Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Supervised image classification method based on self-paced constraint mechanism

A classification method and image technology, applied in computer parts, instruments, character and pattern recognition, etc., can solve the problems of neglect and improve the effect of image recognition

Pending Publication Date: 2019-07-12
JIANGNAN UNIV
View PDF1 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Classifying natural images containing a large number of object categories is one of the most challenging problems in pattern recognition, and mainstream solutions include wavelet relational vector machines (WRVM), global and local saliency feature encoding, and bag-of-words models (bow), Previous image classification algorithms have focused on obtaining visual representations of image features while ignoring specific class information. In order to find a more suitable method for data representation, a large number of schemes have been developed to solve this problem. Recently, these have been developed In the model of , the sparse representation classification technology with supervision has attracted many people's interest because of its powerful image modeling ability. Many studies have shown that this kind of sparse representation-based classification (SRC) algorithm has a very Excellent, however, the supervised dictionary learning mechanism is no longer applicable when faced with complex samples containing noise and large intra-class variation, moreover, learning a discriminative and representative dictionary from complex training samples is still a challenge

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
  • Supervised image classification method based on self-paced constraint mechanism
  • Supervised image classification method based on self-paced constraint mechanism
  • Supervised image classification method based on self-paced constraint mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] refer to figure 1 , provides a schematic diagram of the overall structure of a supervised image classification method based on a self-paced constraint mechanism, such as figure 1 , a supervised image classification method based on a self-procedural constraint mechanism, including S1: dividing training samples into difficult and easy categories; S2: establishing a sparse representation model, and bringing samples into the sparse representation model for training; S3: obtaining an image classification model and a prediction model; And, S4: constructing a category decision maker; wherein, the types of difficulty and difficulty of training samples include training easy samples and training difficult samples.

[0049] Specifically, the main structure of the present invention includes S1: Divide the difficulty types of training samples, the operator divides the database images, and divides them into training samples and test samples, and here divides the difficulty of the tra...

Embodiment 2

[0057] refer to figure 2 , this embodiment is different from the first embodiment in that: the step of obtaining the image classification model and the prediction model includes: S41: training and training easy samples; S42: updating X; S43: obtaining sparse code X, coefficient code D and self-stepping Constrained weighting coefficient α; S44: Determine the image classification model and prediction model. Specifically, see figure 1 , its main structure includes S1: Divide the difficulty types of training samples, the operator divides the database images into training samples and test samples, and here divides the difficulty of training samples, among which, the difficulty of training samples is divided into Training easy samples and training hard samples; S2: Establish a sparse representation model. It should be noted that the sparse representation model is a model related to self-paced constraint regularization, and the discriminant training easy samples and training diffic...

Embodiment 3

[0110] refer to Figure 4 , This embodiment is different from the above embodiments in that this embodiment relates to the technical field of plant image classification and recognition, specifically a supervised plant image classification method based on a self-paced constraint mechanism. Specifically, see figure 1 , its main structure includes S1: Divide the difficulty types of training samples, the operator divides the database images into training samples and test samples, and here divides the difficulty of training samples, among which, the difficulty of training samples is divided into Training easy samples and training hard samples; S2: Establish a sparse representation model. It should be noted that the sparse representation model is a model related to self-paced constraint regularization, and the discriminant training easy samples and training difficult samples are brought into the sparse representation in turn. Training in the model, it needs to be emphasized that th...

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 discloses a supervised image classification method based on a self-paced constraint mechanism. The method comprises the following steps: dividing difficult types of training samples; establishing a sparse representation model, and substituting samples into the sparse representation model for training; obtaining an image classification model and a prediction model; constructing a category decision-making device, wherein the training sample difficult type comprises a training easy sample and a training difficult sample, and the division training sample difficultly-easy types are divided by adopting a self-step constraint matrix. According to the invention, the training samples are divided through the self-paced constraint matrix; the easy training sample and the difficult training sample are sequentially substituted into a defined sparse representation model for continuous training; a specific self-step constrained image classification scheme can be formed, more judgment information can be conveniently utilized, robustness is achieved on sample noise, and therefore the problem that a supervised dictionary learning mechanism is not suitable for complex samples containingnoise and huge intra-class changes can be solved, and the image recognition effect is improved.

Description

technical field [0001] The invention relates to the technical field of image classification and recognition, in particular to a supervised image classification method based on a self-procedural constraint mechanism. Background technique [0002] Classifying natural images containing a large number of object categories is one of the most challenging problems in pattern recognition, and mainstream solutions include wavelet relational vector machines (WRVM), global and local saliency feature encoding, and bag-of-words models (bow), Previous image classification algorithms have focused on obtaining visual representations of image features while ignoring specific class information. In order to find a more suitable method for data representation, a large number of schemes have been developed to solve this problem. Recently, these have been developed In the model of , the sparse representation classification technology with supervision has attracted many people's interest because o...

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): G06K9/62
CPCG06F18/24G06F18/214
Inventor 张涛于宏斌冯长安葛格石慧许志强崔光明潘详
Owner JIANGNAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products