In book: Food Policy, Control and Research, Chapter: 6, Publisher: Nova Biomedical, pp.149-186


Rice is an important staple food throughout the world. Its market quality is mainly based on physical properties such as colour, chalkiness, length, width, shape, density and the number of broken rice kernels. These grain quality indicators can be determined by flatbed scanning (FBS) and image analysis (IA). The rice kernels were distributed in a single layer on the glass plate of the scanner and covered with a black sheet of paper. To facilitate the separation of touching rice kernels on the glass plate of the scanner, a sample matrix with small holes can be used. A fully automatic procedure was developed using freeware IA software and standard spreadsheet software. The FBS procedure requires a PC with standard desktop scanner. The FBS method is fast, easy to use and cheap. It allows the visualisation and quantitative physical analysis of rice. The method for the determination of the size and size distribution of rice and the amount of broken rice kernels was tested on parboiled and regular-milled white rice of different varieties and compared to manual analysis by weighing after visual separation of whole and broken kernels and by measuring the length and width of rice kernels using a sliding calliper. It yields the same accuracy and better precision than the more time-consuming manual method. Beside the colour of individual rice kernels also the colour of a thick layer of rice could be measured. This so-called bulk colour provides an objective assessment of the rice colour using the CIE L*a*b* colour space. Determination of the bulk colour was tested on milled raw rice and processed rice (puffed and popped) and compared to the analysis using a chromatic reflectometer. FBS-IA can monitor colour changes with the same accuracy and better precision than a chromatic reflectometer. Analysis by FBS-IA takes about 3 min per sample compared to about 30 min for manual analysis (broken rice kernels, length and width). FBS can also be used for the characterisation of other cereal grains and their products such as breakfast cereals, snacks, dry pasta and meals.


Available from: Gerard VAN Dalen
  • Source
    • "The most important steps are image data collection, feature extractions (such as shape, size, color, and orientation etc.) and their representation, model/algorithm selection and learning, and model testing. For example, Gerard van Dalen [8] extracted characteristics of rice using flatbed scanning and image analysis. Jose D Guzman et al. [9] investigated grain features extracted from each sample image. "
    [Show abstract] [Hide abstract] ABSTRACT: This paper presents a system for automated classification of rice variety for rice seed production using computer vision and image processing techniques. Rice seeds of different varieties are visually very similar in color, shape and texture that make the classification of rice seed varieties at high accuracy challenging. We investigated various feature extraction techniques for efficient rice seed image representation. We analyzed the performance of powerful classifiers on the extracted features for finding the robust one. Images of six different rice seed varieties in northern Vietnam were acquired and analyzed. Our experiments have demonstrated that the average accuracy of our classification system can reach 90.54% using Random Forest method with a simple feature extraction technique. This result can be used for developing a computer-aided machine vision system for automated assessment of rice seeds purity.
    Full-text · Conference Paper · Oct 2015
  • [Show abstract] [Hide abstract] ABSTRACT: Determination of rice quality is a key function for rice research and rice industry. Traditionally, rice quality parameters were performed separately by human visual inspection. It is labor-intensive and time-consuming. In this paper, a novel analysis method was proposed to determine multi rice quality parameters simultaneously. On the glass of a flatbed scanner, 35 g rice kernels was spread and imaged. Then, the length, width, aspect ratio, head rice yield, percentage of chalky rice, chalkiness, and transparency grade were obtained after simply processing the acquired image. The developed method for the determination of rice quality was tested on 507 milled rice samples and compared to the traditional manual analysis method. The regression coefficients (R) were 0.9916, 0.9691, 0.9938, 0.9929, 0.9649, and 0.9377 for length, width, aspect ratio, head rice yield, percentage of chalky rice, and chalkiness, respectively. The accuracies of length, width, aspect ratio, and head rice yield determined by the developed method were 100, 100, 100, and 92.1 % respectively. The results indicated that the developed method was a useful and alternative method for determining rice quality.
    No preview · Article · Jan 2014 · Food Analytical Methods