Counting method and device based on windows and multi-class incremental learning

Abstract

The invention provides a counting method and device based on windows and multi-class incremental learning, and the method and device make the most of the characteristic that the shape of a target is regular, build the direct relation between pixels and the number, reduce the accumulative errors, achieve the quick counting, allow objects to be adhered, and neglect the non-uniform density and quality factors. In order to solve a problem that the limit of a shooting angle enables the pixels of each region of a target image to have errors during the image collection, the method and device enable arange to be divided into regions through windows, and perform the independent counting through each window, so as to reduce errors. The device employs a camera obscura for avoiding the interference caused by an external light source, and is very low in requirements on the external environment. A multi-window template is used for the dividing of a counting region, and avoids the rolling of a target object and the adhering of the adjacent windows. The method and device achieve the high-accuracy quick counting of regular objects which are similar to an industrial sealed felt, are light in weight, are small in size and are not uniform in density.

Description

technical field [0001] The invention relates to image processing and machine learning technology, in particular to fast counting of regular objects with light weight, small volume and uneven density. Background technique [0002] Industrial sealing felt pad is a sealing gasket made by punching, which has the functions of sealing, heat insulation, sound insulation, shockproof, filtering, etc. It is widely used in various industrial fields such as home appliances, musical instruments, sports equipment, automobiles, and cultural products. , Accurately calculating the number of felt pads is very important to ensure the economic benefits of the manufacturer. [0003] The basic characteristics of felt pads are small size, light weight, and regular shape. Since the processed raw materials contain different types of wool, the final finished product will have uneven density and thickness due to the length and thickness of the wool, resulting in errors. The traditional methods are ge...

AI Technical Summary

Problems solved by technology

The weighing method requires that the weight of the weighing object is basically the same and meets the minimum unit of measurement, but the felt pad is small in size and light in weight, and uneven density and thickness are likely to cause large errors

The manual counting method is relatively slow, inefficient, and easily affected by human factors, occupying and wasting human resources

[0004] How to improve the efficiency and accuracy of counting regular objects with light weight, small volume and uneven density similar to industrial sealing felt pads is an urgent problem to be solved

Images