Context-aware-saliency-detection

Image segmentation systems have the potential to dramatically improve the performance of Digital image processing. Segmentation procedures partition an image into its constituent parts or objects. In general, segmentation is one of the most difficult tasks in digital image processing. Detection of salient image regions is useful for applications like image segmentation, adaptive compression, and region-based image retrieval. This problem can be tackled by mapping the pixels into various feature spaces, which are subjected to various grouping algorithms It present a novel method to determine salient regions in images using low-level features of luminance and color. The method is fast, easy to implement and generates high quality saliency maps of the same size and resolution as the input image.

zftjh:直方图均衡图像灰度化、均衡直方图、图像对比度增强，图像预处理(zftjh: histogram equalization of image gray-scale, balanced histogram, image contrast enhancement, image preprocessing)

利用turbopixel的超像素图像分割方法，可以显示不同块的颜色。(This is a mex c and matlab code, which uses the turbopixel to segment the object from the image. )

基于样图的纹理合成 效果很好的块匹配合成(Based Texture Synthesis from Samples effective synthesis of block-matching)

说明：  实现DCT与DWT相结合的算法,用matable及小波变换实现所想构思。(The algorithm of combining DCT with DWT is realized, and the idea is realized by matable and wavelet transform.)

K-means彩色图像分割，有实验报告，main文件中还有区域生长的算法。(K-means color image segmentation, with experimental report.)

多种融合规则，基于contourlet变换的图像融合规则(multiple fusio rule for coefficient selection)

使用MATLAB编写，可以给图像添加数字水印。(Adding digital watermark to image)

新的形态学图像增强，采用多尺度形态学增强算法，对图像进行增强(morphology image enhance )

说明：  基于脉冲耦合神经网络的图像分割，脉冲耦合神经网络是近年研究的热点。(Based on Pulse Coupled Neural Network for Image Segmentation, pulse coupled neural network is the research hotspot in recent years.)