id: 05807918
dt: a
an: 05807918
au: Moon, Cheol-Hong; Jang, Hyun-Chul; Jun, Jin-Kook
ti: Implementation of the pattern matching system to detect flip chip PCB
    defects.
so: Huang, De-Shuang (ed) et al., Advanced intelligent computing theories and
    applications. 6th international conference on intelligent computing,
    Changsha, China, August 18‒21, 2010. Proceedings. Berlin: Springer
    (ISBN 978-3-642-14830-9/pbk; 978-3-642-14831-6/ebook). Communications
    in Computer and Information Science 93, 273-280 (2010).
py: 2010
pu: Berlin: Springer
la: EN
cc: 
ut: PCB; pattern matching; MAD; parallel processing MAD pattern matching IP
ci: 
li: doi:10.1007/978-3-642-14831-6_37
ab: Summary: FPGA-based Pattern Matching System, which supports a Camera Link
    (Medium), was used to detect Flip Chip PCB defect patterns. For the
    automation of the vision inspection of the Flip Chip PCB production
    process, the system was optimized by implementing the vision library in
    IP, which is used to produce high speed processing FPGA-based systems
    and to detect defect patterns. The implemented IPs comprised of Pattern
    Matching IP, VGA Control IP, Memory Control IP and Parallel Processing
    MAD Pattern Matching IP. Xilinx was used to process the image
    transmitted in high speed from Digital Camera, Vertex-4 type 1.6
    million gate FPGA chip. It allowed the processing of 4Tap $(2352(H) *
    1728(V) *8Bit)$ image data transmitted from the camera without the need
    for a separate Frame Grabber Board[5] in the FPGA. In addition, it
    could check the 1Tap$(588(H) * 1728(V) *8bit)$ image data on a PC via
    USB transmission out of 4 Taps. For pattern matching, it abstracted a
    256*256 area out of the 1Tap image, transmitted the image to each IP
    and displayed the Pattern Matching output result on a 7inch TFT-LCD.
rv: