-
Edge-based-text-region-extraction-from-natural-im
The basic steps of the edge-based text extraction algorithm are given below
1. Create a Gaussian pyramid by convolving the input image with a Gaussian kernel
and successively down-sample each direction by half. (Levels: 4)
2. Create directional kernels to detect edges at 0, 45, 90 and 135 orientations.
3. Convolve each image in the Gaussian pyramid with each orientation filter.
4. Combine the results of step 3 to create the Feature Map.
5. Dilate the resultant image using a sufficiently large structuring element (7x7 [1])
to cluster candidate text regions together.
6. Create final output image with text in white pixels against a plain black
background.
- 2014-12-16 02:56:28下载
- 积分：1
-
CS_OMP
实现了正交匹配追踪算法的matlab编程(To achieve the orthogonal matching pursuit algorithm matlab programming)
- 2011-11-28 14:40:34下载
- 积分：1
-
GA_Test
利用GA算法实现软件测试的测试用例选取，对参数估计进行GA估计(GA algorithm using software testing test cases selected, the parameter estimate is estimated GA)
- 2009-01-07 15:52:58下载
- 积分：1
-
ebpsk-and-cp-ebpsk
高效调制信号ebpsk和cp-ebpsk，以及功率谱特征。(ebpsk and cp-ebpsk)
- 2014-08-08 22:10:15下载
- 积分：1
-
v2
说明： 长春应用化学研究所，嵌段共聚物，高分子，物理学(Changchun Institute of Applied Chemistry，Block copolymers，Macromolecule，physics)
- 2013-12-15 21:40:37下载
- 积分：1
-
SWcomplex
生成小世界网络的Matlab程序，比较好，很多人都在用这个(Generate small-world network Matlab program, better, a lot of people are using this)
- 2010-11-26 20:07:02下载
- 积分：1
-
KL-face-recgonition
基于KL的人脸识别算法,matlab版本(face recognition based on KL)
- 2014-11-17 10:30:39下载
- 积分：1
-
pcnn
利用pcnn，每当有一批像素对应的神经元点火，对像素值进行一次修正。第n次点火的所有神经元用矩阵B（n）表示，
已经点火的像素位置标记为‘1’，未点火的标记为‘0’。通过一个3*3的模板滑过B（n），判断若模板内的值全为‘1’或全为‘0’，
则这些像素值不进行处理，否则若模板中心的值为‘1’，则增加该位置的像素值的大小，中心值为‘0’，则减小像素值。该功能由xiugai(B,K)函数实现
Beta取负值来抑制周围的神经元点火，因为输入pcnn（X）的是模糊图像，抑制之后使处理的像素值更加接近原图像的像素值（抑制参数通过试验确定，并不精确）
总之运行结果只是对像素值变化较大的边缘区域进行了像素值的修正。
通过不断调整参数使峰值信噪比有所升高，但是升高得不是太多(Use pcnn, whenever a group of pixels corresponding to the firing of neurons, a correction value for the pixel. Ignition of all the n-th neuron matrix B (n) represents,
Already ignition pixel position labeled 1 , unfired labeled 0 . By a 3* 3 templates over the B (n), determines if the value within the template are all 1 or all 0 ,
These pixel values are not processed, otherwise the value if the template center 1 , then the increase in the size of the pixel values of the position, the center value of 0 , the pixel value is reduced. This function is implemented by xiugai (B, K) function
Beta is a negative value around the element to inhibit neuronal firing, because the input pcnn (X) is a blurred image, the pixel values of inhibition after treatment of the pixel value closer to an original image (suppression parameter determined by experiment, is not exact)
Results only in short run large changes in the edge region of the pixel values of the corrected pixel values.
)
- 2014-12-01 09:16:42下载
- 积分：1
-
SVM
SVM的SMO算法实现，svm_train为训练函数，svm_predict为预测函数，按说明输入参数即可(The SMO SVM algorithm, svm_train of the training function, svm_predict to predict function, follow the instructions to input parameters)
- 2014-05-07 09:38:10下载
- 积分：1
-
TM_nonpml_one_gap
Tm波，单峰衍射，无边界条件，适合初学者(Tm wave, single-peak diffraction, no boundary conditions, suitable for beginners)
- 2010-12-01 16:43:41下载
- 积分：1
