检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jingchao Hou Guanghui He Shanghai Jiao Tong University

This paper addresses two key limitations in existing image Signal processing (ISP) approaches: the suboptimal performance in low-light conditions and the lack of trainability in traditional ISP methods. To tackle these issues, we propose a novel, trainable ISP framework that incorporates both the strengths of traditional ISP techniques and advanced Multi-Scale Retinex (MSR) algorithms for night-time enhancement. Our method consists of three primary components: an ISP-based Luminance Harmonization layer to initially optimize luminance levels in RAW data, a deep learning-based MSR layer for nuanced decomposition of image components, and a specialized enhancement layer for both precise, region-specific luminance enhancement and color denoising. The proposed approach is validated through rigorous experiments on machine vision benchmarks and objective visual quality indicators. Our results demonstrate not only a significant improvement over existing methods but also robust adaptability under diverse lighting conditions. This work offers a versatile ISP framework with promising applications beyond its immediate scope.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of methods for parallel processing of series of images obtained by a machine vision system in various electromagnetic ranges 2

Development of methods for parallel processing of series of ...

引用

Conference on Optical Instrument Science, Technology, and applications II Held as Part of SPIE Optical System Design Conference

作者： Semenishchev, Evgenii Voronin, Viacheslav Alepko, Andrey Zelensky, Aleksandr Agaian, Sos Moscow State Tech Univ STANKIN Moscow Russia CUNY Dept Comp Sci New York NY 10314 USA

ISBN: (数字)9781510645974

ISBN: (纸本)9781510645974;9781510645967

machine vision systems used in modern industrial complexes, based on the analysis of multi and hyperspectral imaging. The transition to implementing the "Industry 4.0" program is not possible when using one type of data. The first control system used only the visible range image. They made it possible to analyze the trajectories of movement of objects, control product quality, carry out security functions (control of perimeter crossing), etc. The development of new industrial robotic cells and processing complexes using cognitive functions implying the receipt, analysis, and processing of heterogeneous data. The construction of a unified information field, which allows performing multidimensional operations with data, allows increasing the speed of decision-making and the implementation of automated robot-human systems at the level of an assistant working in a unified workspace. The use of machine vision systems analyzing information received in: visible (shape, the trajectory of movement, position of objects, etc.);near-infrared range (data is similar to visible, allows operation in dusty, foggy, low light conditions);far-infrared range - thermal (plotting temperature gradients, identifying areas of overheating);ultraviolet range (analysis of ionization sources, corona discharges, static charges, tags);X-ray and microwave ranges (analysis of the surface and internal structure of objects, allow the identification of defects);range and 3D sensors (construction of volumetric figures, analysis of the relative position of objects and their interaction), etc. Data analysis is often performed not by a single camera but by a group of sensors located not in a single housing. Primary data integration reduces the number of information channels while maintaining the functionality and accuracy of the analysis. The article discusses creating fusion images obtained by industrial sensors into a combined image containing joint data. Combining multi and hyperspectral imaging makes i

关键词： preprocessing IR image local features denoising combining image fusion image

来源：评论

学校读者我要写书评

暂无评论

High-precision velocity measurement method based on high frame rate image processing

High-precision velocity measurement method based on high fra...

引用

2022 International Conference on machine vision, Automatic Identification and Detection, MVAID 2022

作者： Zhou, Saiao Nie, Yuman Fan, Fan Tang, Yuanyang Wang, Zhou Wang, Lingfei Wang, Yaoxiong Cao, Pingguo Hefei University of Technology Anhui Hefei China Hefei Institutes of Physical Science Chinese Academy of Sciences Anhui Hefei China Hefei Shuangling Electronic Technology Co. Ltd. Anhui Hefei China

