Electric power business hall dressing normalization identification method based on color and Hu moment matching

Abstract

The present invention provides an electric power business hall dressing normalization identification method based on color and Hu moment matching. The method comprises: extracting a dressing color analysis area, wherein the process comprises the capture of fact identification, human body upper body identification and rectangle dressing color analysis area; performing color matching analysis of the captured rectangle area, and performing matching analysis through extraction of the maximum color of the identification area and the maximum color of the clothes in the frock picture base; extracting the identified upper body clothes outline and calculating the Hu moment, and performing Hu moment matching of the Hu moment and the outline Hu moment of the clothes in the frock picture base; and finally weighing and synthesizing the color matching result and the Hu moment matching result to obtain a clothing analysis result. The electric power business hall dressing normalization identification method based on the color and Hu moment matching solves the phenomenon that it is easy to generate errors in the traditional clothing identification process caused by single identification factor, and realizes the intelligence of the electric power business hall dressing management so as to reduce the work of the manual supervision management and improve the validity and the normalization of the work of the power electric business hall.

Description

technical field [0001] The invention relates to a dress normative identification method for electric business halls based on color and Hu moment matching. Background technique [0002] In the traditional clothing recognition technology, most of them use a single factor as the matching condition, and use a single color matching or outline matching as the matching condition. The single matching condition has a certain impact on the matching accuracy, and the obtained matching results are often Lack of sufficient convincingness is prone to certain matching errors. Therefore, a single matching condition often cannot support the matching effect well. [0003] In addition, traditional image contour recognition and matching technologies mostly complete the final matching and recognition function through feature extraction, template establishment, and pattern matching. They have a relatively good matching effect on static image contour matching. During the process, because the clot...

AI Technical Summary

Problems solved by technology

[0002] In the traditional clothing recognition technology, most of them use a single factor as the matching condition, and use a single color matching or outline matching as the matching condition. The single matching condition has a certain impact on the matching accuracy, and the obtained matching results are often Lack of sufficient persuasiveness, prone to certain matching errors, therefore, a single matching condition often cannot support the matching effect well

[0003] In addition, traditional image contour recognition and matching technologies mostly complete the final matching and recognition function through feature extraction, template establishment, and pattern matching. They have a relatively good matching effect on static image contour matching. During the process, because the clothes of the people in the monitoring area may appear tilted or out of shape, the ordinary contour matching technology cannot deal with the contour deformation caused by the tilt or out of shape of the clothes, and the obtained matching effect cannot avoid the out of shape problems due to the inclination of the clothes. The error caused by the matching process will produce different results due to clothing tilt, translation and other issues, so the matching accuracy also produces a certain error

Images