Target detection method for feature extraction of images on basis of deep learning framework

A technology of deep learning and feature extraction, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as large amount of calculation, optimization of pre-processing, etc., achieve regression rate and accuracy improvement, reduce calculation amount, improve The effect of accuracy
CN106203450AInactive Publication Date: 2016-12-07ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION
2 Cites 17 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
ACADEMY OF BROADCASTING SCI STATE ADMINISTATION OF PRESS PUBLICATION RADIO FILM & TELEVISION
Publication Date
2016-12-07
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to a target detection method for feature extraction of images on the basis of a deep learning framework. The method is technically characterized in that the images are preprocessed on the basis of the MCG algorithm, and possible image blocks at target positions are extracted; the extracted image blocks are optimized on the basis of the MTSE algorithm; the obtained image blocks are iterated and adjusted to the size meeting the caffe framework input requirement through the superpixel optimization method; feature extraction is conducted on the image blocks through the caffe deep learning framework, and model configuration is finished through the R-CNN algorithm; obtained features are classified through the SVM algorithm to obtain a final result. The method is reasonable in design, the calculation quantity of the features is reduced by preprocessing the images, then deep features of the images are extracted through the caffe deep learning framework, objects can be represented better, the features are classified through the SVM classification algorithm, and a good detection result is obtained.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the technical field of target detection, in particular to a target detection method for feature extraction of images based on a deep learning framework. Background technique

[0002] Vision is an important sensory modality by which humans interact with the world around them. More than 80% of the information processed in the human brain comes from visual information, which ensures that we can intelligently perceive the world and make appropriate actions in our daily life, especially in today's rapid development of mobile smart devices, more and more image sensors are scattered around us and used by ourselves. The human visual system can detect and locate target objects from complex environments, which is the basic function of human vision. Computer target detection and recognition aims to use machines to detect and locate specific targets, and is the basis for target search and tracking. Object detection and recognition has a...

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