Classification of Glaucoma in Retinal Images Using EfficientnetB4 Deep Learning Model

Today, many eye diseases jeopardize our everyday lives, such as Diabetic Retinopathy (DR), Age-related Macular Degeneration (AMD), and Glaucoma. Glaucoma is an incurable and unavoidable eye disease that damages the vision of optic nerves and quality of life. Classification of Glaucoma has been an active field of research for the past ten years. Several approaches for Glaucoma classification are established, beginning with conventional segmentation methods and feature-extraction to deep-learning techniques such as Convolution Neural Networks (CNN). In contrast, CNN classifies the input images directly using tuned parameters of convolution and pooling layers by extracting features. But, the volume of training datasets determines the performance of the CNN; the model trained with small datasets, overfit issues arise. CNN has therefore developed with transfer learning. The primary aim of this study is to explore the potential of EfficientNet with transfer learning for the classification of Glaucoma. The performance of the current work compares with other models, namely VGG16, InceptionV3, and Xception using public datasets such as RIM-ONEV2 & V3, ORIGA, DRISHTI-GS1, HRF, and ACRIMA. The dataset has split into training, validation, and testing with the ratio of 70:15:15. The assessment of the test dataset shows that the pre-trained EfficientNetB4 has achieved the highest performance value compared to other models listed above. The proposed method achieved 99.38% accuracy and also better results for other metrics, such as sensitivity, specificity, precision, F1_score, Kappa score, and Area Under Curve (AUC) compared to other models.     

利用迁移学习和焦点损失卷积神经网络的石墨分类

为了使得优质石墨资源得到优质优用, 提出利用迁移学习和焦点损失卷积神经网络的石墨分类识别算法.在自建的初始数据集基础上, 通过对数据集的离线扩充与在线增强, 有效扩大数据集并减低深层CNN过拟合的风险. 以VGG16、ResNet34和MobileNet V2为基础模型, 重新设计新的输出模块载入全连接层, 提高了模型...     

Classification and Diagnosis of Lymphoma’s Histopathological Images Using Transfer Learning

Current cancer diagnosis procedure requires expert knowledge and is time-consuming, which raises the need to build an accurate diagnosis support system for lymphoma identification and classification. Many studies have shown promising results using Machine Learning and, recently, Deep Learning to detect malignancy in cancer cells. However, the diversity and complexity of the morphological structure of lymphoma make it a challenging classification problem. In literature, many attempts were made to classify up to four simple types of lymphoma. This paper presents an approach using a reliable model capable of diagnosing seven different categories of rare and aggressive lymphoma. These Lymphoma types are Classical Hodgkin Lymphoma, Nodular Lymphoma Predominant, Burkitt Lymphoma, Follicular Lymphoma, Mantle Lymphoma, Large B-Cell Lymphoma, and T-Cell Lymphoma. Our proposed approach uses Residual Neural Networks, ResNet50, with a Transfer Learning for lymphoma’s detection and classification. The model used results are validated according to the performance evaluation metrics: Accuracy, precision, recall, F-score, and kappa score for the seven multi-classes. Our algorithms are tested, and the results are validated on 323 images of 224 × 224 pixels resolution. The results are promising and show that our used model can classify and predict the correct lymphoma subtype with an accuracy of 91.6%.     

基于迁移学习的人脸姿态分类方法

人脸姿态分类在智能人机交互、虚拟现实、智能控制以及人脸识别等多个领域都有广泛的应用。由于人脸姿态分类过程中存在不同角度间特征重叠率高的问题,导致其分类精度过低。为提高人脸姿态分类的准确率与鲁棒性,提出了基于迁移学习的人脸姿态分类方法。该方法利用卷积神经网络的特征提取和学习能力,对特征进行识别和分类,从而得到单方向人脸姿态的训练参数。利用迁移学习,将卷积神经网络训练好的参数应用于训练两个方向的人脸姿态模型中。使用该方法在CAS-PEAL数据集上进行了实验,最终结果的准确率达到98. 7%,并且与AlexNet、VGGNet和ResNet等网络模型做对比实验,得到了更好的人脸姿态分类效果。实验结果表明,所提出的方法显著提高了人脸姿态分类的准确率与鲁棒性。     

