首页/论文/2004.03153

arXiv 2004.031532020-04-07cs.CV

Adaptive Multiscale Illumination-Invariant Feature Representation for Undersampled Face Recognition

School of Automation, Southeast University（东南大学自动化学院）；School of Automation, Nanjing University of Posts and Telecommunications（南京邮电大学自动化学院）

Yang Zhang, Changhui Hu, Xiaobo Lu

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

This paper presents an novel illumination-invariant feature representation approach used to eliminate the varying illumination affection in undersampled face recognition. Firstly, a new illumination level classification technique based on Singular Value Decomposition (SVD) is proposed to judge the illumination level of input image. Secondly, we construct the logarithm edgemaps feature (LEF) based on lambertian model and local near neighbor feature of the face image, applying to local region within multiple scales. Then, the illumination level is referenced to construct the high performance LEF as well realize adaptive fusion for multiple scales LEFs for the face image, performing JLEF-feature. In addition, the constrain operation is used to remove the useless high-frequency interference, disentangling useful facial feature edges and constructing AJLEF-face. Finally, the effects of the our methods and other state-of-the-art algorithms including deep learning methods are tested on Extended Yale B, CMU PIE, AR as well as our Self-build Driver database (SDB). The experimental results demonstrate that the JLEF-feature and AJLEF-face outperform other related approaches for undersampled face recognition under varying illumination.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

A Data Dependent Multiscale Model for Hyperspectral Unmixing With Spectral Variability

Federal University of Santa Catarina（圣卡塔琳娜联邦大学）；Université Côte d’Azur（蔚蓝海岸大学）；Northeastern University（东北大学）；Catholic University of Pelotas（佩洛塔斯天主教大学）

Spectral variability in hyperspectral images can result from factors including environmental, illumination, atmospheric and temporal changes. Its occurrence may lead to the propagation of significant estimation errors in the unmixing process. To address this issue, extended linear mixing models have been proposed which lead to large scale nonsmooth ill-posed inverse problems. Furthermore, the regularization strategies used to obtain meaningful results have introduced interdependencies among abundance solutions that further increase the complexity of the resulting optimization problem. In this …

2020-01-22cs.CV

AIGS-Net: 基于2D高斯泼溅的紧凑光照场建模用于快速低光图像增强

AIGS-Net: Compact Illumination Field Modeling via 2D Gaussian Splatting for Fast Low-Light Image Enhancement

College of Mechanical and Vehicle Engineering, Chongqing University（重庆大学机械与车辆工程学院）；Department of Electrical and Computer Engineering, Carnegie Mellon University（卡内基梅隆大学电气与计算机工程系）；Herbert Wertheim College of Engineering, University of Florida（佛罗里达大学赫伯特·韦特海姆工程学院）；School of Mathematics and Statistics, Qingdao University（青岛大学数学与统计学院）；National Innovation Center of Intelligent and Connected Vehicles（国家智能网联汽车创新中心）；School of Vehicle and Mobility, Tsinghua University（清华大学车辆与运载学院）

提出AIGS-Net，通过输入自适应的2D高斯泼溅光照场和零参数多尺度上下文编码，以约40个可学习参数实现低光图像增强，在LOL和LSRW基准上平衡了增强质量与推理效率。

2026-06-17cs.CV

Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding

Ankara University（安卡拉大学）

A common approach for moving objects segmentation in a scene is to perform a background subtraction. Several methods have been proposed in this domain. However, they lack the ability of handling various difficult scenarios such as illumination changes, background or camera motion, camouflage effect, shadow etc. To address these issues, we propose a robust and flexible encoder-decoder type neural network based approach. We adapt a pre-trained convolutional network, i.e. VGG-16 Net, under a triplet framework in the encoder part to embed an image in multiple scales into the feature space and use …

2018-01-07cs.CV

视觉提示结合基于特征重建的双教师监督异常检测

Visual Prompting Meets Feature Reconstruction-Based Anomaly Detection with Dual-Teacher Supervision

IBM Research Europe Zurich（IBM欧洲研究院苏黎世分院）

针对异常检测在真实场景中因物体尺度、视角等变化失效的问题，提出视觉提示管道、解冻教师模型和扩散生成数据增强，在AeBAD数据集上提升3.5个百分点。

2026-06-08cs.AIcs.CV

Deep Local Binary Patterns

Faculdade de Engenharia da Universidade do Porto（波尔图大学工程学院）；INESC TEC（INESC TEC 研究所）

