zifushibie

所属分类:图形图像处理
开发工具:matlab
文件大小:821KB
下载次数:17
上传日期:2008-11-29 13:49:50
上 传 者linlinfly1108
说明:  有数字1和2的图片各四十张,利用mat lab读取图片并将其二值化,得到只由0和1表示的矩阵,根据数字的不同特征,选择两个特征值,用来对分类器进行训练,最后用剩下的5个1和5个2来进行测试,看分类器是否可以正确的对数据进行分类。
(Figures 1 and 2 pictures of the 40, using mat lab picture and secondly, the value of reading, and received only by 0 and 1, said matrix, according to the number of different features, select the two characteristic values, used to classifier training, and finally with the remaining 5 1 and 5 2 to carry out tests to see whether the classifier can correctly classify the data.)

文件列表:
moshishibie--12.doc (77824, 2008-11-29)
字符识别\0\0005.BMP (1798, 1999-10-28)
字符识别\0\0014.BMP (1798, 1999-10-28)
字符识别\0\0019.BMP (1798, 1999-10-28)
字符识别\0\0020.BMP (1798, 1999-10-28)
字符识别\0\0026.BMP (1798, 1999-10-28)
字符识别\0\0027.BMP (1798, 1999-10-28)
字符识别\0\0033.BMP (1798, 1999-10-28)
字符识别\0\0040.BMP (1798, 1999-10-28)
字符识别\0\0054.BMP (1798, 1999-10-28)
字符识别\0\0055.BMP (1798, 1999-10-28)
字符识别\0\0056.BMP (1798, 1999-10-28)
字符识别\0\0061.BMP (1798, 1999-10-28)
字符识别\0\0062.BMP (1798, 1999-10-28)
字符识别\0\0063.BMP (1798, 1999-10-28)
字符识别\0\0070.BMP (1798, 1999-10-28)
字符识别\0\0090.BMP (1798, 1999-10-28)
字符识别\0\0110.BMP (1798, 1999-10-28)
字符识别\0\0145.BMP (1798, 1999-10-28)
字符识别\0\0148.BMP (1798, 1999-10-28)
字符识别\0\0152.BMP (1798, 1999-10-28)
字符识别\0\0155.BMP (1798, 1999-10-28)
字符识别\0\0166.BMP (1798, 1999-10-28)
字符识别\0\0181.BMP (1798, 1999-10-28)
字符识别\0\0188.BMP (1798, 1999-10-28)
字符识别\0\0210.BMP (1798, 1999-10-28)
字符识别\0\0217.BMP (1798, 1999-10-28)
字符识别\0\0220.BMP (1798, 1999-10-28)
字符识别\0\0224.BMP (1798, 1999-10-28)
字符识别\0\0231.BMP (1798, 1999-10-28)
字符识别\0\0234.BMP (1798, 1999-10-28)
字符识别\0\0241.BMP (1798, 1999-10-28)
字符识别\0\0252.BMP (1798, 1999-10-28)
字符识别\0\0259.BMP (1798, 1999-10-28)
字符识别\0\0298.BMP (1798, 1999-10-28)
字符识别\0\0301.BMP (1798, 1999-10-28)
字符识别\0\0305.BMP (1798, 1999-10-28)
字符识别\0\0308.BMP (1798, 1999-10-28)
字符识别\0\0319.BMP (1798, 1999-10-28)
... ...

模式识别大实验:字符识别 ================================================================== 实验的关键有两点:提取特征和分类器设计。方法力求新颖。分类器应具有一定的 拒识能力。 目录名 内容 用途 ---------------------------------------------------- Template 标准字符模板 作训练样本集 单字符目录 各种字符样本 作测试样本或训练样本 mass 噪声 检测拒识能力

近期下载者

相关文件


收藏者