深度学习模型GoogleNet-PNN对肝硬化的识别

针对传统机器学习人工提取特征耗时耗力,并且提取高质量特征存在一定困难等问题,将基于深度学习的方法,首次结合卷积神经网络和概率神经网络,提出了一种新的模型GoogleNet-PNN,其自动学习特征,避免了手动提取特征的繁琐性,而且结合了PNN训练容易、收敛速度快等特点,在肝病分类的实验中取得了较好的效果;并使用了迁移学习的方法,通过在自然图像集的预训练,然后应用到医学图像,避免了因样本不足而出现的过拟合问题,实验结果最终表明识别准确率要优于其他方法,达到了98%的客观识别率。     

基于深度学习和迁移学习的水果图像分类

图像识别作为深度学习领域内的一项重要应用,水果图像的分类识别在智慧农业以及采摘机器人等方面具有重要应用。针对以往传统图像分类算法存在泛化能力差、准确率不高等问题,提出一种在TensorFlow框架下基于深度学习和迁移学习的水果图像分类算法。该算法采用Inception-V3的部分模型结构对水果图像数据进行特征提取,采用Softmax分类器对图像特征进行分类,并通过迁移学习方式进行训练得到迁移训练模型。测试结果表明,该算法与传统水果分类算法对比,具有较高识别准确率。     

联合集成学习与EfficientNet的光学遥感图像场景分类

深度学习能够提高光学遥感图像场景分类的准确率和效率,但光学遥感图像语义丰富,部分场景仍存在易误分类的情况,同时由网络模型规模扩大带来的硬件要求过高、时间成本消耗过大等问题制约着深度学习网络模型的推广应用.为此,提出一种基于轻量化网络模型的光学遥感图像场景分类方法.通过EfficientNet网络提取图像特征,对图像特征...     

面向三维模型多样化分类的深度集成学习

基于深度学习的三维模型分类方法大都面向特定的具体任务,在面向三维模型多样化分类任务时表现不佳,泛用性不足。为此,提出了一种通用的端到端的深度集成学习模型E2E-DEL(end-to-end deep ensemble learning),由多个初级学习器和一个集成学习器组成,可以自动学习复杂三维模型的复合特征信息;并使用层次迭代式学习策略,综合考量不同层次网络的特征学习能力,合理平衡各个初级学习器的子特征学习和集成学习器的集成特征学习效果,自适应于三维模型多样化分类任务。基于此,设计了一种面向多视图的深度集成学习网络MV-DEL(multi-view deep ensemble learning),应用于一般性、细粒度、零样本三种不同类型的三维模型分类任务中。在多个公开数据集上的实验验证了该方法具有良好的泛化性与普适性。     

基于深度神经网络的遥感图像分类算法综述

准确、高效的遥感图像分类是遥感图像解析的重要研究内容之一。近年来,随着机器学习技术的发展,深度神经网络日渐成为一种有效的遥感图像分类处理方法。分析了遥感图像分类目前存在的一些问题,并简要阐述了几种典型的深度神经网络的原理结构;然后根据遥感图像分类的研究现状和深度神经网络对遥感图像分类的研究现状,总结了深度神经网络在遥感图像分类技术应用中的发展趋势。     

Breast Mammogram Analysis and Classification Using Deep Convolution Neural Network

One of the fast-growing disease affecting women’s health seriously is breast cancer. It is highly essential to identify and detect breast cancer in the earlier stage. This paper used a novel advanced methodology than machine learning algorithms such as Deep learning algorithms to classify breast cancer accurately. Deep learning algorithms are fully automatic in learning, extracting, and classifying the features and are highly suitable for any image, from natural to medical images. Existing methods focused on using various conventional and machine learning methods for processing natural and medical images. It is inadequate for the image where the coarse structure matters most. Most of the input images are downscaled, where it is impossible to fetch all the hidden details to reach accuracy in classification. Whereas deep learning algorithms are high efficiency, fully automatic, have more learning capability using more hidden layers, fetch as much as possible hidden information from the input images, and provide an accurate prediction. Hence this paper uses AlexNet from a deep convolution neural network for classifying breast cancer in mammogram images. The performance of the proposed convolution network structure is evaluated by comparing it with the existing algorithms.     

