检索结果-内蒙古大学图书馆

UDC-UNet: Under-Display Camera Image Restoration via U-shape Dynamic Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Xina Hu, Jinfan Chen, Xiangyu Dong, Chao Shenzhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shanghai China University of Chinese Academy of Sciences Shanghai China University of Macau Shanghai China Shanghai AI Laboratory Shanghai China

Under-Display Camera (UDC) has been widely exploited to help smartphones realize full-screen displays. However, as the screen could inevitably affect the light propagation process, the images captured by the UDC system usually contain flare, haze, blur, and noise. Particularly, flare and blur in UDC images could severely deteriorate the user experience in high dynamic range (HDR) scenes. In this paper, we propose a new deep model, namely UDC-UNet, to address the UDC image restoration problem with an estimated PSF in HDR scenes. Our network consists of three parts, including a U-shape base network to utilize multi-scale information, a condition branch to perform spatially variant modulation, and a kernel branch to leverage the prior knowledge of the PSF. According to the characteristics of HDR data, we additionally design a tone mapping loss to stabilize network optimization and achieve better visual quality. Experimental results show that the proposed UDC-UNet outperforms the state-of-the-art methods in quantitative and qualitative comparisons. Our approach won second place in the UDC image restoration track of the MIPI challenge. Codes and models are available at https://***/J-FHu/UDCUNet. © 2022, CC BY.

关键词： Image reconstruction

Fast Algorithm for Parallel Solving Inversion of Large Scale Small Matrices Based on Gpu

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Jin, Xuebin Chen, Yewang Fan, Wentao Zhang, Yong Du, Jixiang The College of Computer Science and Technology Huaqiao University Xiamen China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Xiamen China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China College of Mechanical Engineering and Automation Huaqiao University Xiamen China

Inverting a matrix is time-consuming, and many works focus on accelerating inverting a single large matrix by GPU. However, the problem of inverting large-scale small matrices has little attention. In this paper, we propose a Revised In-Place Inversion algorithm for inverting large-scale small matrices, which runs on the CUDA platform and utilizes multicore GPUs. The proposed algorithm is well-suited for large-scale-small matrices (dimension $n \leq 32$), which can invert millions of small matrices within tens of milliseconds. In addition, we find there is an upper bound of input data size for each GPU device, the performance will degrade if the input data size is too large. Hence, we improve the proposed method by dividing matrices into batches according to this finding. Experimental results show that this strategy can effectively alleviate the performance degradation for inverting large scale small matrices, and maintain the high-performance execution of the algorithm. © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

Feature refinement: An expression-specific feature learning and fusion method for micro-expression recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhou, Ling Mao, Qirong Huang, Xiaohua Zhang, Feifei Zhang, Zhihong School of Computer Science and Communication Engineering Jiangsu University ZhenjiangJiangsu212013 China School of Computer Engineering Nanjing Institute of Technology China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing100190 China Xiamen University Xiamen China Center for Machine Vision and Signal Analysis University of Oulu Finland

Micro-Expression Recognition has become challenging, as it is extremely difficult to extract the subtle facial changes of micro-expressions. Recently, several approaches proposed several expression-shared features algorithms for micro-expression recognition. However, they do not reveal the specific discriminative characteristics, which lead to sub-optimal performance. This paper proposes a novel Feature Refinement (FR) with expression-specific feature learning and fusion for micro-expression recognition. It aims to obtain salient and discriminative features for specific expressions and also predict expression by fusing the expression-specific features. FR consists of an expression proposal module with attention mechanism and a classification branch. First, an inception module is designed based on optical flow to obtain expression-shared features. Second, in order to extract salient and discriminative features for specific expression, expression-shared features are fed into an expression proposal module with attention factors and proposal loss. Last, in the classification branch, labels of categories are predicted by a fusion of the expression-specific features. Experiments on three publicly available databases validate the effectiveness of FR under different protocol. Results on public benchmarks demonstrate that our FR provides salient and discriminative information for micro-expression recognition. The results also show our FR achieves better or competitive performance with the existing state-of-the-art methods on micro-expression recognition. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

A new efficient and adaptive sclera recognition system

学校读者我要写书评

暂无评论

A new efficient and adaptive sclera recognition system

IEEE Workshop on Computational Intelligence in Biometrics and Identity Management (CIBIM)

作者： Abhijit Das Umapada Pal Miguel Angel Ferrer Ballester Michael Blumenstein Institute for Integrated and Intelligent Systems Griffith University Queensland Australia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India IDeTIC Universidad de Las Palmas de Gran Canaria Las Palmas de Gran Canaria Islas Canarias ES

