1 / 34

Department of Automation Engineering National Formosa University

Department of Automation Engineering National Formosa University. Attendance Administrative System Using Dactyloscopy. Kuang-Chyi Lee, Gavin Thomson and Yong-Jia Huang. Department of Automation Engineering, National Formosa University. Outline. Introduction Attendance administrative system

Download Presentation

Department of Automation Engineering National Formosa University

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Department of Automation EngineeringNational Formosa University Attendance Administrative System Using Dactyloscopy Kuang-Chyi Lee, Gavin Thomson and Yong-Jia Huang

  2. Department of Automation Engineering, National Formosa University Outline • Introduction • Attendance administrative system • Identification of fingerprints • Discussions • Conclusions

  3. Department of Automation Engineering, National Formosa University Introduction • Biometry, safety, uniqueness. • Attendance administrative system, database consistency.

  4. 4.Check out • 2. Check the recording of fingerprint data • 3.Collecting check in/out times Department of Automation Engineering, National Formosa University Attendance administrative system 1. Basic staff data

  5. Department of Automation Engineering, National Formosa University Flowchart

  6. Department of Automation Engineering, National Formosa University Functions • Check fingerprint • Personnel ID verification • Login/logout • Add/Delete staff • Modify personnel database • Report list • Administrator

  7. Department of Automation Engineering, National Formosa University Database

  8. Department of Automation Engineering, National Formosa University Fingerprint registration Select mode Fingerprint image Staff name Registered finger

  9. Check mode Message Department of Automation Engineering, National Formosa University Fingerprint identification

  10. Department of Automation Engineering, National Formosa University New staff

  11. Department of Automation Engineering, National Formosa University ID verification

  12. Login Logout Exit Data modification Department of Automation Engineering, National Formosa University Login system

  13. Department of Automation Engineering, National Formosa University Records of attendance

  14. Department of Automation Engineering, National Formosa University Administrator

  15. Department of Automation Engineering, National Formosa University Identification of fingerprints fingerprint scanner

  16. Department of Automation Engineering, National Formosa University Low-pass filter, Binarize, Thinning.

  17. Department of Automation Engineering, National Formosa University Fingerprint classification (Henry [1])

  18. Department of Automation Engineering, National Formosa University Fingerprint tracing Spherical algorithm Ci+1 is node for the first round window and ridge line

  19. Department of Automation Engineering, National Formosa University Ten ridge patterns (Chang [6]) Plain ridge: Left End belong to left area, right End belong to right area,|H|< fifty pixel..

  20. Department of Automation Engineering, National Formosa University Simplified R-D Model p+α+tl+a+ p+α+tl+a+ p+α+tl+a+ p+α+tl+a+ p+α+tl+a+ p+α+tl+a+ p+α+tl+a+ p+α+tl+a+

  21. Department of Automation Engineering, National Formosa University Fingerprint test

  22. Department of Automation Engineering, National Formosa University Discussions • The FRR for the fingerprint system is 1.45%,and the FAR is 0.8%. • If we add person date, it can cancellation FRR and reduce FAR. • In this system, average time to identification is about 1.6 seconds.

  23. Department of Automation Engineering, National Formosa University Conclusions • The paper develop high exactly, low error, operation fast relation database by logic database. • Finish a fingerprint and person ID to do attendance administrative system, it can make user to use easily. • Finish the fingerprint classification by the R-D Mode after catch the fingerprint.

  24. Department of Automation Engineering, National Formosa University Thanks for your attention

  25. Database normalization • In first normalization can reduce the value for recover roll. And have three reasons are sample, easy, and can use an operation to success. • In second normalization can reduce the depend on each other for data, and use division table can make it the same main key. • In third normalization can reduce the depend on each other for data, it can make the data structure for delete or insert. Return

  26. Low-pass filter • It can use mask to process the value in one time. • We can give the middle value for the average value in 3x3 space mask.

  27. Binarize • If f(x,y)>m, then f(x,y) is255 • If f(x,y)< m, then f(x,y) is0 ( m is threshold value, f is input vision)

  28. Thinning Tinning algorithm can be division into two steps, and we will implement it until no delete point. Step1 delete condition:(a) 2≦ N(P1) ≦6(b) S(P1)=1(c1) P2 ·P4 ·P6 = 0(d1) P4 ·P6 ·P8 = 0 Step2 delete condition:(a) 2≦ N(P1) ≦6(b) S(P1)=1(c2) P2 ·P4 ·P8 = 0(d2) P2 ·P6 ·P8 = 0 Return

  29. Smile ridge and Triangle ridge Triangle: Left Ending belong left area, Right Ending belong right area, the max is> . Smile ridge: Left Ending belong left area, Right Ending belong right area, and H<-HT. ( define 50°)

  30. Left-loop ridge and Right-loop ridge Left-Loop: Left Ending and Right Ending in left area. Right-Loop: all ending in right area. Explain : main point are two point

  31. Circle ridge and Balloon ridge Balloon ridge: Left end or Right End have node with ridge line. Circle ridge: Left End =Right End

  32. Whorl ridge and Double-loop ridge Double-Loop ridge: <360° >360° Whorl ridge: Return

  33. Ridge line trace spherical algorithm Finish trace result Ci+1 is node for the first round window and ridge line

  34. Fragment point and Ending point Ending point Fragment elimination by additional tracing steps Return

More Related