Algorithm-How To Identifying Same IMG

recently i wrote one php spider progrom just for downloading images , then i find i have had download to many duplicated images

as one poor student , i got to find the way clean the copy of them .

this is what i found by digging web for related Pin Point The Same Images

while wrriting and digging the main point move from Pin point same Images to Transform images into Linear/Static/Geomatry problems

Structure

Algorithm	Base theory	Advance Apply
Perceptual hash algorithm	fingerprint	pHash / SIFT
Color histogram	transform	Otsu’s method
PPMCC	linear dependence
TF-IDF	statistics dependence
Cosine similarity	geomatry dependence

Info

1, Perceptual hash algorithm

2, Color histogram

3, Pearson product-moment correlation coefficient

4, Term frequency–Inverse document frequency

5, Cosine similarity

update 2016/05/20