1. Department of Electrical and Computer Engineering Blind Assistive Technology Bill Reading Device (BATBRD) Professor Aura Ganz Ian McAlister Colin Smith Chris Neyland Erick Drummond TEAM GANZ Preliminary Design Review

2. 2 Department of Electrical and Computer Engineering OUTLINE  Background and Significance  Ideal Final Product  Requirements, Technical Challenges  Design Alternatives  Proposed Platform  Imaging Device and Initial Testing  System Specifications and Block Level Diagram  Image Processing Algorithms  Proposed MDR Prototype Specifications  Conclusion and Pathway to FPR

3. 3 Department of Electrical and Computer Engineering Background and Significance  Population 1.8 million legally blind individuals in the U.S. [1] 21.2 million reported experiencing vision loss [1]  Definitions Legally Blind Visual acuity less than 20/200 in the better eye with the use of a correcting lens [2] Vision Loss Reported unable to see even with corrections including blind above [1] http://www.lighthouse.org/research/statistics-on-vision-impairment/prevalence/ [2] 42 U.S.C. § 416(i)(1)(B) (Supp. IV 1986). http://www.law.cornell.edu/socsec/rulings/ssr/SSR90-05.html

4. 4 Department of Electrical and Computer Engineering  Current Scenario Interview with Jenny Folding Schemes KNFB Reader Background and Significance (Cont)

5. 5 Department of Electrical and Computer Engineering  Our vision: Bill Reading Wallet Jenny’s Feedback and Reaction  Portable  Low Power Day Long Availability On a Single Charge  Easy to Use  Cost <$100  Bill Recognition Speed<2 sec Proposed Ideal Final Product

6. 6 Department of Electrical and Computer Engineering OUTLINE  Background and Significance  Ideal Final Product  Requirements, Technical Challenges  Design Alternatives  Proposed Platform  Imaging Device and Initial Testing  System Specifications and Block Level Diagram  Image Processing Algorithms  Proposed MDR Prototype Specifications  Conclusion and Pathway to FPR

7. 7 Department of Electrical and Computer Engineering Product Requirements and Technical Challenges  Intuitive Interface design  Form Factor  Cost constraints  Power considerations  Performance  Computer Vision algorithms  HW/SW integration

8. 8 Department of Electrical and Computer Engineering Design Alternatives  Handheld Optical Scanner Costly Lack of Availability/Support  Hat Mounted Reader Poor Form Factor Numerous Image Processing Variables  Camera Based Contact Device Small Form Factor Reduces Image Processing and Lighting Variables Easier to Integrate components

9. 9 Department of Electrical and Computer Engineering Platform Choice SystemBeagle BoardGumstix Earth + Summit daughter boardFPGA Approx Cost$150$150 to $210$30-$70 CPU600MHz 60MHz or Slower RAM256MB256MB low-power DDR RAM Up to 1.1 Mbit of On- Chip Embedded Memory Supported OS(s) Android, Angstrom Linux, and Win CE Linux 2.6.29No OS Needed Size3"x3"3.15" x 1.54" x.16"Approx 1" x 1" Weight1.41oz3.57oz.357 to 1.41oz Power2W1-2WLess than 1W Development Community Yes, Strongest FollowingSecond Strongest Following Third Strongest Following LibrariesBinaries/SourceFew Binaries, SourceN/A ReliabilityFlashable from homeRTM for Re-flashFlashable From Home DSP supportYes, Built InYes, With Summit BoardNo Camera & Other Peripherals Most Linux Compatible USB/RS232 Devices Will Work Little Documentation on Compatible Devices Minimal To No Documentation

10. 10 Department of Electrical and Computer Engineering Platform Decision: The Alternatives  FPGA Small Development Community Difficult to Program Advised to Avoid by Field Experts  Gumstix High Cost: >42% of budget Specs Similar to Beagle Board Less Documentation Smaller Development Community

11. 11 Department of Electrical and Computer Engineering Platform Decision: The Beagle Board  Beagle Board Low power consumption Cost: <30% of budget Form factor Good processing speed Strong development community Simple integrated development environment

12. 12 Department of Electrical and Computer Engineering OUTLINE  Background and Significance  Ideal Final Product  Requirements, Technical Challenges  Design Alternatives  Proposed Platform  Imaging Device and Initial Testing  System Specifications and Block Level Diagram  Image Processing Algorithms  Proposed MDR Prototype Specifications  Conclusion and Pathway to FPR

13. 13 Department of Electrical and Computer Engineering  Camera Requirements Small Form Factor Easy to Integrate  Device Alternatives Discrete CMOS Camera Little Documentation UART-Controlled Camera Slow Problematic Imaging Device

14. 14 Department of Electrical and Computer Engineering Imaging Device: PS3 EYE Webcam  Designed for Computer Vision Applications  Hacking Tutorials Available  Low-Cost  High Speed

15. 15 Department of Electrical and Computer Engineering Initial Lighting Tests: Contrast Red Ink → Best Contrast: GREEN Conclusion: Use two colors (one image for each) Green Ink → Best Contrast: RED

16. 16 Department of Electrical and Computer Engineering System Specifications: Bill Reading Device  The Bill Reader Device will have the Approximate Specifications: 1 processing unit: Beagle Board Commercial Off-The-Shelf (COTS) Camera: PS3 EYE Speaker LED Lights SD Card Low power usage System standby when not in use

17. 17 Department of Electrical and Computer Engineering System Level Block Diagram

18. 18 Department of Electrical and Computer Engineering OUTLINE  Background and Significance  Proposed Final Product  Alternatives  Requirements, Technical Challenges  Design Alternatives  Proposed Platform  Imaging Device and Initial Testing  Specs and System Block Level Diagram  Image Processing Algorithms  Proposed MDR Prototype Specifications  Conclusion and Pathway to FPR

19. 19 Department of Electrical and Computer Engineering Image Processing Algorithms Potential Algorithm (High-Level): Receive images (Red, Green) Perform:  Smoothing  Thresholding  Edge Detection Compare statistically with database (Rotate if necessary, recompare) Vote on results

20. 20 Department of Electrical and Computer Engineering  Evaluate image processing algorithms (9 NOV)  Implement one image processing algorithm on a PC (16 NOV)  Learn hardware/software platform (20 NOV)  Test the algorithm on ideal images (20 NOV)  Build bill library (20 NOV)  All tasks critical foundation Whole team is assigned to all tasks. Proposed MDR Specifications

21. 21 Department of Electrical and Computer Engineering  Mid February (CDR) Complete and test image processing algorithm(s) on a PC Integrate and test hardware components Finalize design  March Integrate software to Beagle Board Develop and fabricate project enclosure  April Begin final testing and data collection Analysis of data for presentation Approximate pathway from MDR to FPR

22. 22 Department of Electrical and Computer Engineering  Identified Current Issues  Developed Idea with Ideal Design  Determined an Attainable Project Design  Decided on Specific Hardware for Our Project  Highlighted Image Processing as #1 Challenge  Developed/Assigned MDR Tasks around anticipated Image Processing Difficulties Conclusion

23. 23 Department of Electrical and Computer Engineering Questions ?

24. 24 Department of Electrical and Computer Engineering  Colin: Intro, Schedule  Ian: Research background and significance  Erick: Camera selection and related research  Chris: Platform selection research Slide Credits: In Random Order