检索结果-内蒙古大学图书馆

Comparative Study on Evaluating the Performance of Automated Bacterial Colony Counting with Available APP and Software on Generated image Dataset

引用

SN Computer Science 2025年第4期6卷 1-16页

作者： Arora, Prachi Tewary, Suman Krishnamurthi, Srinivasan Kumari, Neelam School of Computing Indian Institute of Information Technology Una (IIIT-Una) Una 177209 India Academy of Scientific and Innovative Research (AcSIR) Ghaziabad 201002 India Thin Film Coating Facility CSIR-Central Scientific Instruments Organisation (CSIR-CSIO) Sector 30-C Chandigarh 160030 India Materials Science and Sensor Applications CSIR-Central Scientific Instruments Organisation (CSIR-CSIO) Sector 30-C Chandigarh 160030 India Advanced Materials and Processes Division CSIR-National Metallurgical Laboratory (CSIR-NML) Jamshedpur 831007 India MTCC-Gene bank CSIR-Institute of Microbial Technology (CSIR-IMTECH) Sector 39-A Chandigarh 160039 India

Recent developments in image analysis and interpretation using computer vision techniques have shown potential for novel applications in microbiology laboratories to support the task of automation, aiming for faster and more reliable detection. image processing techniques and machine learning models can be valuable tools in the screening process, helping technicians spend less time classifying no-growth results and quickly separating the categories for further analysis. In this context, creating a dataset of different bacterial strain images is a fundamental objective for developing and improving the accuracy of image processing models. Therefore, this manuscript acquired a dataset of water samples with different bacterial strain images on a petri dish following a standardized process with controlled conditions of positioning and lighting. The image acquisition device was also developed with a light-emitting diode (LED) and diffuser as a lighting source and a smartphone camera with 16 MP resolution. In addition, the present manuscript also focuses on comparing the accuracy of the proposed algorithm with the available apps and software using the custom-built imaging device. Hence, the resulting dataset consists of 100 images, which is helpful for researchers working in image processing to develop an algorithm for automated counting of bacterial colonies on petri dishes. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Bacterial colonies image datasets image processing Imaging device Segmentation Water samples

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition with CNN in FastAI 1

Human Activity Recognition with CNN in FastAI

引用

1st International Conference on Social and Sustainable Innovations in Technology and Engineering (SASI-ITE)

作者： Parvathaneni, Naga Srinivasu Bonu, Rahul Karthik Chaitanya, A. J. K. Naga Bolliboiyna, Sivaraju Galinki, Deepak Abbineni, Venkata Sivamani Kumar Prasad V Potluri Siddhartha Inst Technol Vijayawada India

ISBN: (纸本)9798350360806;9798350360790

Human activity recognition (HAR) is the designated term for the automated distinguishing of physical activities conducted by individuals. The current study analyzes convolutional neural networks (CNN) in human activity recognition, particularly on datasets including images. By analyzing and correctly identifying the activities performed by individuals in image datasets, analysts and programmers can achieve a valuable understanding of human behaviors across different circumstances. HAR involves the automation of detection and categorization of activities that are performed by individuals and are included in image datasets using deep learning methodologies and advanced image processing techniques. Here, we propose a deep learning methodology that can accurately classify the given input images into various activities like sitting, standing, walking, and sleeping. To determine the models efficiency, we have employed a comprehensive dataset that is available in Kaggles repository, namely the activity dataset. This dataset offers a wide range of authentic and varied activities performed by groups of individuals across different locations. It contains an array of labeled images capturing their activities, like sitting, standing, walking, and sleeping, across diverse circumstances. This research established an unusual approach for HAR, which was empowered by CNN Drive by FastAI and offered an easy and accessible deep learning platform for users.

