Invention Grant
- Patent Title: Image recognition method and system based on deep learning
-
Application No.: US15670511Application Date: 2017-08-07
-
Publication No.: US10726291B2Publication Date: 2020-07-28
- Inventor: Guo-Zhen Wang
- Applicant: PIXART IMAGING INC.
- Applicant Address: TW Hsin-Chu
- Assignee: PIXART IMAGING INC.
- Current Assignee: PIXART IMAGING INC.
- Current Assignee Address: TW Hsin-Chu
- Agency: Li & Cai Intellectual Property (USA) Office
- Priority: com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@7a819be9 com.zzzhc.datahub.patent.etl.us.BibliographicData$PriorityClaim@10696734
- Main IPC: G06K9/46
- IPC: G06K9/46 ; G06N20/00 ; G06K9/00 ; G06K9/62 ; G06N3/04 ; G06N3/08

Abstract:
The present disclosure discloses an image recognition method and system based on deep learning. The image recognition method trains a recognizing engine for high resolution images and a recognizing engine for low resolution image separately. The two recognizing engines generate two independent feature groups specifically for high resolution and low resolution images respectively. A categorizing engine categorizes a testing image to a high resolution mode or a low resolution mode, and then the testing image is recognized by the appropriate recognizing engine. Therefore, the present disclosure increases the accuracy of image recognition under various conditions.
Public/Granted literature
- US20180060687A1 IMAGE RECOGNITION METHOD AND SYSTEM BASED ON DEEP LEARNING Public/Granted day:2018-03-01
Information query