Image recognition method, device, medium and electronic equipment
An image recognition and image technology, applied in the computer field, can solve problems such as inability to cross-platform and efficient use of cross-platform
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0069] combined with figure 1 In this embodiment, a cross-platform image is input, and the recognition of the UI area in the image is realized through corresponding steps, specifically:
[0070] Step S101, acquiring an image to be recognized. The image in this embodiment can be selected as a cross-platform image, that is, an image that may have multiple UI areas. Considering that terminal devices (such as mobile phones, computers, etc.) generally have its screen capture function, the image can be a screen capture image. Use the screen capture function of the terminal device to perform a screen capture operation on a screen with multiple user interfaces to obtain a cross-platform screenshot image, which contains one or more UI areas, and the screen capture image is used as an image to be recognized, from which the UI area is extracted Information, the UI area information includes UI area location and category information.
[0071] Step S102, performing hierarchical segmentati...
Embodiment 2
[0131] See attached Image 6 , the difference between this embodiment and embodiment 1 is that the first potential UI area is determined when the straight line is extracted after the image is input, and the second potential UI area is generated after the image is synchronously input into the deep learning training module, and the above-mentioned first potential UI area is combined with The second potential UI area is compared and analyzed to obtain accurate UI information.
[0132] With reference to Embodiment 1, steps S601-S602 are the same as Embodiment 1 and will not be repeated here. Next, step S603 is to identify straight line features on the segmented image to determine the first potential user interface area. This embodiment also uses the method based on image morphology in OpenCV to perform image segmentation operations, and uses the line segment detector LSD to extract straight line features, and then determines potential UI regions.
[0133] Step S604, performing tr...
Embodiment 3
[0136] Such as Figure 7 As shown, according to a specific embodiment of the present invention, on the other hand, the present invention provides an image recognition device, including:
[0137] The obtaining unit 701 is configured to obtain an image to be recognized. The image can be a screenshot image, and the screenshot function of the terminal device can be used to perform a screenshot operation on a screen with multiple user interfaces to obtain a cross-platform screenshot image. The screenshot image includes one or more UI areas, and the screenshot image is used as The image to be recognized is extracted from the UI area information, and the UI area information includes UI area position and category information.
[0138] The segmentation unit 702 is configured to perform hierarchical segmentation on the image. There are some techniques for hierarchical image segmentation, such as frequency segmentation, gray threshold segmentation, histogram segmentation, feature space...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