一种迁移学习和可变形卷积深度学习的蝴蝶检测算法

针对自然生态蝴蝶多种特征检测的实际需求,以及生态环境下蝴蝶检测效率低、精度差问题,本文提出了一种基于迁移学习和可变形卷积深度神经网络的蝴蝶检测算法（Transfer learning and deformable convolution deep learning network,TDDNET）.该算法首先使用可变形卷积模型重建ResNet-101卷积层,强化特征提取网络对蝴蝶特征的学习,并以此结合区域建议网络（Region proposal network,RPN）构建二分类蝴蝶检测网络,以下简称DNET-base;然后在DNET-base的模型上,构建RPN网络来指导可变形的敏感位置兴趣区域池化层,以便获得多尺度目标的评分特征图和更准确的位置,再由弱化非极大值抑制（Soft non-maximum suppression,Soft-NMS）精准分类形成TDDNET模型.随后通过模型迁移,将DNET-base训练参数迁移至TDDNET,有效降低数据分布不均造成的训练困难与检测性能差的影响,再由Fine-tuning方式快速训练TDDNET多分类网络,最终实现了对蝴蝶的精确检测.所提算法在854张蝴蝶测试集上对蝴蝶检测结果的mAP0.5为0.9414、mAP0.7为0.9235、检出率DR为0.9082以及分类准确率ACC为0.9370,均高于在同等硬件配置环境下的对比算法.对比实验表明,所提算法对生态照蝴蝶可实现较高精度的检测.     

一个新的在线学习文档分类模型

为了对在线学习文档进行分类,本文根据自适应谐振理论给出了一个半监督学习模糊ART模型(SLFART)及其算法.该算法不仅克服一般半监督学习算法中假设已知数据概率分布的条件,而且还具有非常强的学习新模式和纠正错误的能力.实验结果表明SLFART性能明显优于其它算法.     

基于半监督编码生成对抗网络的图像分类模型

在实际应用中, 为分类模型提供大量的人工标签越来越困难, 因此, 近几年基于半监督的图像分类问题获得了越来越多的关注.而大量实验表明, 在生成对抗网络(Generative adversarial network, GANs)的训练过程中, 引入少量的标签数据能获得更好的分类效果, 但在该类模型的框架中并没有考虑用于提取图像特征的结构, 为了进一步利用其模型的学习能力, 本文提出一种新的半监督分类模型.该模型在原生成对抗网络模型中添加了一个编码器结构, 用于直接提取图像特征, 并构造了一种新的半监督训练方式, 获得了突出的分类效果.本模型分别在标准的手写体识别数据库MNIST、街牌号数据库SVHN和自然图像数据库CIFAR-10上完成了数值实验, 并与其他半监督模型进行了对比, 结果表明本文所提模型在使用少量带标数据情况下得到了更高的分类精度.     

Automatic Classification of Biological Particles from Electron-microscopy Images Using Conventional and Genetic-algorithm Optimized Learning Vector Quantization

Automatic classification of transmission electron-microscopy images is an important step in the complex task of determining the structure of biologial macromolecules. The process of 3D reconstruction from a set of such images implies their previous classification into homogeneous image classes. In general, different classes may represent either distinct biochemical specimens or specimens from different directions of an otherwise homogenous specimen. In this paper, a neural network classification algorithm has been applied to a real-data case in which it was known a priori the existence of two differentiated views of the same specimen. Using two labeled sets as a reference, the parameters and architecture of the classifier were optimized using a genetic algorithm. The global automatic process of training and optimization is implemented using the previously described g-lvq (genetic learning vector quantization) [10] algorithm, and compared to a non-optimized version of the algorithm, Kohonen's lvq (learning vector quantization) [7]. Using a part of the sample as training set, the results presented here show an efficient (approximately 90%) average classification rate of unknown samples in two classes. Finally, the implication of this kind of automatic classification of algorithms in the determination of three dimensional structure of biological particles is discused. This paper extends the results already presented in [11], and also improves them.     

