Learning type image processing method, system and server

Abstract

The embodiment of the invention discloses a learning type image processing method, a system and a server. The method comprises the following steps of acquiring a to-be-detected target image; inputtingthe to-be-detected target image into a preset convolution neural network model; obtaining classification data outputted by the convolution neural network model in response to the input of a human face image, wherein the convolution neural network model takes a loss function as a constraint condition and the cosine distance of the in-class features in the classification data is defined to tend tobe the Euclidean distance; acquiring the classification data, and performing content understanding on the to-be-detected target image according to the classification data. According to the invention,the classification data are screened through a loss function based on the cosine distance in the joint loss function. The cosine distance in the classification data is maximized. However, the color ina simple image is single, and the maximization of the cosine distance with relatively strong internal convergence is achieved. The cosine distance can tend to be a calculation result of the Euclideandistance, so that the implementation complexity is simplified.

Description

technical field [0001] Embodiments of the present invention relate to the field of image processing, in particular to a learning image processing method, system and server. Background technique [0002] With the development of deep learning technology, the convolutional neural network has become a powerful tool for extracting face features. For the convolutional neural network with a fixed model, the core technology is how to design the loss function so that it can effectively supervise the convolutional neural network. Convolutional neural network training, so that the convolutional neural network has the ability to extract face features. [0003] The loss function commonly used in the prior art based on Softmax+Centerloss is the most commonly used supervised loss function because of its good effect and simple training. The Centerloss loss function refers to counting an average center point for each class, and then using the The Euclidean distance between each sample and t...

AI Technical Summary

Problems solved by technology

[0004] The inventors of the present invention found in the research that the loss function based on Softmax+Centerloss can better solve complex samples compared with Softmax, but it does not optimize some simple samples, and instead increases part of the cosine distance measure. Although the intra-class distance of simple samples can better express the facial features in general, the feature expression of some simple samples still needs to be further optimized

Images