Filter bank training method and system and image key point positioning method and system

Abstract

The invention relates to a filter bank training method. The filter bank training method comprises the steps that first, a training image which has a target position mark is preprocessed to obtain a denoising training image; second, initial clustering is conducted on the denoising training image, and the image is decomposed into K training sets; third, an ideal filter output model is designed according to the target position mark in the training image; fourth, K total filter models are obtained by training according to the ideal filter output model to constitute a filter bank; fifth, whether an image sample set is convergent or not is judged, if yes, the seventh step is executed, and otherwise the sixth step is executed; sixth, whether the convergent frequency reaches a preset threshold value or not is judged at present, if yes, the seventh step is executed, otherwise, classification is conducted again to obtain K new training sets, the K new training sets replace the K training sets, and the fourth step is executed again; seventh, the filter bank is stored, and the training process of the filter bank is completed. The filter bank training method has better distinguishing performance to targets, and improves the accuracy and the precision of positioning to a certain extent.

Description

technical field [0001] The invention relates to an image processing technology, in particular to a filter bank training method and system and an image key point positioning method and system, belonging to an image key point positioning device, especially suitable for the key points of targets such as faces and pedestrians in images or videos. point positioning. Background technique [0002] The existing image key point localization methods are mainly divided into three categories: object feature-based methods, statistics-based methods and hybrid methods. [0003] The method based on the target feature distinguishes it on the image according to the inherent characteristics of the feature point target, so as to realize the positioning function. Common features include shape, intensity contrast, texture, etc. A deformable model proposed by Yuille et al. for eye positioning (see A.L. Yuille, P.W. Hallinan, D.S. Cohen, Feature extraction from faces using deformable template, Int...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that the existing traditional filters all use a single filter template to perform unified filtering processing on all images, because the required positioning target has many appearances and shapes among the images. The change of the change and the impact of noise make it difficult for a single filter template to cope with the differences in the appearance, expression, posture, etc. of the target between different images; Inaccurate positioning caused by the problem, providing a filter bank training method and system and image key point positioning method and system

Images