The traditional drop-weight impact velocity measurement is affected by the measurement distance of the sensor and the measurement environment, and the accuracy is difficult to guarantee. Aiming at this problem, this paper proposes a high-precision velocity measurement method based on high frame rate image. Firstly, a measurement scheme based on high frame rate image is designed, the position information is obtained by processing the image of the marked point, and the target impact velocity is obtained according to the time difference between frames;Then an error model is established, and the sources of errors and solutions are analyzed;Then by improving the subpixel edge and other methods to improve the feature extraction accuracy of the marking point image, thereby improving the velocity measurement accuracy. Finally, the measurement accuracy is verified by the actual drop-weight free-fall experiment. The experimental results show that the method proposed in this paper is better than 0.5% in the measurement of the impact velocity of the drop weight, which meets the needs of practical applications, and the measuring process is visualized and traceable, which has high application value. © Published under licence by IOP Publishing Ltd.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

Combining SIFT and BRISK Descriptors to Improve image Matching Accuracy

Combining SIFT and BRISK Descriptors to Improve Image Matchi...

引用

IEEE Pacific Rim Conference on Communications, Computers and Signal processing

作者： Sina Ghaffari Kin Fun Li David W. Capson Department of Electrical and Computer Engineering University of Victoria Victoria Canada

ISBN: (数字)9798350362312

ISBN: (纸本)9798350362329

Local descriptor algorithms are foundational in computer vision applications such as image matching and image retrieval. Some local descriptor algorithms extract features containing similar information from images while others extract complementary information. In this work, we investigate the advantages of combining a binary and a non-binary local descriptor algorithm. We propose and compare three methods to combine SIFT and BRISK descriptor algorithms selected because they produce complementary descriptor vectors. First, we propose to combine SIFT and BRISK descriptors using a weighted summation of their individual descriptor distances with learned weights. Our second method converts SIFT into a binary descriptor and concatenates the binary SIFT vector with the BRISK descriptor. The third method is to scale the binary BRISK descriptor vector and concatenate it with the SIFT descriptor. Parameters for combining the descriptors are learned based on the HPatches data set for each of the three methods. Our proposed methods increase the mean Average Precision in the range of 3% to 15.8% over the original BRISK and in the range of 5.9% to 21.8% over the original SIFT algorithm in various evaluation conditions.

关键词： machine learning algorithms image matching Neural networks image retrieval Signal processing algorithms machine learning Signal processing Feature extraction Vectors Data mining

来源：评论

学校读者我要写书评

暂无评论

Chromosome analysis using a hybrid deep CNN and structural feature-based grouping model

引用

Multimedia Tools and applications 2025年 1-30页

作者： Isfahani, Farahnaz Peiravi Pourghassem, Hossein Mahdavi-Nasab, Homayoun Naghsh, Alireza Department of Electrical Engineering Najafabad Branch Islamic Azad University Najafabad Iran Digital Processing and Machine Vision Research Center Najafabad Branch Islamic Azad University Najafabad Iran

Chromosome analysis and classification are essential in clinical applications to diagnose various structural and numerical abnormalities. Recently, karyotype analysis using intelligent image processing methods, especially deep learning, has attracted significant attention as a genetic abnormality test. This paper presents a novel chromosome classification algorithm that uses high-level features extracted from deep convolutional neural networks (DCNN) along with morphological features designed to identify and modify the classes of misclassified chromosomes. Initially, chromosomes are classified using a DCNN. Some structural features, such as centromere and banding profile, are then extracted to group chromosomes again. Based on the results of the two preceding methods, a decision strategy is utilized to identify misclassified chromosomes. Here, a final DCNN-based strategy is introduced to assign misclassified chromosomes to the associated classes. The proposed method can be used in parallel with other chromosome classification methods to modify misclassified chromosomes and promote the accuracy of the classification. Evaluation results show that the proposed algorithm outperforms relevant state-of-the-art algorithms regarding the classification precision and accuracy of 99.66 and 96.52%, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EG-SNIK: A Free Viewing Egocentric Gaze Dataset and Its applications

