Online measurement method and device of dimensions of massive agricultural products based on machine vision

Abstract

The invention discloses an online measurement method and device of dimensions of massive agricultural products based on machine vision. The method comprises the following steps: setting a clocked flip-flop camera to acquire images of one-frame massive agricultural products at certain intervals along the conveying direction of the massive agricultural products according to the conveying rate of a conveyor belt; preprocessing the acquired images of the massive agricultural products and separating the massive agricultural products from own backgrounds; extracting the connected regions to obtain the independent massive agricultural product, computing the areas of the massive agricultural products and removing the massive agricultural products with unqualified areas, then computing the minimumrectangle containing the massive agricultural products with qualified areas and computing the degree of fitting of the rectangle; and judging the massive agricultural products with qualified degree of fitting and dimensions but with difference beyond the set threshold to be the massive agricultural products with unqualified dimensions and computing the qualified rate of the massive agricultural products. The method has the advantages of more objective and fair results and no damage to human health and sanitation of the massive agricultural products.

Description

technical field [0001] The invention relates to the field of on-line quality detection in an automated production process, in particular to an on-line measurement method and device for the size of block agricultural products based on machine vision. Background technique [0002] Machine vision is a comprehensive technology that integrates digital image processing, machinery, control, lighting, optics, computer software and hardware and other technologies. Machine vision system can realize non-destructive detection of products and quickly obtain a large amount of information. Therefore, machine vision technology, as an important detection method, has attracted increasing attention and is widely used in the fields of finished product inspection and quality control. [0003] The qualification rate of raw-cut agricultural products is mainly determined by the two appearance characteristics of the size and color of the agricultural products. In machine vision, different color inf...

AI Technical Summary

Problems solved by technology

The sensory evaluation is to sort the qualified and unqualified lumped agricultural products by judging the size and color of the lumped agricultural products one by one by trained professional sorting personnel, but the sensitivity of human sensory organs is limited. The interference of factors such as experience, mental state, physical condition, and surrounding environment, and long-term tedious repetitive work can easily cause visual fatigue, thereby affecting the accuracy of the sorting results

At present, there is no method and device for automatic on-line detection of the qualified rate of block agricultural products by using machine vision

Images