Local Binary Pattern (LBP) is a traditional descriptor for texture analysis that gained attention in the last decade. Being robust to several properties such as invariance to illumination translation and scaling, LBPs achieved state-of-the-art results in several applications. However, LBPs are not able to capture high-level features from the image, merely encoding features with low abstraction levels. In this work, we propose Deep LBP, which borrow ideas from the deep learning community to improve LBP expressiveness. By using parametrized data-driven LBP, we enable successive applications of t…

2017-11-17cs.CV

Evaluation of Human and Machine Face Detection using a Novel Distinctive Human Appearance Dataset

Stevens Institute of Technology（斯蒂文斯理工学院）

Face detection is a long-standing challenge in the field of computer vision, with the ultimate goal being to accurately localize human faces in an unconstrained environment. There are significant technical hurdles in making these systems accurate due to confounding factors related to pose, image resolution, illumination, occlusion, and viewpoint [44]. That being said, with recent developments in machine learning, face-detection systems have achieved extraordinary accuracy, largely built on data-driven deep-learning models [70]. Though encouraging, a critical aspect that limits face-detection p…

2021-11-02cs.CV

更多相关论文收起更多论文

One for All: An End-to-End Compact Solution for Hand Gesture Recognition

Malaviya National Institute of Technology Jaipur（斋浦尔马拉维亚国家理工学院）；olx people（OLX人事）

The HGR is a quite challenging task as its performance is influenced by various aspects such as illumination variations, cluttered backgrounds, spontaneous capture, etc. The conventional CNN networks for HGR are following two stage pipeline to deal with the various challenges: complex signs, illumination variations, complex and cluttered backgrounds. The existing approaches needs expert expertise as well as auxiliary computation at stage 1 to remove the complexities from the input images. Therefore, in this paper, we proposes an novel end-to-end compact CNN framework: fine grained feature atte…

2021-05-15cs.CV

GMGaze：基于MoE的上下文感知 gaze 估计方法结合 CLIP 和多尺度 Transformer

GMGaze: MoE-Based Context-Aware Gaze Estimation with CLIP and Multiscale Transformer

School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, China（桂林电子科技大学人工智能学院）；The Laboratory for Imagery, Vision and Artificial Intelligence, École de Technologie Supérieure, Montreal, Canada（图像、视觉与人工智能实验室，蒙特利尔大学高级技术学院）；Information Technology Department, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia（计算机与信息科学学院信息科技系，沙特国王大学）；Department of Cybersecurity, College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia（计算机科学与工程学院网络安全系，塔伊卜大学）；Department of Networked Engineering, College of Computer Science and Engineering, Jeddah University, Jeddah, Saudi Arabia（计算机科学与工程学院网络工程系，吉达大学）

本文提出 GMGaze 方法，通过多尺度 Transformer 和 CLIP 结合，利用语义原型条件和稀疏 MoE 模块提升 gaze 估计精度，实验表明在多个基准上均优于现有方法。

2026-05-01cs.CV

FeatEnHancer：增强低光照视觉下目标检测及其他任务的分层特征

FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision

DFKI - German Research Center for Artificial Intelligence（德国人工智能研究中心）；RPTU Kaiserslautern（凯泽斯劳滕工业大学）

本文提出即插即用的 FeatEnHancer 模块，通过任务相关损失引导的多头注意力分层融合多尺度特征，在暗光目标检测、人脸检测、夜间语义分割和视频目标检测等多个低光照视觉任务中取得显著一致的性能提升。

2023-08-07cs.CV

Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

University of Freiburg（弗莱堡大学）；Toyota Research Institute（丰田研究院）

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering t…

2019-07-08cs.CV

眼底图像中的视盘分割：从经典图像处理与可变形模型到现代人工智能

Optic Disc Segmentation in Fundus Images: From Classical Image Processing and Deformable Models to Modern AI

The University of Akron（阿克伦大学）

本综述梳理视盘分割技术从经典方法到现代AI方法的发展，总结核心原则，指出边界模糊等持续挑战，为该领域研究提供方法学参考。

2026-08-20cs.CVeess.IV