资源列表
TestCopybookDetect
- 基于深度学习的手写体汉字识别,所用框架为Mxnet框架-Handwritten Chinese character recognition
HyperLPR-master
- 车牌定位源程序代码,效果还是很不错的,希望大家喜欢-LICENSE PLATE LOCATE
reg
- 对于乒乓球目标的识别,采用matlab完成,比较简单,不过可以使用- U5BF9 u4E8E u4E52 u4E53 u7403 u76EE u6807 u7684 u8BC6 u522B uFF0C u91C7 u7528matlab u5B8C u6210 uFF0C u6BD4 u8F83 u7B80 u5355 uFF0C u4E0D u8FC7 u53EF u4EE5 u4F7F u7528
wbntrs
- 用ORL人脸库进行测试,给出一幅图片可以指出他是40个人中的哪一个人的第几个人脸,这些要以界面的形式显示出来并配以文字说明(文字说明就是哪一个人的第几个人脸),测试用的图片在一个文件夹中,我可以通过界面选择要测试该文件夹中的哪个图片,选定之后程序可以显示出对应这个图片的相应的ORL中的人脸并显示这是第几个人的第几张脸,如果在人脸库中检测不到测试的图片(如测试的图片是一朵花什么的)的话也要有提示说这个图在ORL中不存在 -Using the ORL face to test, give a pi
distinguish_test_2010
- hu矩识别,将hu矩应用在识别方面,将数字和字母的hu矩算出来,再跟模版对比-Hu moment recognition, hu moments will be used in recognition, the numbers and letters of the hu moment calculated, then compared with the template
train
- 字符库,包含大小写英文字符和阿拉伯数字,每类字符包含1000余张图片,可用于字符识别-Character library, including case English letters and Arabic numerals, each character consists of more than 1000 pictures, can be used for character recognition
zifushibie
- 可以简单地完成字符识别,并且对输入的汉字可以在原文中找到并加下划线,适合学生使用 -You can simply complete the character recognition, and the input of Chinese characters can be found in the original and underlined, suitable for students to use
shap
- 一个识别圆,矩形,三角形等形状的MATLAB程序,有不足之处可以相互联系,取长补短。-An identification of circle, rectangle, triangle shape such as MATLAB, have shortcomings can connect with each other, complement each other.
chapter29
- 《MATLAB 神经网络个案例分析》,可以实现对图像进行分割,去噪,识别和分类。-" MATLAB neural network 43 case studies" can be achieved on image segmentation, de-noising, identification and classification.
similaritymeasure
- 在对图像进行识别和分类过程中,相似性测量可以作为一种判别策略,目的是刻画图像之间的本质特性。-In the image recognition and classification process, the similarity measure can be used as a discriminating strategy aimed portray the essential characteristics of images.
53607888mnistclassify_DBN
- 目前深度学习已经得到研究者的广泛关注,在这里深信度网络被用于手写字符的识别,得到非常好的分类精度。-Currently deep learning has been much attention, here we are convinced of the network is used to identify handwritten characters, get very good classification accuracy.
CNN-pooling-strategy
- 基于卷积层和池化层的卷积深度网络被执行,该框架可以有效地识别灰度图像,彩色图像和高光谱图像。- Convolution deep network based on convolution layer and pooling layer is performed, the framework can effectively identify grayscale images, color images and hyperspectral images.