In this paper an efficient and adaptive biometric sclera recognition and verification system is proposed. Sclera segmentation was performed by Fuzzy C-means clustering. Since the sclera vessels are not prominent, in order to make them clearly visible image enhancement was required. Adaptive histogram equalization, followed by a bank of Discrete Meyer Wavelet was used to enhance the sclera vessel patterns. Feature extraction was performed by, Dense Local Directional pattern (D-LDP). D-LDP patch descriptors of each training image are used to form a bag of features; further Spatial Pyramid Matching was used to produce the final training model. Support Vector Machines (SVMs) are used for classification. The UBIRIS version 1 dataset was used here for experimentation of the proposed system. To investigate regarding sclera patterns adaptively with respect to change in environmental condition, population, data accruing technique and time span two different session of the mention dataset are utilized. The images in two sessions are different in acquiring technique, representation, number of individual and they were captured in a gap of two weeks. An encouraging Equal Error Rate (EER) of 3.95% was achieved in the above mention investigation.

关键词： Iris recognition Image segmentation Histograms Training Feature extraction Adaptive systems

The devil is in the channels: Mutual-channel loss for fine-grained image classification

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chang, Dongliang Ding, Yifeng Xie, Jiyang Bhunia, Ayan Kumar Li, Xiaoxu Ma, Zhanyu Wu, Ming Guo, Jun Song, Yi-Zhe Pattern Recognition and Intelligent System Laboratory School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China School of Computer and Communication Lanzhou University of Technology Lanzhou730050 China Centre for Vision Speech and Signal Processing University of Surrey London United Kingdom

The key to solving fine-grained image categorization is finding discriminate and local regions that correspond to subtle visual traits. Great strides have been made, with complex networks designed specifically to learn part-level discriminate feature representations. In this paper, we show that it is possible to cultivate subtle details without the need for overly complicated network designs or training mechanisms- a single loss is all it takes. The main trick lies with how we delve into individual feature channels early on, as opposed to the convention of starting from a consolidated feature map. The proposed loss function, termed as mutual-channel loss (MC-Loss), consists of two channel-specific components: a discriminality component and a diversity component. The discriminality component forces all feature channels belonging to the same class to be discriminative, through a novel channel-wise attention mechanism. The diversity component additionally constraints channels so that they become mutually exclusive across the spatial dimension. The end result is therefore a set of feature channels, each of which reflects different locally discriminative regions for a specific class. The MC-Loss can be trained end-to-end, without the need for any boundingbox/ part annotations, and yields highly discriminative regions during inference. Experimental results show our MC-Loss when implemented on top of common base networks can achieve stateof- the-art performance on all four fine-grained categorization datasets (CUB-Birds, FGVC-Aircraft, Flowers-102, and Stanford Cars). Ablative studies further demonstrate the superiority of the MC-Loss when compared with other recently proposed generalpurpose losses for visual classification, on two different base networks. Code available at https://***/dongliangchang/ Mutual-Channel-Loss. Copyright © 2020, The Authors. All rights reserved.

关键词： Image classification

Evaluation of feature sensitivity to training data inaccuracy in detection of retinal lesions

学校读者我要写书评

暂无评论

Evaluation of feature sensitivity to training data inaccurac...

Workshops on Image Processing Theory, Tools and Applications, IPTA

作者： Lauri Laaksonen Antti Hannuksela Ela Claridge Pauli Fält Markku Hauta-Kasari Hannu Uusitalo Lasse Lensu Machine Vision and Pattern Recognition Laboratory Lappeenranta university of Technology Lappeenranta Finland School of Computer Science The University of Birmingham United Kingdom School of Computing University of Eastern Finland Finland Department of Ophthalmology University of Tampere Finland TAUH Eye Center Tampere University Hospital Finland

computer aided diagnostic and segmentation tools have become increasingly important in reducing the workload of medical experts performing diagnosis, monitoring and documentation of various eye diseases such as age-related macular degeneration (AMD), diabetic retinopathy (DR) and glaucoma. Supervised methods have been developed for the segmentation and detection of lesions, and the reported performance has been good. The supervised methods, however, need representative data to properly train the classifier. Inaccuracies in the ground truth may have a significant impact on the performance of a supervised method as the training data are not representative. In this study, a quantitative evaluation of the sensitivity of different image features, including colour, texture, edge and higher-level features, to inaccuracy in the ground truth on exudates is presented. A mean decrease of approx. 20% in sensitivity and 13% in specificity was observed when using the most inaccurate training data.