面向图像分类的残差网络进展研究

近年来,随着数据量的扩大,计算机性能不断提升,用传统的图像分类方法无法获得大数据下图像分类的高精度准确率,残差网络因其高度准确性和良好收敛性已成为图像分类领域的技术热点,值得深入研究。介绍了残差网络,并从提升分类准确率、减少模型参数量和降低模型计算量三个角度出发,详细讨论了各个变体的内在结构,分析了各个变体的优缺点,给出了各个变体适用场合的建议。从准确率、参数量和计算量三个方面对各个变体的性能进行了直观的对比。提出了残差网络现在面临的挑战和未来的发展方向。     

基于迁移学习的机器人视觉识别与分拣策略

针对传统工业机器人辨识复杂工件困难、识别度单一等问题，提出一种基于迁移学习的视觉识别与分拣策略。高精度工业相机拍摄到的图片经过HALCON软件图像膨胀、腐蚀等处理之后，导入Pytorch中的神经网络模型，利用迁移学习对目标进行识别分类，最终实现工业机器人智能分拣的目的。实验中，在UR5机器人平台上以形状多变的两种菇类为对象进行迁移学习，进而完成识别及分拣。实验结果表明该策略具备良好的准确性和稳定性。     

基于改进VGG-16神经网络的图像分类方法

为提高图像分类模型的准确度,提出了一种迁移学习VGG-16并对其进行改进的图像分类方法,即NewVGG-16模型.首先从ImageNet数据集中选取十种不同类型的部分图像数据,进行去噪、标准化等预处理;接着迁移学习VGG-16模型同时将其改进,模型的优化包括改进池化层为sort_pool2d,在每个卷积层后面添加BN层以增强规范性,并选用Adaboost分类器提升整体的分类性能.通过训练集实现模型参数的调整,用测试集检验其准确性.实验证明,该模型能有效提升图像分类的准确性和适用性,准确度可达到98.75％.     

一种基于直推判别字典学习的零样本分类方法

零样本分类的目标是对训练阶段未出现过的类别的样本进行识别和分类,其主要思路是,借助类别语义信息,将可见类别的知识转移到未见类别中.提出了一种直推式的字典学习方法,包含以下两个步骤：首先,提出一个判别字典学习模型,对带标签的可见类别样本的视觉特征和类别语义特征建立映射关系模型;然后,针对可见类别和未见类别不同引起的域偏移问题,提出了一个基于直推学习的修正模型.通过在3个基准数据集（AwA,CUB和SUN）上的实验结果,证明了该方法的有效性和先进性.     

Intelligent Beetle Antenna Search with Deep Transfer Learning Enabled Medical Image Classification Model

Recently, computer assisted diagnosis (CAD) model creation hasbecome more dependent on medical picture categorization. It is often usedto identify several conditions, including brain disorders, diabetic retinopathy,and skin cancer. Most traditional CAD methods relied on textures, colours,and forms. Because many models are issue-oriented, they need a more substantial capacity to generalize and cannot capture high-level problem domainnotions. Recent deep learning (DL) models have been published, providinga practical way to develop models specifically for classifying input medicalpictures. This paper offers an intelligent beetle antenna search (IBAS-DTL)method for classifying medical images facilitated by deep transfer learning.The IBAS-DTL model aims to recognize and classify medical pictures intovarious groups. In order to segment medical pictures, the current IBASDTLM model first develops an entropy based weighting and first-ordercumulative moment (EWFCM) approach. Additionally, the DenseNet-121technique was used as a module for extracting features. A BAS with an extremelearning machine (ELM) model is used to classify the medical photos. A widevariety of tests were carried out using a benchmark medical imaging datasetto demonstrate the IBAS-DTL model’s noteworthy performance. The resultsgained indicated the IBAS-DTL model’s superiority over its pre-existingtechniques.     

并行学习神经网络集成方法

该文分析了神经网络集成中成员神经网络的泛化误差、成员神经网络之间的差异度对神经网络集成泛化误差的影响,提出了一种并行学习神经网络集成方法;对参与集成的成员神经网络,给出了一种并行训练方法,不仅满足了成员网络本身的精度要求,还满足了它与其余成员网络的差异性要求;另外,给出了一种并行确定集成成员神经网络权重方法．实验结果表明,使用该文的成员神经网络训练方法、成员神经网络集成方法能够构建有效的神经网络集成系统．