US 12,287,850 B2
Handwriting geometry recognition and calibration system by using neural network and mathematical feature
Jianming Zhuang, Shenzhen (CN); and Chung Kwong Chan, Shenzhen (CN)
Assigned to SUNIA PTE. LTD, Center (SG)
Filed by Jianming Zhuang, Shenzhen (CN); and Chung Kwong Chan, Shenzhen (CN)
Filed on Oct. 13, 2022, as Appl. No. 18/046,160.
Prior Publication US 2024/0134938 A1, Apr. 25, 2024
Int. Cl. G06F 18/2431 (2023.01); G06F 3/04883 (2022.01); G06F 18/10 (2023.01); G06F 18/24 (2023.01); G06F 18/243 (2023.01); G06N 3/02 (2006.01); G06T 7/60 (2017.01); G06T 7/64 (2017.01); G06V 10/20 (2022.01); G06V 10/22 (2022.01); G06V 10/422 (2022.01); G06V 10/44 (2022.01); G06V 10/46 (2022.01); G06V 10/72 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/142 (2022.01); G06V 30/148 (2022.01); G06V 30/18 (2022.01); G06V 30/182 (2022.01); G06V 30/186 (2022.01); G06V 30/19 (2022.01); G06V 30/226 (2022.01); G06V 30/228 (2022.01); G06V 30/242 (2022.01); G06V 30/32 (2022.01); G06V 40/16 (2022.01); G06V 40/30 (2022.01)
CPC G06F 18/2431 (2023.01) [G06F 3/04883 (2013.01); G06F 18/10 (2023.01); G06F 18/24 (2023.01); G06F 18/24317 (2023.01); G06N 3/02 (2013.01); G06T 7/60 (2013.01); G06T 7/64 (2017.01); G06V 10/20 (2022.01); G06V 10/22 (2022.01); G06V 10/255 (2022.01); G06V 10/422 (2022.01); G06V 10/44 (2022.01); G06V 10/454 (2022.01); G06V 10/476 (2022.01); G06V 10/72 (2022.01); G06V 10/764 (2022.01); G06V 10/765 (2022.01); G06V 10/82 (2022.01); G06V 30/10 (2022.01); G06V 30/1423 (2022.01); G06V 30/153 (2022.01); G06V 30/1801 (2022.01); G06V 30/1834 (2022.01); G06V 30/186 (2022.01); G06V 30/19153 (2022.01); G06V 30/19173 (2022.01); G06V 30/19193 (2022.01); G06V 30/2264 (2022.01); G06V 30/228 (2022.01); G06V 30/242 (2022.01); G06V 30/32 (2022.01); G06V 30/333 (2022.01); G06V 30/347 (2022.01); G06V 30/36 (2022.01); G06V 40/171 (2022.01); G06V 40/30 (2022.01); G06V 40/382 (2022.01); G06V 40/388 (2022.01); G06V 40/394 (2022.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A handwriting geometry recognition and calibration system by using a neural network and mathematical feature, comprising:
a mainframe including a processor and a memory connected to the mainframe;
a handwriting geometry recognition system installed in the mainframe for recognizing a handwriting geometric figure inputted from users, the processor serving for performing operations of the handwriting geometry recognition system; the memory serving to store data and programs of the handwriting geometry recognition system;
the handwriting geometry recognition system including:
a pre-processor for pre-processing coordinate points of geometric figures from a user's handwriting so as to get a plurality of sample points which expresses the geometric figures to be recognized;
a neural network connected to the pre-processor for receiving the sample points of the geometric figure and recognizing the geometric figure so as to acquire a coarse class of the geometric figure; and
an mathematical logic unit connected to the neural network for receiving recognition results from the neural network, including coarse classifications which are used in a secondary classification by using conventional mathematical recognition logics so as to determine an exact geometry shape of the geometric figure; then the geometric figure being calibrated so as to get a geometry with a regular shape:
wherein the arithmetic logic unit comprises:
a turning-point finding unit for finding turning points to the sample points of the geometric figure by mathematical logic operation: the turning point being a turning location of the geometric figure; and
a figure classification and calibration unit connected to the turning-point finding unit for performing a secondary classification to the geometric figure based on the coarse classification from the neural network and turning points finding by the turning- point finding unit so as to determine the exact class of the geometric figure and calibrate the shape of the geometric figure.