BP neural network image compression method based on improved image block classification algorithm
A BP neural network and classification algorithm technology, applied in the field of image data compression of modern communication networks, can solve problems such as poor compression performance, achieve good compression performance, solve poor compression performance, and improve accuracy.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0018] A kind of BP neural network image compression method based on improved image block classification algorithm, this method is to adopt following steps to realize:
[0019] Step 1: Calculate the mean square error SMSE of each image block and the mean square error FIMSE of the entire image according to the mean value SIM of the image sub-block;
[0020] Step 2: Use the improved image block classification algorithm to reasonably select the classification threshold δ of the image block to divide the image block into three types of image sub-blocks, namely image smooth block, target block, and edge block;
[0021] Step 3: Normalize the classified image sub-blocks, so that the pixel value of each pixel is suitable for the requirements between 0 and 1 of the input data set of the BP neural network;
[0022] Step 4: Use the Levenberg-Marquardt algorithm with the largest memory requirement and the fastest convergence speed to train the BP neural network to obtain a compressed data...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

