Sample labeling method and computer storage medium
A sample labeling and sample image technology, applied in the computer field, can solve the problems of low efficiency of manual labeling and poor labeling effect, and achieve the effect of high character detection accuracy, avoiding heavy workload and improving recognition accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0013] figure 1 This is a schematic flowchart of a sample labeling method provided in Embodiment 1 of the present invention. Such as figure 1 As shown, according to the embodiment of the present invention, the sample labeling method includes:
[0014] S101: Obtain a sample image to be labeled.
[0015] Among them, the sample image to be labeled is used for subsequent training of the machine learning model as a training sample image. In the embodiment of the present invention, the training sample image is an image including character information, where the characters include, but are not limited to: text, letters, numbers, and symbols.
[0016] S102: Perform connected domain analysis and character category recognition on the sample image to be labeled, and generate a first detection and recognition result, where the first detection and recognition result includes a first character position indicating the position of each character in the sample image to be labeled Information and in...
Embodiment 2
[0037] figure 2 This is a schematic flowchart of a sample labeling method provided in Embodiment 2 of the present invention. Such as figure 2 As shown, according to the embodiment of the present invention, the sample labeling method includes:
[0038] S201: Obtain a sample image to be labeled.
[0039] Among them, the sample image to be labeled is used for subsequent training of the machine learning model as a training sample image. In the embodiment of the present invention, the training sample image is an image including character information, where the characters include, but are not limited to: text, letters, numbers, and symbols.
[0040] S202: Determine whether there is a labeled data file corresponding to the sample image to be labeled.
[0041] The first thing to note is that this step is optional.
[0042] The marked data file includes information of marked character positions of the sample image to be marked and information of marked character types. The information of ...
Embodiment 3
[0074] According to an embodiment of the present invention, a computer storage medium is provided, the computer storage medium stores: an instruction for obtaining a sample image to be labeled; for performing connected domain analysis and character classification on the sample image to be labeled Recognize and generate a first detection and recognition result, where the first detection and recognition result includes instructions for indicating the first character position of each character in the sample image to be labeled and the first character category information ; Instructions for determining whether there is a first neural network model for detecting the position of characters in the image and a second neural network model for recognizing characters in the image; if it exists, through the first neural network The model and the second neural network model perform character detection and recognition on the sample image to be labeled, and generate a second detection and reco...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

