2ad14c0212
This driver works quite nicely. Seems a little too sensitive though (too much black in the standardized image, not enough ridge gap definition). Processing results are quite good, but you need a good enrollment image (i.e. long!). It's best to get such images by pressing harder than you might think necessary and swiping slowly.
29 lines
745 B
Plaintext
29 lines
745 B
Plaintext
LIBRARY
|
|
=======
|
|
identification
|
|
test suite against NFIQ compliance set
|
|
make library optionally asynchronous and maybe thread-safe
|
|
nbis cleanups
|
|
API function to determine if img device supports uncond. capture
|
|
race-free way of saying "save this print but don't overwrite"
|
|
|
|
NEW DRIVERS
|
|
===========
|
|
Sunplus 895 driver
|
|
AES1610 driver
|
|
AES3400/3500 driver
|
|
ID Mouse driver
|
|
Support for 2nd generation MS devices
|
|
Support for 2nd generation UPEK devices
|
|
|
|
IMAGING
|
|
=======
|
|
ignore first frame or two with aes2501
|
|
aes2501: increase threshold "sum" for end-of-image detection
|
|
aes2501 gain calibration
|
|
aes4000 gain calibration
|
|
aes4000 resampling
|
|
PPMM parameter to get_minutiae seems to have no effect
|
|
nbis minutiae should be stored in endian-independent format
|
|
|