-
barcode
基于图像的条形码识别程序（识别EAN13码），只要条形码的背景部分是纯色，程序就能有相当强的鲁棒性。(Image-based bar code recognition program (recognize EAN13 code), as long as the background of the bar code is solid, the program can be quite strongly robust.)
- 2010-01-23 02:13:23下载
- 积分：1
-
vtk
有关vtk的一些pdf资料，包括：
1.和国外一些朋友讨论VTK的一些经验的整理
2.基于VTK的医学三维可视化分析系统
3.基于VTK库的医学图像处理子系统设计和实现
4.可视化工具VTK技术研究(Some of the vtk pdf information, including: 1. And some foreign friends to discuss some of the experiences of the order VTK 2. VTK-based visualization of the medical system 3. VTK library based on medical image processing subsystem design and implementation 4. visualization tools VTK Technology)
- 2008-07-30 23:26:39下载
- 积分：1
-
sin-and-nml
正余弦+NLM滤波器和正余弦与其他滤波器的视觉效果与数值信息比较(Sine and Cosine+NLM cosine filter and compare numeric information with visual effects and other filters)
- 2020-11-26 16:39:31下载
- 积分：1
-
cavi
图像着色处理，对于不同亮度的图像显示不同颜色，应用于水下声纳图像效果比较好。(Image color processing, to the image shows different colors of different brightness, applied to the underwater sonar image effect is better.
)
- 2021-04-16 14:58:53下载
- 积分：1
-
underwater-image-enhance
新的水下图像对比度增强和分割算法（实现对比度的增强和图像分割，内容包括：新的水下图像对比度增强算法、水下图像的分割算法--2008a）(The new underwater image contrast enhancement and segmentation algorithm (implemented contrast enhancement and image segmentation, including: new underwater image contrast enhancement algorithms, underwater image segmentation algorithm- 2008a))
- 2013-12-28 11:00:20下载
- 积分：1
-
图像修复
说明： 应用DCT字典和KSVD学习字典，对图像进行简单的修复，可行性较高，速度不是很快。(Simple image restoration is feasible and not very fast.)
- 2020-06-28 20:00:01下载
- 积分：1
-
py-faster-rcnn-master
图像检测的算法，Faster R-CNN算法，先对整张图像进行卷积计算，然后通过感兴趣区域池化层(RoI Pooling Layer)将选择性搜索算法推荐出来的候选区域和卷积网络计算出的特征映射图进行融合，得到候选区域对应的特征矢量，这种共享卷积计算的操作极大地减少了卷积计算的次数。而且这些特征矢量的维度统一，方便后续的分类工作。通过感兴趣区域池化层处理卷积特征，并将得到的特征送往两个并行计算任务进行训练，分类和定位回归。通过这些方法和改进的框架，Fast R-CNN 用更短的训练和测试时长，取得了比 R-CNN 更好的效果(Faster R-CNN algorithm first convolutes the whole image, then fuses the candidate regions recommended by the selective search algorithm and the feature mapping maps calculated by the convolution network through the RoI Pooling Layer to get the corresponding feature vectors of the candidate regions, which greatly reduces the number of convolution calculations. Moreover, the dimension of these feature vectors is unified, which facilitates the subsequent classification work. The convolution feature is processed by the pooling layer of the region of interest, and the obtained feature is sent to two parallel computing tasks for training, classification and positioning regression. Through these methods and improved framework, Fast R-CNN uses shorter training and testing time and achieves better results than R-CNN.)
- 2020-12-11 15:39:18下载
- 积分：1
-
defogging_hekaiming
说明： 何凯明的暗通道去雾算法，Python版本代码(image defogging based on dark channel)
- 2020-03-31 16:42:23下载
- 积分：1
-
ACCV10
This is an implementation of a ACCV 2010 paper, Exploiting Self-Similarities for Single Frame Super-Resolution.
- 2010-11-24 03:22:38下载
- 积分：1
-
finally
实现了车辆目标的背景建模、前景检测、阴影消除、车辆跟踪(Achieve a vehicle target background modeling, foreground detection, shadow elimination, vehicle tracking)
- 2013-07-22 21:36:10下载
- 积分：1
