该课题为基于MATLAB的教室人数统计，带有丰富的人机交互GUI界面。实现教室人数的计数统计，进而统计出勤率，上课认真听讲的比例。原先预设总人数，未出勤或者书本遮住脸部、趴着玩手机等必然无法采集到人脸，从而对应数量缺失，得出出勤率或听讲率。该课题采用肤色原理进行人脸定位和人脸分割。本课题中，为了界面GUI的美观，刻意将分割出的人脸单独显示在GUI对应的axes里。是个不错的设计选题。
This topic is based on MATLAB classroom statistics, with rich human-computer interaction GUI interface. Realize the counting statistics of the number of students in the classroom, and then count the attendance rate and the proportion of listening carefully in class. The original preset total number of people, no attendance or books cover the face, prone to play mobile phones, etc. will not be able to collect the face, thus the corresponding number of missing, get attendance rate or listening rate. This project uses skin color principle to locate and segment face. In this project, for the sake of the beauty of GUI, the separated faces are displayed in axes corresponding to GUI. It's a good design topic. (2020-08-06, matlab, 587KB, 下载9次)
用遗传算法( Genetic Algorithm，GA) 搜寻可识别被不同农药污染脐橙的可见/近红外光谱的最佳特征光
谱区间及波长，并建立了支持向量机( Support Vector Machines，SVM) 定性分析模型。实验供试农药为灭多威、
氰戊菊酯和氧乐果3 种。通过GA 来搜寻整个波段范围( 460 ～ 1 800 nm) ，将得到的9 个最佳特征光谱区间所
包含的波长( 共318 个) 作为SVM 建模的输入变量，对识别被3 种农药污染脐橙的准确率为100 。并继续应
用GA 优化，得到71 个特征波长，此时建立的SVM 模型的识别准确率为99． 57 。虽然识别的准确率有所下降，但是模型的复杂程度得到了很大的优化，其输入变量减少到71 个。实验结果表明利用可见/近红外光谱技
术结合SVM 方法可以有效识别被不同农药污染的脐橙。
Genetic algorithm ( GA) was used to search for the best characteristic spectral ranges andwavelengths of visible /near － infrared spectra ( Vis /NIRs) ，a qualitative analysis model of support vector machine
( SVM) was set up to recognize navel oranges contaminated with different pesticides． The pesticides in
the experiment were Methomyl，fenvalerate and omethoate． Using GA to search the entire band range ( 460 ～1 800 nm) ，the 9 best characteristic spectral ranges ( 318 wavelengths) were used as the input variables of SVM model and the accuracy of the prediction set classification was 100 ． Then GA method was used continually
and 71 wavelengths were extracted，the corresponding SVM model was built with 99． 57 accuracy． Although
the classification accuracy rate declined，the complexity of the model was greatly optimized by reducing
the input variables to 71． The experiment results showed that the application of Vis /NIRs combined with SVM can effectively detect the navel oranges conta (2011-08-22, PDF, 215KB, 下载121次)
边缘检测1.制作一张包括色块、线条的单色背景图片，先对其作低通滤波产生一幅色块和线条边缘模糊的降质图片待处理，采用任意二种边缘检测算法检测待处理图片中的色块和线条的边缘，得到二值化的处理结果图。从结果图中提取色块和线条的边界坐标值，与实际生成原始图像时采用的真实坐标数据作比较，对产生的检测误差作分析。2.拍摄一张包含待检测物体的黑白或者彩色照片，试采用一种边缘检测的算法做待检测物体的自动提取，对生成的结果作分析。
Edge Detection 1. To produce a including blocks of color lines color the background picture, the first of its low-pass filter for a color blocks and lines produced lower quality images fuzzy edges to be processed, using any two edge detection algorithm to detect when processing in the image blocks of color and line the edge of the two values are the result of the treatment plan. Extracted from the results map the boundary blocks of color and line coordinates, the original image and the actual generated coordinate data used to compare the true, and on the detection of error for analysis. 2. Take a test to be included black and white or color photographs of objects, try using a edge detection algorithm on automatic extraction of objects to be detected, the results generated for analysis. (2010-06-02, matlab, 646KB, 下载101次)
提出了一种基于小波域的图像数字水印算法·该算法将相互正交的两种水印(鲁棒水印和参考
水印)同时添加到经过DWT后的载体图像小波系数中,然后用小波反变换得到添加了水印的图像·用提取出
的参考水印来估计图像所受到的攻击,由于提取出的鲁棒水印所受的攻击与参考水印受到的攻击一样,因此
可以估计出原始的鲁棒水印·通过对嵌入水印的图像进行加入噪声、滤波、压缩以及裁剪等大量图像处理等试
验,均能正确检测出水印,表明该算法具有很好的感知效果和鲁棒性
A wavelet-based image digital watermarking algorithm that the algorithm will be mutually orthogonal two watermarks (watermark robust watermarking and reference) at the same time added to the carrier after image after DWT wavelet coefficients, and then using wavelet transform has been Add a watermark image to use to extract a reference to estimate the watermark image by the attacks, as a result of the robust watermark extracted suffered attacks and the reference watermark by the same attack, it can be estimated through the original Robust Watermarking of the embedded watermark image by adding noise, filtering, compression and cutting, such as a large number of image processing such as testing, can correctly detect the watermark, show that the algorithm has good performance and robustness of perception (2007-08-15, matlab, 186KB, 下载547次)