关键词： Training data Sensitivity Retina Image color analysis Image segmentation Feature extraction Lesions

MorphMLP: An Efficient MLP-Like Backbone for Spatial-Temporal Representation Learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhang, David Junhao Li, Kunchang Wang, Yali Chen, Yunpeng Chandra, Shashwat Qiao, Yu Liu, Luoqi Shou, Mike Zheng National University of Singapore Singapore Meitu Inc China ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shanghai AI Laboratory China

Recently, MLP-Like networks have been revived for image recognition. However, whether it is possible to build a generic MLP-Like architecture on video domain has not been explored, due to complex spatial-temporal modeling with large computation burden. To fill this gap, we present an efficient self-attention free backbone, namely MorphMLP, which flexibly leverages the concise Fully-Connected (FC) layer for video representation learning. Specifically, a MorphMLP block consists of two key layers in sequence, i.e., MorphFCs and MorphFCt, for spatial and temporal modeling respectively. MorphFCs can effectively capture core semantics in each frame, by progressive token interaction along both height and width dimensions. Alternatively, MorphFCt can adaptively learn long-term dependency over frames, by temporal token aggregation on each spatial location. With such multi-dimension and multi-scale factorization, our MorphMLP block can achieve a great accuracy-computation balance. Finally, we evaluate our MorphMLP on a number of popular video benchmarks. Compared with the recent state-of-the-art models, MorphMLP significantly reduces computation but with better accuracy, e.g., MorphMLP-S only uses 50% GFLOPs of VideoSwin-T but achieves 0.9% top-1 improvement on Kinetics400, under ImageNet1K pretraining. MorphMLP-B only uses 43% GFLOPs of MViT-B but achieves 2.4% top-1 improvement on SSV2, even though MorphMLP-B is pretrained on ImageNet1K while MViT-B is pretrained on Kinetics400. Moreover, our method adapted to the image domain outperforms previous SOTA MLP-Like architectures. Code is available at https://***/MTLab/MorphMLP. Copyright © 2021, The Authors. All rights reserved.

关键词： Image recognition

An Automatic Student Verification System Utilising Off-Line Thai Name Components

学校读者我要写书评

暂无评论

An Automatic Student Verification System Utilising Off-Line ...

Proceedings of the Digital Image Computing: Technqiues and Applications (DICTA)

作者： Hemmaphan Suwanwiwat Abhijit Das Miguel A. Ferrer Umapada Pal Michael Blumenstein Information Technology Academy James Cook University Cairns Australia School of Software University of Technology Sydney Sydney Australia Palmas de Gran Canaria IDeTIC University of Las Las Palmas Spain Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

This research proposed an automatic student identification and verification system utilising off-line Thai name components. The Thai name components consist of first and last names. Dense texture-based feature descriptors were able to yield encouraging results when applied to different handwritten text recognition scenarios. As a result, the authors employed such features in investigating their performance on Thai name component verification system. In this research, Dense-Local Binary pattern, Dense-Local Directional pattern, and Local Binary pattern combined with Local Directional pattern were employed. A base-line shape/feature i.e. Hidden Markov Model (HMM) was also utilised in this study. As there is no dataset on Thai name verification in the literature, a dataset is proposed for a Thai name verification system. The name component samples were collected from high school students. It consists of 8,400 name components (first and last names) from 100 students. Each student provided 60 genuine name components, and each of the name components was forged by 12 other students. An encouraging result was found employing the above-mentioned features on the proposed dataset.

关键词： Hidden Markov models Feature extraction Handwriting recognition Australia Support vector machines Head

CRNN Based Jersey-Bib Number/Text Recognition in Sports and Marathon Images

学校读者我要写书评

暂无评论

CRNN Based Jersey-Bib Number/Text Recognition in Sports and ...

International Conference on Document Analysis and Recognition

作者： Sauradip Nag Raghavendra Ramachandra Palaiahnakote Shivakumara Umapada Pal Tong Lu Mohan Kankanhalli Department of Computer Science & Engineering Kalyani Government Engineering College Kalyani India Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Norway Faculty of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University China Department of computer science National University of Singapore Singapore

The primary challenge in tracing the participants in sports and marathon video or images is to detect and localize the jersey/Bib number that may present in different regions of their outfit captured in cluttered environment conditions. In this work, we proposed a new framework based on detecting the human body parts such that both Jersey Bib number and text is localized reliably. To achieve this, the proposed method first detects and localize the human in a given image using Single Shot Multibox Detector (SSD). In the next step, different human body parts namely, Torso, Left Thigh, Right Thigh, that generally contain a Bib number or text region is automatically extracted. These detected individual parts are processed individually to detect the Jersey Bib number/text using a deep CNN network based on the 2-channel architecture based on the novel adaptive weighting loss function. Finally, the detected text is cropped out and fed to a CNN-RNN based deep model abbreviated as CRNN for recognizing jersey/Bib/text. Extensive experiments are carried out on the four different datasets including both bench-marking dataset and a new dataset. The performance of the proposed method is compared with the state-of-the-art methods on all four datasets that indicates the improved performance of the proposed method on all four datasets.

关键词： Text recognition Sports Image recognition Hip Thigh Torso Biological system modeling