OpenCV mergevec issues
Someone answered this within a few hours on the opencv Q&A. If you have any OpenCV questions i highly recommend you go there first as it is much more likely that someone will answer your question on their page. Here's the answer i received.
You do not need to merge vec files for object classifier training using the cascade of weak classifiers approach. I keep wonder why the hell people merge vec files, and always the answer is because they want to create artificial data vectors. Avoid this at all costs if you want you models to do something with sense.
Skip the complete haar training interface and move on to the traincascade interface, which is better supported, more bugfree and better supported.
- Start with the traincascade and createsamples information in the Description.
Haartraining, Why do i keep getting the error unable to read negative images
Instead make your entries in the bg file like--
1.png
2.png
3.png
4.png
....
That will do the trick
Regards
Related Topics
How to Write on Serial Port Using Qextserialport
Where Are Core Files Stored in a Lxc Container
How to Include Debug Information with Nasm
How to Rename a Kernel Module Name Without Renaming The .Ko Passed to Insmod
.Dat Attachment Instead of Text Using Mailx in Redhat Linux
Embedded Linux Poll() Returns Constantly
Merge Multiple Lines to 1 Row with Awk(Or Familiar)
How to Launch a Background Process Through a Wrapper That'Ll Undo The Sigint Ignore
Where to Store The Private Key on a Digital Signing Server
Qemu Simple Backend Tracing Dosen'T Print Anything
How to Schedule a Cron for The First Thursday of Every Month
How Does Ltrace() Display Rand()
How to Extract Every N Columns and Write into New Files
Prevent Git Checkout from Overwriting a File
Bash Script with User Defined Functions in Autocomplete
Slurm: After Allocating All Gpus No More CPU Job Can Be Submitted