-precision diamond machining to produce a functional and polar-coordinate surface named ‘polar microstructure’. The unique characteristic of a polar microstructure is the distinctive pattern of any locations including rotation in the global surface which provides the feasibility of achieving precise absolute positions by matching the patterns by utilizing computer vision technology. A polar microstructure which possesses orientation characteristics is also able to measure the displacement of rotation angle. A series of simulation experiments including feature point extraction, orientation detection as well as resolution of pattern recognition was conducted, and the results show that a polar microstructure can achieve a resolution of 9.35 nm which is capable of providing a novel computer vision-based nanometric precision measurement method which can be applied in positioning on machine tools in the future.
Keywords: Polar microstructure | Computer vision | Ultra-precision machining | Nanoscale measurement | Pattern recognition
Simultaneous learning of reduced prototypes and local metric for image set classification
یادگیری همزمان از نمونه های اولیه کاهش یافته و متریک محلی برای طبقه بندی مجموعه تصویر-2019
Classification based on image set is recently a competitive technique, where each set contains multiple images of a person or an object. As a widely used model, affine hull has shown its power in modeling image set. However, due to the existence of noise and outliers, the over-large affine hull usually matches fails when two hulls overlapped. Aiming at alleviating this handicap, this paper proposes a novel method for image set classification, namely Learning of Reduced Prototypes and Local Metric (LRPLM). Specifi- cally, for each gallery image set, a reduced set of prototypes and an optimal local feature-wise metric are simultaneously learned, which jointly minimize the loss function involved the estimation of classifi- cation error probability. In doing so, LRPLM inherits the merits of affine hull with better representation to account for the unseen appearances and makes use of the powerful discriminative ability improved by the local metric. It looks like that LRPLM pulls similar image sets with the same class label “closer”to each other, while pushing dissimilar ones “far away”. Extensive experiments illustrate the considerable effectiveness of LRPLM on three widely used datasets. As we know, classification is a research hotspot in expert and intelligent systems. Different from the previous classification methods, LRPLM focuses on im- age set-based classification technology, while most of them are single-shot classification technology. Thus, the proposed method can be considered as an expert system technology for medical diagnosis, security monitoring, object categorization, and biometrics recognition applications.
Keywords: Image set classification | Prototype learning | Metric learning | Face recognition | Expert system
Dependence structure of Gabor wavelets based on copula for face recognition
ساختار وابستگی Gabor wavelets بر اساس کوپول برای تشخیص چهره-2019
Low resolution, difficult illumination and noise are the important factors that affect the performance of face recognition system. In order to counteract these adverse factors, in this paper we propose copula probability models based on Gabor wavelets for face recognition. Gabor wavelets have robust performance under lighting and noise conditions. The strong dependencies exist in the domain of Gabor wavelets due to their non-orthogonal property. In the light of the structure characteristic of Gabor wavelet sub- bands, the proposed methods use copula to capture the dependencies to represent the face image. Three probability-model-based methods CF-GW (Copula Function of Gabor Wavelets), LCM-GW (Lightweight Copula Model of Gabor Wavelets) and LCM-GW-PSO (Lightweight Copula Model of Gabor Wavelets with Particle Swarm Optimization) are proposed for face recognition. Experiments of face recognition show our proposed methods are more robust under the conditions of low resolution, lighting and noise than the popular methods such as the LBP-based methods and other Gabor-based methods. The face features extracted by our methods belong to the Riemannian manifold which is different to Euclidean space. In order to deal the issue of face recognition in complex environment, we can combine the face features in Riemannian manifold with the face features in Euclidean space to obtain the more robust face recognition system by using expert system technologies such as reasoning model and multi-classifier fusion.
Keywords: Face recognition | Gabor wavelets | Gaussian copula | Covariance matrix | Particle swarm optimization