Image transformation method and apparatus, storage medium, and computer device

An image transformation method, applicable to a computer device, the method comprising:

• obtaining a transformed image corresponding to an original image;
• performing frequency domain transformation on the transformed image to obtain a converted brightness matrix of the transformed image in a frequency domain space;
• extracting a pixel value of an identification image from the converted brightness matrix, the identification image being an image obtained by converting identification information of the original image;
• and
• performing image identification on the identification image to obtain the identification information of the original image,
• wherein the extracting the pixel value comprises:
• determining an image embedding bit in the converted brightness matrix;
• obtaining a pixel value of the image embedding bit in the converted brightness matrix;
• determining an embedding intensity factor, and determining a pixel adjustment range by using a pixel conversion formula, which is based on the embedding intensity factor and the pixel value of the image embedding bit in the identification image, wherein one of different pixel conversion formulas is selected according to the pixel value of the image embedding bit;
• and
• determining the pixel value of the identification image based on the pixel value of the image embedding bit in the converted brightness matrix and the pixel adjustment range, to obtain the identification image.

An image transformation apparatus, comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• first obtaining code configured to cause the at least one processor to obtain identification information of an original image;
• information conversion code configured to cause the at least one processor to convert the identification information to an identification image;
• first frequency domain transformation code configured to cause the at least one processor to perform frequency domain transformation on the original image to obtain a pixel matrix of the original image in a frequency domain space;
• decomposition code configured to cause the at least one processor to perform matrix decomposition on the pixel matrix to obtain an image brightness matrix;
• pixel conversion code configured to cause the at least one processor to convert pixel values of corresponding pixels in the image brightness matrix based on pixel values of pixels in the identification image to obtain a converted brightness matrix;
• and
• inverse transformation code configured to cause the at least one processor to perform inverse frequency domain transformation on the converted brightness matrix to obtain a transformed image including invisible identification information, and add the invisible identification information to the original image,
• wherein the pixel conversion code comprises:
• determination sub-code configured to cause the at least one processor to determine an image embedding bit in the identification image;
• pixel value obtaining sub-code configured to cause the at least one processor to obtain a pixel value of the image embedding bit in the identification image;
• and
• pixel value conversion sub-code configured to cause the at least one processor to:
• determine an embedding intensity factor, and determine a pixel adjustment range by using a pixel conversion formula, which is based on the embedding intensity factor and the pixel value of the image embedding bit in the identification image, wherein one of different pixel conversion formulas is selected according to the pixel value of the image embedding bit;
• and
• convert the pixel value of the image embedding bit in the image brightness matrix based on the pixel adjustment range, to obtain the converted brightness matrix.