Pattern recognition apparatus using parallel operation

Image analysis – Pattern recognition

Reexamination Certificate

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Reexamination Certificate

active

10156942

ABSTRACT:
In a pattern recognition apparatus, a local area recognition module is constructed with operation elements having predetermined operation characteristics. Pattern data of a predetermined size in input data is acquired by time-sequentially performing inputting process at a plurality of times via a local area scanning unit, and information indicating the position of pattern data in the input data is output. The local area recognition module detects a feature of a predetermined middle-order or high-order category from the pattern data. A consolidation module time-sequentially consolidates outputs from the local area recognition module on the basis of the position information and the category of the feature thereby producing feature detection map information. A judgment unit outputs position information and category information of a high-order feature present in the input data, on the basis of the output from the time-sequential consolidation module.

REFERENCES:
patent: 5058184 (1991-10-01), Fukushima
patent: 5329594 (1994-07-01), Maruno et al.
patent: 5493688 (1996-02-01), Weingard
patent: 5627943 (1997-05-01), Yoneda et al.
patent: 5664065 (1997-09-01), Johnson
patent: 5664069 (1997-09-01), Takatori et al.
patent: 5987170 (1999-11-01), Yamamoto et al.
patent: 6088490 (2000-07-01), Iwata et al.
patent: 6185337 (2001-02-01), Tsujino et al.
patent: 6647139 (2003-11-01), Kunii et al.
patent: 6687386 (2004-02-01), Ito et al.
patent: 6829384 (2004-12-01), Schneiderman et al.
patent: 2002/0038294 (2002-03-01), Matsugu
patent: 2002/0159627 (2002-10-01), Schneiderman et al.
patent: 2002/0181765 (2002-12-01), Mori et al.
patent: 0 926 885 (1999-06-01), None
patent: 6-176158 (1994-06-01), None
patent: 9-153021 (1997-06-01), None
patent: 2741793 (1998-01-01), None
patent: 11-15495 (1999-01-01), None
patent: 11-15945 (1999-01-01), None
patent: 11-196332 (1999-07-01), None
John G. Daugman, “Complete Discrete 2-D Gabor Transforms by Neural Networks for Image Analysis and Compression,” IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 36, No. 7, 1169-1179 (Jul. 1988).
John G. Daugman, “Uncertainty Relation for Resolution in Space, Spatial Frequency, and Orientation Optimized by Two-dimensional Visual Cortical Filters,” J. Opt. Soc. Am. A/vol. 2, No. 7, 1160-1169 (Jul. 1985).
S. Y, Kung, “Mapping Neural Nets to Array Architectures,” Digital Neural Networks, 340-361 (PTR Prentice Hall 1993).
John Lazzaro, et al., “Silicon Auditory Processors as Computer Peripherals,” Advances in Neural Information Processing Systems 5, 820-827 (Morgan Kaufmann 1993).
Yann LeCun and Yoshua Bengio, “Convolutional Networks for Images, Speech, and Time Series,” The Handbook of Brain Theory Neural Networks, 255-258 (Michael A. Arbib ed. MIT Press 1995).
B. D. Terris, et al., “Near-field Optical Data Storage Using a Solid Immersion Lens,” Appl. Phys. Lett., vol. 65, No. 4, 388-390 (Jul. 25, 1994).
Yasuhiro Ota and Bogdan M. Wilamowski, “Analog Implementation of Pulse-Coupled Neural Networks,” IEEE Transactions on Neural Networks, vol. 10, No. 3, 539-544 (May 1999).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Pattern recognition apparatus using parallel operation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Pattern recognition apparatus using parallel operation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Pattern recognition apparatus using parallel operation will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-3737434

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.