检索结果-内蒙古大学图书馆

rPPG-MAE: Self-supervised Pre-training with Masked Autoencoders for Remote Physiological Measurement

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Xin Zhang, Yuting Yu, Zitong Lu, Hao Yue, Huanjing Yang, Jingyu School of Electrical and Information Engineering Tianjin University Tianjin300072 China Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta-Lahti University of Technology LUT Lappeenranta53850 Finland Great Bay University Dongguan523000 China Guangzhou511453 China

Remote photoplethysmography (rPPG) is an important technique for perceiving human vital signs, which has received extensive attention. For a long time, researchers have focused on supervised methods that rely on large amounts of labeled data. These methods are limited by the requirement for large amounts of data and the difficulty of acquiring ground truth physiological signals. To address these issues, several self-supervised methods based on contrastive learning have been proposed. However, they focus on the contrastive learning between samples, which neglect the inherent self-similar prior in physiological signals and seem to have a limited ability to cope with noisy. In this paper, a linear self-supervised reconstruction task was designed for extracting the inherent self-similar prior in physiological signals. Besides, a specific noise-insensitive strategy was explored for reducing the interference of motion and illumination. The proposed framework in this paper, namely rPPG-MAE, demonstrates excellent performance even on the challenging VIPL-HR dataset. We also evaluate the proposed method on two public datasets, namely PURE and UBFC-rPPG. The results show that our method not only outperforms existing self-supervised methods but also exceeds the state-of-the-art (SOTA) supervised methods. One important observation is that the quality of the dataset seems more important than the size in self-supervised pre-training of rPPG. The source code is released at https://***/linuxsino/rPPG-MAE. Copyright © 2023, The Authors. All rights reserved.

关键词： Supervised learning

Dynamic hand gesture early recognition based on Hidden Semi-Markov Models

学校读者我要写书评

暂无评论

Dynamic hand gesture early recognition based on Hidden Semi-...

IEEE International Conference on Robotics and Biomimetics

作者： Qianqian Wang Yuanrong Xu Yen-Lun Chen Yong Wang Xinyu Wu University of Science and Technology of China Shenzhen Key Lab for Computer Vision and Pattern Recognition Chinese Academy of Sciences Dept. Mechanical and Automation Engineering The Chinese University of Hong Kong. Guangdong Provincial Key Laboratory of Robotics and Intelligent System Chinese Academy of Sciences

ISBN: (纸本)9781479973989

Real-time performance can be greatly improved, if the early recognition is implemented. In this paper, a dynamic hand gesture early recognition system is proposed. The system can recognize the gesture before it is completed. Our method is based on the Hidden Semi-Markov Models. Three-dimensional information of the gesture trajectory collected by leapmotion is the main data we used. Experiments on the dataset which we established demonstrate the effectiveness of our method.

关键词： Hidden Markov models Gesture recognition Training Conferences Trajectory Arrays

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

Conditional sequential modulation for efficient global image retouching

学校读者我要写书评

暂无评论

arXiv 2020年

作者： He, Jingwen Liu, Yihao Qiao, Yu Dong, Chao ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China SIAT Branch Shenzhen Institute of Artificial Intelligence Robotics for Society Korea Republic of University of Chinese Academy of Sciences China

Photo retouching aims at enhancing the aesthetic visual quality of images that suffer from photographic defects such as over/under exposure, poor contrast, inharmonious saturation. Practically, photo retouching can be accomplished by a series of image processing operations. In this paper, we investigate some commonly-used retouching operations and mathematically find that these pixel-independent operations can be approximated or formulated by multi-layer perceptrons (MLPs). Based on this analysis, we propose an extremely light-weight framework - Conditional Sequential Retouching Network (CSRNet) - for efficient global image retouching. CSRNet consists of a base network and a condition network. The base network acts like an MLP that processes each pixel independently and the condition network extracts the global features of the input image to generate a condition vector. To realize retouching operations, we modulate the intermediate features using Global Feature Modulation (GFM), of which the parameters are transformed by condition vector. Benefiting from the utilization of 1×1 convolution, CSRNet only contains less than 37k trainable parameters, which is orders of magnitude smaller than existing learning-based methods. Extensive experiments show that our method achieves state-of-the-art performance on the benchmark MIT-Adobe FiveK dataset quantitively and qualitatively. Code is available at https://***/hejingwenhejingwen/CSRNet. Copyright © 2020, The Authors. All rights reserved.

关键词： Pixels

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

ICDAR 2013 CROHME: Third International Competition on recognition of Online Handwritten Mathematical Expressions

学校读者我要写书评

暂无评论

ICDAR 2013 CROHME: Third International Competition on Recogn...

International Conference on Document Analysis and recognition

作者： Harold Mouchère Christian Viard-Gaudin Richard Zanibbi Utpal Garain Dae Hwan Kim Jin Hyung Kim LUNAM IRCCyN IVC-UMR CNRS 6597 Ecole Polytechnique de Université de Nantes Nantes France Department of Computer Science Rochester Institute of Technology Rochester NY USA Computer Vision & Pattern Recognition Unit Indian Statistical Institute Kolkata India Korea Advanced Institute of Science and Technology Daejeon South Korea

ISBN: (纸本)9781479901937

We report on the third international Competition on Handwritten Mathematical Expression recognition (CROHME), in which eight teams from academia and industry took part. For the third CROHME, the training dataset was expanded to over 8000 expressions, and new tools were developed for evaluating performance at the level of strokes as well as expressions and symbols. As an informal measure of progress, the performance of the participating systems on the CROHME 2012 data set is also reported. Data and tools used for the competition will be made publicly available.

关键词： Grammar Handwriting recognition Training Training data Layout Mathematical model

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

A new cold feature based handwriting analysis for enthnicity/nationality identification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Nag, Sauradip Shivakumara, Palaiahnakote Yirui, Wu Pal, Umapada Lu, Tong Kalyani Government Engineering College Kalyani Kolkata India Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia College of Computer and Information Hohai University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India National Key Lab for Novel Software Technology Nanjing University Nanjing China

Identifying crime for forensic investigating teams when crimes involve people of different nationals is challenging. This paper proposes a new method for ethnicity (nationality) identification based on Cloud of Line Distribution (COLD) features of handwriting components. The proposed method, at first, explores tangent angle for the contour pixels in each row and the mean of intensity values of each row in an image for segmenting text lines. For segmented text lines, we use tangent angle and direction of base lines to remove rule lines in the image. We use polygonal approximation for finding dominant points for contours of edge components. Then the proposed method connects the nearest dominant points of every dominant point, which results in line segments of dominant point pairs. For each line segment, the proposed method estimates angle and length, which gives a point in polar domain. For all the line segments, the proposed method generates dense points in polar domain, which results in COLD distribution. As character component shapes change, according to nationals, the shape of the distribution changes. This observation is extracted based on distance from pixels of distribution to Principal Axis of the distribution. Then the features are subjected to an SVM classifier for identifying nationals. Experiments are conducted on a complex dataset, which show the proposed method is effective and outperforms the existing method. Copyright © 2018, The Authors. All rights reserved.

关键词： Crime

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