关键词： Human Activity Recognition Convolutional Neural Networks image datasets Activity Classes FastAI

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based instance segmentation architectures in agriculture: A review of the scopes and challenges

引用

SMART AGRICULTURAL TECHNOLOGY 2024年 8卷

作者： Charisis, Christos Argyropoulos, Dimitrios Univ Coll Dublin Sch Biosyst & Food Engn Dublin Ireland

Deep learning (DL) based instance segmentation has attracted a growing research interest in the scientific community to tackle precision agriculture problems over the past few years. However, accurate crop detection and localization in complex environments pose a significant challenge. Instance segmentation is considered as a promising DL technique that expands on object detection to perform pixel-wise image instance segmentation and address pattern recognition problems efficiently. In this review, we identify 77 relevant studies on DL-based instance segmentation implementations in agriculture and thoroughly investigate them from the following perspectives: i) the specific architecture employed;ii) the data type and availability, the data annotation process and the data pre-processing techniques;iii) the performance metrics used;and iv) hardware, inference time and GPU requirements. Our findings indicate that crop detection (48 papers) constitutes a fundamental task in a DLbased instance segmentation pipeline to enable crop growth monitoring (19 papers) and plant health analysis (10 papers). Among them, 6 papers reported robotic manipulation and other related automation tasks. Based on our findings we can conclude that there is a significant trend towards two-stage DL-based instance segmentation models i.e., Mask R-CNN baseline and customized architectures (69 papers). Limitations and challenges, such as availability of benchmark crop datasets, open-source codes for semi-automatic annotation tools, technical requirements and opportunities for future research are discussed.

关键词： image datasets Specialty crops Mask R-CNN Automation machine vision Robotics

来源：评论

学校读者我要写书评

暂无评论

Tackling Dataset Bias With an Automated Collection of Real-World Samples

引用

IEEE ACCESS 2022年 10卷 126832-126844页

作者： Sevetlidis, Vasileios Pavlidis, George Mouroutsos, Spyridon Gasteratos, Antonios Athena Res Ctr Univ Campus Kimmeria Xanthi 67100 Greece Democritus Univ Thrace Dept Prod & Management Engn Xanthi 67100 Greece Democritus Univ Thrace Dept Elect & Comp Engn Univ Campus Kimmeria Xanthi 67100 Greece

The early 21st-century technological advancements tilted the scales towards data-driven learning. Thus, modern machine-learning systems rely heavily on data to learn complex models to efficiently provide relevant predictions. Data-driven learning suffers from overfitting, a situation in which the learning process seems to have converged into a model that, unfortunately, lacks generalization power. One way to withstand overfitting is to expand the training dataset with more diverse samples. Typically, this is implemented (particularly in computer vision research, which is of interest in this study) by multiplying the original sample using several transformations. Although this strategy might seem straightforward, it does not affect any preexisting dataset bias because the initial distribution remains more or less similar. Ideally, new samples of unseen data must be found, but the cost of acquiring them individually is high. This study presents a novel pipeline that combines state-of-the-art modules to automatically create new thematic datasets with low bias. The proposed method was able to acquire and allocate more than 880K previously unseen images to produce a data collection, that InceptionV3 classified it with 72% accuracy and achieved 0.0008 performance variance when testing on similar datasets.

关键词： Benchmark testing Training data Artificial intelligence Data models Machine learning Ontologies Computer vision Search methods Web sites AI dataset bias domain shift image datasets machine learning web search

来源：评论

学校读者我要写书评

暂无评论

INCREMENTAL image LABELING VIA ITERATIVE REFINEMENT

INCREMENTAL IMAGE LABELING VIA ITERATIVE REFINEMENT

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Giunchiglia, Fausto Diao, Xiaolei Bagchi, Mayukh Univ Trento DISI Trento Italy

ISBN: (纸本)9798350302615

Data quality is critical for multimedia tasks, while various types of systematic flaws are found in image benchmark datasets, as discussed in recent work. In particular, the existence of the semantic gap problem leads to a many-to-many mapping between the information extracted from an image and its linguistic description. This unavoidable bias further leads to poor performance on current computer vision tasks. To address this issue, we introduce a Knowledge Representation (KR)-based methodology to provide guidelines driving the labeling process, thereby indirectly introducing intended semantics in ML models. Specifically, an iterative refinement-based annotation method is proposed to optimize data labeling by organizing objects in a classification hierarchy according to their visual properties, ensuring that they are aligned with their linguistic descriptions. Preliminary results verify the effectiveness of the proposed method.

