Method and device for image recognition
An image recognition and image technology, applied in the field of image recognition, can solve the problems such as the recognition accuracy rate will not be reached, the efficiency of category label pictures is low, and achieve the effect of improving efficiency.
Active Publication Date: 2020-06-02
BEIJING XIAOMI MOBILE SOFTWARE CO LTD
View PDF12 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] The recognition accuracy of the general image recognition model will not reach 100%. If the image recognition model needs to recognize a large number of pictures, there will be many pictures with wrong category labels added to the corresponding large number of pictures. Find images with wrong category labels, which leads to low efficiency in obtaining pictures with wrong category labels
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
[0054] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present disclosure as recited in the appended claims.
[0055]An exemplary embodiment of the present disclosure provides an image recognition method, which can be implemented by a server. The server can be a background server of the application using image captcha. The server can be provided with a processor, a memory, a transceiver, etc., the processor can be used to process the process of image recognition, the memory can be used to stor...
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 present disclosure relates to an image recognition method and device, and belongs to the technical field of computers. The method includes: adding the first image and the first category tag correspondingly to the image verification code database; in the process of verifying the terminal verification code based on the image verification code database, if the If the correct verification code image corresponding to the first category label includes the first image, and the verification code image selected by the terminal does not include the first image, record a category label mismatch event for the first image ; When the recorded number of category label mismatch events corresponding to the first image satisfies a first preset quantity condition, mark the first image as mismatching with the first category label. By adopting the present disclosure, the efficiency of identifying images with wrong class labels can be improved.
Description
technical field [0001] The invention relates to the field of computer technology, in particular to an image recognition method and device. Background technique [0002] With the development of computer technology, images in the sample image database can be trained based on deep learning algorithms to obtain image recognition models (such as CNN (Convolutional Neural Network) can be obtained by training images in the sample image database based on convolutional neural network algorithms Network, convolutional neural network) training model)), the image recognition model can identify the category of the picture, and add the corresponding category label to the picture. [0003] The recognition accuracy of the general image recognition model will not reach 100%. If the image recognition model needs to recognize a large number of pictures, there will be many pictures with wrong category labels added to the corresponding large number of pictures. Find out the pictures with the wr...
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
CPCG06F18/22
Inventor 陈志军万韶华龙飞
Owner BEIJING XIAOMI MOBILE SOFTWARE CO LTD