content-based-image-retrieval

对玻璃表面缺陷图像进行处理，进行分类识别(The glass surface defect image processing, classification and identification)

实现对图像的经验模态分解，得到经验模态分解后的第一层IMF分量，反映了图像的主要信息，去除冗余信息，为识别提供了基础。(Empirical mode decomposition of image, obtain the empirical mode decomposition of the first layer of IMF component, reflected the main information of the image, to remove redundant information, provide the basis for identification. )

8路串行lvds转单路并行axistream(8 single-pathLVDS to 1parallel AXI_Stream)

说明：  LSB替换隐写软件，该软件能把ASCII码嵌入到图像中，其载体图像是24位的BMP格式图像(LSB replaces steganography software, which can embed ASCII code into image, and its carrier image is 24 bit BMP format image)

联合贝叶斯人脸验证python代码，机器学习(Joint Bayes face verification)

E:

基于模糊C-均值聚类算法的图像分割，消除二值分割的非此即彼的缺陷(Image segmentation based on fuzzy C- means clustering algorithm eliminates the defects of two value segmentation.)

运用于人脸图像预处理中，主要实现功能有：人脸检测，人脸对齐，人脸图像放缩，人脸剪切。(Applied to the face image preprocessing, the main features are: face detection, face alignment, face image zoom, face cuts.)

四种图像去噪程序，给原图像分别加上高斯噪声，椒盐噪声，乘性噪声，脉冲噪声后进行去噪，输出去噪后的图像(Four image denoising procedures, to the original image plus Gaussian noise, salt and pepper noise, multiplicative noise, impulse noise the Denoising output denoised image)

迭代收缩阈值算法和快速收缩阈值迭代算法求解Lasso问题(Iterative Shrinkage Thresholding Algorithm (ISTA) for LASSO problem)