Artificial intelligence learning method based on deep learning

A technology of artificial intelligence and deep learning, applied in the field of artificial intelligence learning based on deep learning, can solve the problems of object occlusion, impact on recognition accuracy, incomplete images, etc., to avoid false detection, high precision and high accuracy Effect

Pending Publication Date: 2020-09-01
JIANGSU VOCATIONAL INST OF ARCHITECTURAL TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide an artificial intelligence learning method based on deep learning to solve the problem that the identification and scanning equipment of the existing license plate, ID card, and various cards proposed in the above background technology often appear to be photographed due to the installation angle of the equipment. Improperly causing the target to be occluded by the object or the image is incomplete, which affects the recognition accuracy

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Artificial intelligence learning method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0026] see figure 1 , the present invention provides a technical solution: a deep learning-based artificial intelligence learning method, the specific steps of the deep learning-based artificial intelligence learning method are as follows:

[0027] S1: Obtain video stream or input picture information, use the video stream or picture information as the input data for identification and detection, and the video stream or picture information contains the target object, and input the video stream or picture information to the artificial intelligence recognition terminal;

[0028] S2: Localize the input picture information or video stream through deep learning. The artificial intelligence recognition end uses the Tiny-DSOD network to locate the video stream or picture information. Separation convolution, preparation of training samples: the training samples used by the Tiny-DSOD network take pictures or video streams of objects in various scenes, mark the samples with horizontal fr...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of artificial intelligence. The invention relates to a learning method, in particular to an artificial intelligence learning method based on deep learning.The artificial intelligence learning method based on deep learning comprises the following specific steps: S1, acquiring video stream or input picture information, taking the video stream or the picture information as input data for identification detection, and inputting a target object in the video streams or the picture information to an artificial intelligence identification terminal and , inputting picture information or video streams, S2, carrying out area positioning on the input picture information or the video streams in a deep learning mode, S3, carrying out recognition and judgment based on deep learning, obtaining a target object cutting area, and then, carrying out multi-scale feature fusion. The invention has the characteristics of small model, high speed, high precision and the like; A part of video streams or picture information without a target object into the training sample set is added to avoid false detection of the network so that the shielding judgment accuracy of the identity card images with different rotation angles and different scales of the picture information or the video stream is relatively high.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence learning method based on deep learning. Background technique [0002] Artificial intelligence is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. [0003] Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that can respond in a manner similar to human intelligence. Research in this field includes robotics, language recognition, image recognition, natural language processing and expert systems, etc. Since the birth of artificial intelligence, the theory and technology have become increasingly mature, and the application fields have also continued to expand. It can be imagined that the technological products brought by artific...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/24147G06F18/253G06F18/214
Inventor 郭扬
Owner JIANGSU VOCATIONAL INST OF ARCHITECTURAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products