引用

IEEE ACCESS 2022年 10卷 129626-129641页

作者： Malladi, Sai Phani Kumar Mukherjee, Jayanta Larabi, Mohamed-Chaker Chaudhury, Santanu Indian Inst Technol Kharagpur Adv Technol Dev Ctr Kharagpur 721302 India IIT Kharagpur Dept Comp Sci & Engn Kharagpur 721302 India Univ Poitiers Xlim Umr Cnrs 7252 F-86000 Poitiers France IIT Jodhpur Dept Comp Sci & Engn Jodhpur 342030 India

Egocentric vision data captures the first person perspective of a visual stimulus and helps study the gaze behavior in more natural contexts. In this work, we propose a new dataset collected in a free viewing style with an end-to-end data processing pipeline. A group of 25 participants provided their gaze information wearing Tobii Pro Glasses 2 set up at a museum. The gaze stream is post-processed for handling missing or incoherent information. The corresponding video stream is clipped into 20 videos corresponding to 20 museum exhibits and compensated for user's unwanted head movements. Based on the velocity of directional shifts of the eye, the I-VT algorithm classifies the eye movements into either fixations or saccades. Representative scanpaths are built by generalizing multiple viewers' gazing styles for all exhibits. Therefore, it is a dataset with both the individual gazing styles of many viewers and the generic trend followed by all of them towards a museum exhibit. The application of our dataset is demonstrated for characterizing the inherent gaze dynamics using state trajectory estimator based on ancestor sampling (STEAS) model in solving gaze data classification and retrieval problems. This dataset can also be used for addressing problems like segmentation, summarization using both conventional machine and deep learning approaches.

关键词： Egocentric gaze dataset museum exhibit head movement compensation representative scanpath categorization

来源：评论

学校读者我要写书评

暂无评论

Unobtrusive human activity classification based on combined time-range and time-frequency domain signatures using ultrawideband radar

引用

IET SIGNAL processing 2021年第8期15卷 543-561页

作者： Mostafa, Mohamad Chamaani, Somayyeh KN Tooth Univ Technol Fac Elect Engn Tehran Iran

In this proposed approach to unobtrusive human activity classification, a two-stage machine learning-based algorithm was applied to backscattered ultrawideband radar signals. First, a preprocessing step was applied for noise and clutter suppression. Then, feature extraction and a combination of time-frequency (TF) and time-range (TR) domains were used to extract the features of human activities. Then, feature analysis was performed to determine robust features relative to this kind of classification and reduce the dimensionality of the feature vector. Subsequently, different recognition algorithms were applied to group activities as fall or non-fall and categorise their types. Finally, a performance study was used to choose the higher accuracy algorithm. The ensemble bagged tree and fine K-nearest neighbour methods showed the best performance. The results show that the two-stage classification was more accurate than the one-stage. Finally, it was observed that the proposed approach using a combination of TR and TF domains with two-stage recognition outperformed reference approaches mentioned in the literature, with average accuracies of 95.8% for eight-activities classification and 96.9% in distinguishing between fall and non-fall activities with efficient computational complexity.

关键词： Computer vision and image processing techniques group activities feature vector robust features time-range domain signatures learning (artificial intelligence) two-stage classification image motion analysis different recognition algorithms two-stage recognition feature extraction human activities Radar equipment, systems and applications higher accuracy algorithm backscattered ultrawideband radar signals ultra wideband radar clutter suppression time-frequency analysis radar clutter feature analysis image recognition image classification nonfall activities time-frequency domain signatures unobtrusive human activity classification two-stage machine learning-based algorithm

来源：评论

学校读者我要写书评

暂无评论

An automatic machine vision-based algorithm for inspection of hardwood flooring defects during manufacturing

引用

ENGINEERING applications OF ARTIFICIAL INTELLIGENCE 2023年 123卷

作者： Truong, Van Doi Xia, Jiaping Jeong, Yuhyeong Yoon, Jonghun Hanyang Univ Dept Mech Design Engn Seongdonggu 222 Wangsimni Ro Seoul 04763 South Korea Hanyang Univ Dept Mech Engn 55 Hanyangdaehak Ro Ansan 15588 Gyeonggi Do South Korea Hanyang Univ BK21 FOUR ERICA ACE Ctr Ansan 15588 Gyeonggi South Korea

