Method for detecting swelling capacity of starch particles in gelatinization process based on computer vision

Abstract

The invention discloses a gelatinization process starch particle swelling capacity detection method based on computer vision. According to the method, starch images collected in different gelatinization stages are preprocessed through an algorithm, edge recognition extraction, edge optimization, pixel filling, pixel recognition and statistics and swelling capacity detection are conducted on starchparticles, and intelligent detection of particle form changes in the gelatinization process is achieved through pixel changes; wherein the algorithm is a combination of an rgb2gram algorithm, an improved canny algorithm, mathematical morphology, a flooding filling algorithm and a swelling capacity detection algorithm. According to the invention, a computer vision technology is applied to starch particle swelling property determination for the first time, the automation degree is high, detection efficiency is high, subjective vision difference of observers can be avoided, manual measurement errors are reduced, and measurement accuracy can reach 95% or above. The quantitative method is used for observing and researching the morphological change of starch particles on line and intelligentlydetecting the swelling capacity of the starch particles.

Description

technical field [0001] The invention belongs to the technical field of food science and engineering, and in particular relates to a computer vision-based method for detecting the swelling capacity of starch granules in the gelatinization process. Background technique [0002] As a raw material with wide sources and low price, starch has been widely used in food, paper making, chemical industry, medical treatment and other fields. As the most important characteristic of starch, gelatinization affects its processing behavior and product performance. During the gelatinization process, the starch granules swell gradually, the crystal structure disappears, and finally the granules are completely destroyed. The swelling ability of starch refers to the water swelling degree of granules as the temperature rises during the gelatinization process, which is closely related to the structural arrangement and functional properties of starch molecules. Accurate determination of starch sw...

AI Technical Summary

Problems solved by technology

Since the starch gelatinization image obtained by a digital camera is an RGB three-channel image, the features represented by the three RGB channels are all different and the photo format (1024×768×3), if it is directly used for detection without processing, it will cause a lot of data processing If it is too large, it will take a long time to detect the problem

The problem with the traditional canny algorithm is that when setting the double-threshold interval, it needs to be manually set before detection, and it needs to be adjusted several times depending on the final detection effect.

And different types of starch, the gelatinized image is also very different

It will take a certain amount of time to manually adjust the parameters

Although there are many auxiliary threshold selection algorithms, when the auxiliary double threshold is selected, the effect of the threshold interval is poor as the starch type changes.

Images