搜索资源列表
xianquchuchengxu
- 表单图像线去除的程序,研究了一种直线检测和字线分离的算法.采用了一种检测直线的方法,即有向单单连通链法,它定义简单,物理意义明确,易于存储和处理.且能较好处理倾斜,断裂和字线交叠的情况,且通过将游程平滑,将尺寸小的单连通链滤除,并减少连通链合并时的搜索范围,可达到算法的加速,使结果更加精确.研究了字线相交的不同情况,采用了与框线检测结合的表格框线去除和交叠文字保留的方法,以及对字线分离后的笔画部分的修整.国内做这方面东西的人都很少,资料很少 -form images line removal
HHHarrisCorner
- 加速版的CORNER检测,用于灰度图象的角点特征提取。-accelerated version of the Corner detection for the gray-scale image feature extraction corner.
BP网络
- 这是我参考了n(n>=5,^_^)篇BP神经网优化方法的论文写出的BP神经网源代码,使用了批处理训练方法,带动量项、学习速率的自适应调整、仅对学习精度没有达到指定要求的模式训练,并且训练精度逐步加大,通过这种方法,极大地加快了训练速度;另外,对于0模式和1模式数目相差很大(5-6倍)都能达到很高的学习精度。-This is my reference to the n (NGT; Chapter 5 = ,^_^) BP neural network optimization method
libcvd-20090828.tar
- libCVD is a very portable and high performance C++ library for computer vision, image, and video processing. The emphasis on providing simple and efficient image and video handling and high quality implementations of common low-level image processing
AGAST-corner-detector
- 多尺度快速角点检测算法(FAST).Adaptive and generic corner detection based on the accelerated segment test. Computer Vision–ECCV 2010-Multi-scale fast corner detection algorithm (FAST) Adaptive and generic corner detection based on the accelerated segment test
CUDA-CNN-master
- CNN cuda的加速。 start-of-art结果的流行的数据集 1。测试mnist并获得99.76 ,投票后(99.82 )(最好的99.79 ) 2。测试cifar-10并获得81.42 最好(90 ) 3。测试cifar - 100和51.13 (最好的65 )-CNN accelerated by cuda. The start-of-art result s of popular datasets 1. Test on mnist and get 99.76