当前位置：
首页 资源下载
搜索资源 - image classification using neural network
搜索资源列表
-
0下载：
关于rbf神经网络实现图像分类的IEEE英文文献 和大家一起分享-Image Classification using a Module RBF Neural Network
-
-
0下载：
Semantic analysis of multimedia content is an on going research
area that has gained a lot of attention over the last few years.
Additionally, machine learning techniques are widely used for multimedia
analysis with great success. This work pre
-
-
0下载：
High information redundancy and correlation in face images result in efficiencies when such images are used directly for recognition. In this paper, discrete cosine transforms are used to reduce image information redundancy because only a subset of t
-
-
0下载：
Wavelet transforms are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. We demonstrate experimentally th
-
-
1下载：
神经网络源码，可应用于遥感图像的分类，采用的包括bp、kohonen。可以作为范例来学习。-Neural network source code can be used in remote sensing image classification, using the included bp, kohonen. Can serve as examples to learn.
-
-
0下载：
用Matlab编写的神经元网络程序，可对图像进行分类。程序用到了4种神经元方法，BP效果最好。-Neural network using Matlab program, the image classification. The program used four kinds neurons BP effect.
-
-
0下载：
基于matlab神经网络的遥感图像分类，使用了BP神经网络-Matlab neural network-based remote sensing image classification using BP neural network
-
-
0下载：
二维图像的读取，辨认，分析，并且用神经网络进行，判定哪些图片可以归为一类-Two-dimensional image reading, identifying, analyzing, and using neural network to determine which pictures can be classified as a class
-
-
0下载：
Image classification using Backpropragation Neural Network with data training set and data testing
-
-
0下载：
This a sample of a simple image classification using K-Nearest Neighbor and Backpropagation Neural Network. It uses block averaging in feature extraction process.-This is a sample of a simple image classification using K-Nearest Neighbor and Backprop
-
-
0下载：
为实现合格和缺陷板栗的分级， 研究了 1 种基于 BP 神经网络与板栗图像特征的板栗分级方法。 试验以罗田板
栗为研究对象， 提取的颜色及纹理等 8 个特征值， 通过主成分分析提取相应的主成分得分向量构成模式识别的输入。 利
用 BP 神经网络方法建立了板栗分级模型。 试验结果表明， 在图像信息主成分因子数为 3， 中间层节点数为 12 时， 建立
的模型最佳， 模型训练时的回判率为 100 ， 预测时识别率达到了 91 .67 。 研究结果表明基于机器视觉技术的针对缺陷
板栗分
-
-
0下载：
采用卷积神经网络在cifar-10图像库上进行的分类训练。效果非常好。-Convolution using trained neural network classification on cifar-10' s image library. The effect is very good.
-
-
2下载：
神经网络引入后，检测框架变得更快更准确。然而，大多数检测方法受限于少量物体。检测和训练数据上联合训练物体检测器，用有标签的检测图像来学习精确定位，同时用分类图像来增加词汇和鲁棒性。原YOLO系统上生成YOLOv2检测器；在ImageNet中超过9000类的数据和COCO的检测数据上，合并数据集和联合训练YOLO9-After the neural network is introduced, it is becoming faster and more accurate detection fr
-
-
1下载：
图片情感分析模型，基于卷积神经网络，以颜色特征为依据进行情感分类，图片情感极性分为积极和消极两类。(The model can extract the hue, brightness, contrast and other information from a picture to represent the emotional polarity of the image. The image sentiment analysis model is using convolution neura
-
-
1下载：
在CIFAR-10数据集上使用卷积神经网络进行图像分类(Image classification using convolution neural network on CIFAR-10 dataset)
-
-
1下载：
利用深度学习进行遥感图像场景分类
这里我们对NWPU-RESISC45数据集的场景图像进行分类
我们将卷积神经网络应用于图像分类。我们从头开始训练数据集。此外，还应用了预先训练的VGG16 abd ResNet50进行迁移学习。(Scene Classification of Remote Sensing Images Using Deep Learning
Here we classify scene images from NWPU-RESISC45 dataset
We apply
-
-
1下载：
以python语言为基础，利用tensorflow机器学习架构，两层卷积神经网络实现，CiFar数据集图片分类功能。(Based on Python language, using tensorflow machine learning architecture, two-layer convolutional neural network, CiFar data set image classification function.)
-
-
1下载：
采用神经网络进行图像分类，分类方法简单，但是效果略差。(Using neural network for image classification, the classification method is simple, but the effect is slightly poor.)
-