关键词： Data Quality Semantic Gap Problem image datasets Visual Properties

来源：评论

学校读者我要写书评

暂无评论

Deep learning applied to plant pathology: the problem of data representativeness

引用

TROPICAL PLANT PATHOLOGY 2022年第1期47卷 85-94页

作者： Barbedo, Jayme G. A. Embrapa Informat Agr Av Andre Tosello BR-13083886 Campinas SP Brazil

The rise of deep learning techniques has profoundly impacted both research and applications of pattern and object recognition in digital images. In plant pathology, the number of scientific articles on the use of deep learning for disease classification using images has grown steadily for at least a decade and targeted most important agricultural crops. Results have been encouraging, with accuracies of many prediction models usually approaching 100%. It is now widely accepted that, enough data being available, deep learning models can solve most of the image classification problems. However, determining what "enough" means in each context is far from trivial because this involves not only the number of samples used for training, but also the quality, in particular the representativeness of the dataset. More important than having a large sample size is to guarantee that all the variability associated to a given classification problem is represented in the dataset. Achieving this goal is particularly challenging for plant disease images because the agricultural environment is non-structured and highly dynamic, containing numerous variables that introduce variability to the problem. To make matters even more difficult, image annotation is time consuming and prone to inconsistencies due to its subjectivity. As a result, all studies in the literature employ datasets that represent only a fraction of the whole range of the variability, and many of these do not even acknowledge the limitations of the experimental conditions. Experiments with limited scope are valuable in the early stages of emerging research topics, but the application of deep learning to plant pathology has matured to the point where new studies need to contribute something more substantial. Unfortunately, many of the recent publications have been redundant, differing from previous research only by the adoption of slightly different experimental setups and improved model architectures. To move forward, ne

关键词： image analysis Plant disease image datasets Disease recognition

来源：评论

学校读者我要写书评

暂无评论

Explainable Deep Machine Learning for Medical image Analysis

Explainable Deep Machine Learning for Medical Image Analysis

引用

作者： Gaudio, Alex Carnegie Mellon University

学位级别：Ph.D., Doctor of Philosophy

Explanations justify the development and adoption of algorithmic solutions for prediction problems in medical image analysis. This thesis introduces two guiding principles for creating and exploiting explanations of deep networks and medical image data. The first guiding principle is to use explanations to expose inefficiencies in the design of models and image datasets. The second principle is to leverage tools of compression and fixed-weight methods that minimize learning to make more efficient and effective models and more usable medical image datasets. The outcome is more effective deep learning in medical image analysis. Application of these guiding principles in different settings results in five main contributions: (a) improved understanding of biases present in deep networks and medical images, (b) improved predictive and computational performance of predictive models, (c) creation of ante-hoc models that are interpretable by design, (d) creation of smaller image datasets, and (e) improved visual privacy. This thesis falls within the scope of the TAMI project for Transparent Artificial Machine Intelligence and focuses on explainable artificial intelligence (XAI) for medical image data.

