Face recognition

This change adds support to retrieve 128D face descriptor for a given
landmark. Since now we have full pipeline, README.md has "general usage"
section and integration test is added. Also, return from
FaceLandmarkDetection is changed, so it can be given to FaceRecognition
without changes. All obtained values are crosschecked to match with values
from python versions (however, if num_jitters is > 1 in FaceRecognition,
values don't match between PHP and Python, I suspect it is related to usage
of dlib::rand, but still investigating)..
This commit is contained in:
Branko Kokanovic
2018-08-28 00:37:46 +02:00
parent 1a402fc63c
commit 1e830a3285
11 changed files with 468 additions and 32 deletions

View File

@@ -61,6 +61,22 @@ ZEND_END_MODULE_GLOBALS(pdlib)
ZEND_TSRMLS_CACHE_EXTERN()
#endif
#define PARSE_LONG_FROM_ARRAY(hashtable, key, error_key_missing, error_key_not_long) \
zval* data##key; \
/* Tries to find given key in array */ \
data##key = zend_hash_str_find(hashtable, #key, sizeof(#key)-1); \
if (data##key == nullptr) { \
zend_throw_exception_ex(zend_ce_exception, 0 TSRMLS_CC, #error_key_missing); \
return; \
} \
\
/* We also need to check proper type of value in associative array */ \
if (Z_TYPE_P(data##key) != IS_LONG) { \
zend_throw_exception_ex(zend_ce_exception, 0 TSRMLS_CC, #error_key_not_long); \
return; \
} \
zend_long key = Z_LVAL_P(data##key); \
#endif /* PHP_PDLIB_H */