An image processing method and terminal

Abstract

An embodiment of the present invention provides an image processing method and a terminal. The method includes: obtaining a positive sample set and a negative sample set; performing smoothing processing on the positive sample set and the negative sample set to obtain a target positive sample set and A target negative sample set; respectively performing integration channel feature extraction on the target positive sample set and the target negative sample set to obtain X first target feature sets; for each first target feature set in the X first target feature sets The target feature set performs pixel difference feature extraction to obtain the X second target feature sets, wherein each of the X second target feature sets contains a plurality of pixel difference features; using at least one The boosting decision tree classifies the X second target feature sets to obtain a target classifier. Through the embodiments of the present invention, a classifier with better feature screening ability and faster calculation speed can be obtained without performance degradation.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method and a terminal. Background technique [0002] In the existing technology, face detection is a very basic research direction in the field of vision, and its application range is very wide, such as security, smart business, robotics, human-computer interaction and other fields. Since the human face is a non-rigid object, it is easily disturbed by the external environment, such as weather, light, expression, posture, camera distortion and other factors, the difficulty of detection is obvious. Commonly used face detection methods include early algorithms based on face geometry, template matching algorithms, machine learning-related algorithms, and popular deep learning algorithms in recent years. [0003] Among the existing face detectors, the feature expression of a class of face detectors is relatively complex, such as the 10 channel fea...

AI Technical Summary

Problems solved by technology

[0003] Among the existing face detectors, the feature expression of a class of face detectors is relatively complex, such as the 10 channel features in the integral channel graph and the HOG feature in DPM. Although they show good performance in face detection, the computational It is too complex, the amount of feature calculation is large, and there is large redundant information, which makes it difficult to meet the requirements of real-time applications

Images