Hardwood flooring products are popular construction materials because of their aesthetics, durability, low maintenance requirements, and affordability. To ensure product quality during manufacturing, common defects such as cracks, chips, or stains are typically detected and classified manually, but this process can decrease productivity. The aim of this study was to develop an automatic machine vision-based inspection system with a robust algorithm for inspecting small hardwood flooring defects in a production line. This defect-inspection algorithm is based on image-processing techniques, including background elimination, boundary approximation, and defect inspection of photographs. The YOLOv5 deep-learning algorithm for object detection was applied to detect surface defects. The resulting algorithm identified the quality of each specimen (i.e., either good or defective). The influences of colour and surface patterns on defect inspection were experimentally investigated under light conditions. The algorithm was adaptable to specimens with different colours and patterns under various conditions, demonstrating the potential of this approach in practical situations.

关键词： Hardwood flooring Automatic defect inspection image processing Yolov5

来源：评论

学校读者我要写书评

暂无评论

Uniformity Correction of CMOS image Sensor Modules for machine vision Cameras

引用

SENSORS 2022年第24期22卷

作者： Becker, Gabor Szedo Lovas, Robert Obuda Univ Doctoral Sch Appl Informat & Appl Math Becs Ut 96-B H-1034 Budapest Hungary Eotvos Lorand Res Network ELKH Inst Comp Sci & Control SZTAK Kende U 13-17 H-1111 Budapest Hungary

Flat-field correction (FFC) is commonly used in image signal processing (ISP) to improve the uniformity of image sensor pixels. image sensor nonuniformity and lens system characteristics have been known to be temperature-dependent. Some machine vision applications, such as visual odometry and single-pixel airborne object tracking, are extremely sensitive to pixel-to-pixel sensitivity variations. Numerous cameras, especially in the fields of infrared imaging and staring cameras, use multiple calibration images to correct for nonuniformities. This paper characterizes the temperature and analog gain dependence of the dark signal nonuniformity (DSNU) and photoresponse nonuniformity (PRNU) of two contemporary global shutter CMOS image sensors for machine vision applications. An optimized hardware architecture is proposed to compensate for nonuniformities, with optional parametric lens shading correction (LSC). Three different performance configurations are outlined for different application areas, costs, and power requirements. For most commercial applications, the correction of LSC suffices. For both DSNU and PRNU, compensation with one or multiple calibration images, captured at different gain and temperature settings are considered. For more demanding applications, the effectiveness, external memory bandwidth, power consumption, implementation, and calibration complexity, as well as the camera manufacturability of different nonuniformity correction approaches were compared.

关键词： CMOS image sensor ISP FPGA ASIC NUC FFC FPN DSNU PRNU

来源：评论

学校读者我要写书评

暂无评论

Does explainable machine learning uncover the black box in vision applications?

引用

image AND vision COMPUTING 2022年 118卷

作者： Narwaria, Manish Indian Inst Technol Jodhpur Dept Elect Engn NH 62Surpura Bypass Rd Karwar 342037 Rajasthan India

machine learning (ML) in general and deep learning (DL) in particular has become an extremely popular tool in several vision applications (like object detection, super resolution, segmentation, object tracking etc.). Almost in parallel, the issue of explainability in ML (i.e. the ability to explain/elaborate the way a trained ML model arrived at its decision) in vision has also received fairly significant attention from various quarters. However, we argue that the current philosophy behind explainable ML suffers from certain limitations, and the resulting explanations may not meaningfully uncover black box ML models. To elaborate our assertion, we first raise a few fundamental questions which have not been adequately discussed in the corresponding literature. We also provide perspectives on how explainablity in ML can benefit by relying on more rigorous principles in the related areas.(c) 2021 Elsevier B.V. All rights reserved.

关键词： Explainable machine learning Deep learning vision Signal processing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：