shuizhongyu/Learn-to-identify-similar-images

检测一个文件夹中的相似图片

bash test.sh folder

将每张图片和他之后的五张图片比较（ls默认顺序），相似的会输出两张图片名称。

test.py中修改使用的算法。具体算法见下。

I learn how to identify similar images, I wrote some python scripts.

I implement some algorithm what I study from Internet and I will updata it during I learning Image classification.

I hope these code can help someone who is beginner in identifying similar images just like me.

My goal is to one day use these algorithms on my web spider, make it can collect to a certain class of images.

So,if you are insteresting in it，welcome to Issues or pull requests.

Of course,I will happy if you give me a star.

##This is my script：

aHash.py This module can classify the image by Average Hash Method.
histogram.py This module can classify the image by Calculating the histogram.
histogram2.py This module also can classify the image by Calculating the histogram.But it will split the image to 16 pices and Calculating its histogram.So,it is more accurate than historgram.py
pHash.py This module classify the image by Discrete Cosine Transform and the accurate rate has a little improve.
dHash.py This module can classify the image by dHash.Someone is willing to tell me the name of the Dash in detail?
face1.py Find the location of the face using opencv.
face2.py On the base of face1.py to judge whether two face similar
imagecluster Using Using image clustering to classify the image.

##My enviroment

To be continue......