Image feature extraction method and apparatus
An image feature extraction and image technology, applied in the field of image recognition, can solve problems such as inaccurate face recognition results, and achieve the effect of improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0054] The embodiment of the present invention provides an image feature extraction method, such as figure 1 As shown, the method can include:
[0055] Step 101: Divide the image into blocks to obtain each image block of the image, where any image block has an overlapping area with at least one of the other image blocks in the image except the own image block.
[0056] Here, the method provided by the embodiment of the present invention is mainly applied to the extraction of facial features. The image that needs to be extracted is generally a facial image. Therefore, before this type of image is divided into blocks, the part that does not contain facial information can be cropped in advance. Such as figure 2 As shown, the image includes the face and upper body of the person. Therefore, the image can be cut out except for the face of the person to obtain image 3 The picture shown is then divided into blocks to reduce the feature generation of useless information.
[0057] For most i...
Embodiment 2
[0105] The embodiment of the present invention provides an image feature extraction device 20, such as Picture 8 As shown, the device 20 may include:
[0106] The block division unit 201 is configured to block an image to obtain each image block of the image, wherein any image block has an overlap with at least one of the other image blocks in the image except its own image block area.
[0107] The extraction unit 202 is configured to extract the features of each image block.
[0108] In this way, if the method of the embodiment of the present invention is used for image segmentation, any image block obtained will have an overlapping area with other image blocks. Therefore, the features of the overlapping area will be extracted multiple times; accordingly, the extracted The features of the image will increase, and the features included in these features that contain effective information (information that needs to be recognized) will also increase. In this way, more features contai...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