关键词： Machine learning Exploiting explanations image datasets Deep networks Fixed-weight methods

来源：评论

学校读者我要写书评

暂无评论

Improved Deep Learning Laryngeal Tumour Identification

Improved Deep Learning Laryngeal Tumour Identification

引用

2023 International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2023

作者： Hussain, Mohammad Shahnawaz Malathi, H. Savita Presidency University Department of Electronics and Communication Engineering Karnataka India School of Sciences Department of Life Sciences Karnataka India Maharishi University of Information Technology Maharishi School of Engineering & Technology Uttar Pradesh India

ISBN: (纸本)9798350344387

Laryngeal cancer incidence has significantly increased recently all over the globe. There are several difficulties in correctly diagnosing and treating laryngeal cancer, especially when it is advanced. This kind of cancer affects patients' head and neck areas and is a complicated malignancy. Researchers have created a number of diagnostic techniques and instruments throughout time to help clinical specialists accurately diagnose laryngeal cancer. However, these currently available techniques and methods show a number of performance-related drawbacks, including reduced early-stage laryngeal cancer detection accuracy, increased computational complexity, and extended patient screening periods. Furthermore, our suggested methodology greatly accelerates the real-time screening of patients by successfully catching and recognizing even small laryngeal cancers. The time saved by the professionals due to this efficiency allows them to screen more patients each day. When tested utilizing the imageNet dataset, the outcomes of our suggested model are more accurate and useful, boasting a rate. Numerous research on laryngeal cancer detection have been conducted recently, each using a different methodology. Future research has a lot of chances to investigate innovative methods for detecting laryngeal cancer by using varied and substantial medical picture databases. © 2023 IEEE.

关键词： CNN architecture CT images Deep learning Diagnostic techniques Early detection image datasets Laryngeal cancer Mask R-CNN Patient screening Radiomic analysis Real-time diagnosis

来源：评论

学校读者我要写书评

暂无评论

GPR1200: A Benchmark for General-Purpose Content-Based image Retrieval 28th

GPR1200: A Benchmark for General-Purpose Content-Based Image...

引用

28th International Conference on MultiMedia Modeling (MMM)

作者： Schall, Konstantin Barthel, Kai Uwe Hezel, Nico Jung, Klaus Univ Appl Sci HTW Berlin Visual Comp Grp Wilhelminenhofstr 75 D-12459 Berlin Germany

ISBN: (纸本)9783030983581;9783030983574

Even though it has extensively been shown that retrieval specific training of deep neural networks is beneficial for nearest neighbor image search quality, most of these models are trained and tested in the domain of landmarks images. However, some applications use images from various other domains and therefore need a network with good generalization properties - a general-purpose CBIR model. To the best of our knowledge, no testing protocol has so far been introduced to benchmark models with respect to general image retrieval quality. After analyzing popular image retrieval test sets we decided to manually curate GPR1200, an easy to use and accessible but challenging benchmark dataset with a broad range of image categories. This benchmark is subsequently used to evaluate various pretrained models of different architectures on their generalization qualities. We show that large-scale pretraining significantly improves retrieval performance and present experiments on how to further increase these properties by appropriate fine-tuning. With these promising results, we hope to increase interest in the research topic of general-purpose CBIR.

关键词： Content-based image retrieval image descriptors Feature extraction Generalization Retrieval benchmark image datasets

来源：评论

学校读者我要写书评

暂无评论

When Robots Dream: In Conversation with Alexandra Carlson

引用

ARCHITECTURAL DESIGN 2022年第3期92卷 46-53页

作者： del Campo, Matias Carlson, Alexandra Univ Michigan Architecture & Artificial Intelligence Lab AR2IL Robot Dept Ann Arbor MI USA Taubman Coll Architecture & Urban Planning Ann Arbor MI USA

Matias del Campo interviews Alexandra Carlson who had a key role in founding the pioneering Architecture and Artificial Intelligence Laboratory (AR2IL) at the University of Michigan's Robotics Department and Taubman College of Architecture and Urban Planning. The synthesis of the architectural and dataset sharing adds another dimension to design possibilities.

关键词： University of Michigan Architecture and Artificial Intelligence Laboratory (AR2IL) artificial neural networks (ANNs) generative adversarial networks (GANs) convolutional neural networks (CNNs) Deep neural networks (DNNs) image datasets SPAN Matias del Campo Sandra Manninger Robot Garden Ford Motor Company Robotics Building biological neural networks (BNNs) dendrites AR(2)IL data sharing

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：