get the landmars,positions,features for reconition of the face in the image
Project description
Info
ldm.py 2018-05-25
Author: Zhao Mingming <471106585@qq.com>
Copyright: This module has been placed in the public domain.
version:0.1.0 - add compare2dir
version:0.1.1 - add face_rec_ms version:0.1.3 - add compare2imglist
Classes: - LDM: you can use a function to get landmarks and face feature with no other libs
Functions:
face_feature: the feature of face in the image for face recognition
landmarks: get the landmarks and face in the image
face_rec: return the face similarity of the face in two images
has_same_person: return a int(>0) if there have a same person in two images,otherwise 0
compare2dir: compare the face in the images of the two dirs,and return the rate ,score_avg,class_id1,class_id2
compare2imglist: compare the face in the imglist ,and return the rate ,score_avg,class_id1,class_id2
How To Use This Module
example code:
imagepath="closed_eye/9.jfif"
img=io.imread(imagepath)
img1=img
imagepath="closed_eye/14.jfif"
img2=io.imread(imagepath)
ldmer=ldm.LDM()
print img.shape[0]
ldl,facel,txt=ldmer.landmarks(img)
print txt
for ld in ldl:
print 10*'-'
print 'nose:'
print ld['nose']
for face in facel:
print 10*'-'
print 'face:'
print face.top()
print face.left()
print face.width()
print face.height()
print face.bottom()
print face.right()
x,y,w,h=[face.top(),face.left(),face.width(),face.height()]
print x,y,w,h
print "feature:"
ffl=ldmer.face_feature(img,facel)
for ff in ffl:
print help(ff)
print 'ff='+str(ff)
print 'len(ff)='+str(len(ff))
print 'ff[0]='+str(ff[0])
print 'ff[127]='+str(ff[127])
print "face compare:"
print ldmer.face_rec(img1,img2)
print ldmer.has_same_person(img1,img2)
print ldmer.has_same_person(img2,img2)
print "face number:"
print ldmer.face_number(img,facel)
Refresh
add a function : ldmer.imread(imgpath) modify the return value number to: has_flag,max_score=ldmer.has_same_person(img1,img2)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distributions
File details
Details for the file ldm-0.1.3.tar.gz
.
File metadata
- Download URL: ldm-0.1.3.tar.gz
- Upload date:
- Size: 6.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/40.0.0 requests-toolbelt/0.8.0 tqdm/4.19.4 CPython/3.4.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 65969b847a3f0c5d0038fd811768b308bafde4d632c03ee81cc8ac9dc8583334 |
|
MD5 | 1b224bda3914232bc247f62962e8f4d5 |
|
BLAKE2b-256 | 940e5b3f37208189540ffc4648a841543393de7bd1451fcaaf21ede40b4e580c |
File details
Details for the file ldm-0.1.3-py2.7.egg
.
File metadata
- Download URL: ldm-0.1.3-py2.7.egg
- Upload date:
- Size: 11.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/40.0.0 requests-toolbelt/0.8.0 tqdm/4.19.4 CPython/3.4.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 02fdb035b3c2ef55fe1a08071ed3222c8d66e08a155a244d1420b604e757a458 |
|
MD5 | 1e2313189a2a3d94f4d4c42a1fb0d927 |
|
BLAKE2b-256 | 83f2d1d4101133442eb51da066a5b2c1cd379f663a330a429409d98688e3e3f8 |
File details
Details for the file ldm-0.1.3-py2-none-any.whl
.
File metadata
- Download URL: ldm-0.1.3-py2-none-any.whl
- Upload date:
- Size: 7.8 kB
- Tags: Python 2
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.11.0 pkginfo/1.4.2 requests/2.18.4 setuptools/40.0.0 requests-toolbelt/0.8.0 tqdm/4.19.4 CPython/3.4.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 21eda2f2b22f851207a541cf51ef93cdd2adc060d07b4a1d260edbaf0be9ae9b |
|
MD5 | 7f72e1dcbc5a3c2b4db3e31c7eea24b1 |
|
BLAKE2b-256 | 20b5d43cac57883122588bf3d3e0a39f6cbe0c0ad8144fdd3bf61c6f2c21f863 |