An Image Classification Method Based on Deep Similarity Network
A classification method and similarity technology, which is applied in the field of deep network image classification, can solve the problems that the effect needs to be improved, the correlation of classified pictures is weak, and the accuracy of image classification is affected, so as to achieve the effect of improving the accuracy of image classification
Active Publication Date: 2021-05-25
杭州元凡视觉智能科技有限公司
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these deep learning models often use the pictures in the training picture library to train the model first, and then apply them to the actual picture classification after obtaining specific model parameters. Affects the actual image classification accuracy, the effect still needs to be improved
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiment is only one embodiment of the present invention, not all embodiments. Based on the embodiments of the present invention, other embodiments obtained by those skilled in the art without making creative efforts all belong to the protection scope of the present invention.
[0032] The embodiment of the present invention discloses an image classification method based on a deep similarity network, see figure 1 As shown, the method includes:
[0033] Step S1: Input training pictures, randomly select a specific number of pictures of a specified type from the specified training images as training images.
[0034] Step S2: Model training, by constructing a specific training model and inputting training pictures to the model for specific times of training...
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
Login to View More Abstract
The invention relates to an image classification method based on a deep similarity network, comprising: inputting a training image to a training model; using the training model to perform training for a specified number of times; initializing the image feature extraction model; inputting target image extraction features; Degree calculation; image classification using image feature similarity. The invention passes. Build a deep image feature extraction training model to conduct in-depth training on the specified training image and use the cross-entropy loss function to optimize the training model. When performing actual image feature extraction, add the feature value extracted from the training image to perform similarity calculations, and use this calculation model to achieve accurate images. Classification, the image classification method adding similarity calculation is proposed for the first time, which effectively improves the accuracy of image classification.
Description
technical field [0001] The invention relates to an image classification method based on a deep similarity network, in particular to a deep network image classification method in the field of video image recognition and classification processing. Background technique [0002] With the continuous development and mutual integration of multimedia and Internet technologies, pictures, as one of the most intuitive media forms for conveying information, are appearing in the Internet and people's sight with a trend of increasing geometric quantity, providing us with rich and multi-dimensional information At the same time, there are many redundant and garbage pictures due to the huge number. Therefore, how to classify and identify pictures is the premise of providing efficient picture retrieval and management, and it is also a technical issue that needs continuous optimization. [0003] At present, there are relatively mature image classification methods based on deep learning, and go...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62
CPCG06F18/214
Inventor 胡东平王兴刚
Owner 杭州元凡视觉智能科技有限公司