Abstract
Rice is the most consuming food all over the world and the market for rice is always high. In rice manufacturing industries the market demand is always centred on quality of rice. The analysis of grain type, grading, and quality criteria are still determined by skilled persons manually. Because it depends on a number of variables, including human factors, working conditions, cleaning and salvage recovery rates, this process is complex. Deep learning and image processing methods may be used to overcome this. In the food business, quality testing is becoming more significant for grading and classifying grains. In deep learning-based testing, we take into account both physical (grain form and size) and chemical (amylose content, gel consistency) features. The quality and grading of rice grains were examined using this proposed algorithm's average values for the features that were taken out of the network Since grain quality directly affects human health, it is very important for people. Thus, it is crucial to evaluate grain quality and spot low-quality components. The mix of physical and chemical properties makes up rice quality. Two physical traits are grain size and shape. Using canny edge detection, the derived physical characteristics are used to classify the rice grains. This essay offers a solution to the issue of quality analysis in the rice sector. Compared to conventional human-based inspection methods, computer vision-based inspection offers an option that is quick, accurate, convenient, and safe. This article offers a technique for determining the rice grain's quality and categorising it according to various breed types. In this we are going to use three types of rice grains: - 1. Basmati Rice 2. Sonamasoori Rice 3. jhilli Rice Key words: Image processing, CNN, Rice Grading.
Abstract from the paper’s OpenAlex record, shown for indexing and research. Copyright remains with the authors or the publisher. Read at the source ↗
The text the model read, with the source record’s inline markup (italics, sub- and superscripts) rendered and its character entities decoded; quote offsets refer to the raw text.
Claims 2
Claim · model-written summary
Canny edge detection was used to classify rice grains from physical characteristics.
- Taxon
- rice grains
Oryza sativae0 - Outcome
- classify the rice grainse0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“Using canny edge detection, the derived physical characteristics are used to classify the rice grains”
Claim · model-written summary
The proposed algorithm examined grain quality and grading using average extracted feature values.
- Taxon
- rice grainsOryza sativae0
- Outcome
- quality and grading of rice grainse0
Not reportedComparator
Organisms pictured · Representative pictures of the matched species, not figures from the paper.
Verbatim
e0“The quality and grading of rice grains were examined using this proposed algorithm's average values for the features that were taken out of the network”