Search

To increase productivity in agricultural production, speed, and accuracy is the key requirement for long-term economic growth, competitiveness, and sustainability. Traditional manual paddy rice seed classification operations are costly and unreliable because human decisions in identifying objects and issues are inconsistent, subjective, and slow. Machine vision technology provides an alternative for automated processes, which are nondestructive, cost-effective, fast, and accurate techniques. In this work, we presented a study that utilized machine vision technology to classify 14 Oryza sativa rice varieties. Each cultivar used over 3,500 seed samples, a total of close to 50,000 seeds. There were three main processes, including preprocessing, feature extraction, and rice variety classification. We started the first process using a seed orientation method that aligned the seed bodies in the same direction. Next, a quality screening method was applied to detect unusual physical seed samples. Their physical information including shape, color, and texture properties was extracted to be data representations for the classification. Four methods (LR, LDA, k-NN, and SVM) of statistical machine learning techniques and five pretrained models (VGG16, VGG19, Xception, InceptionV3, and InceptionResNetV2) on deep learning techniques were applied for the classification performance comparison. In our study, the rice dataset were classified in both subgroups and collective groups for studying ambiguous relationships among them. The best accuracy was obtained from the SVM method at 90.61%, 82.71%, and 83.9% in subgroups 1 and 2 and the collective group, respectively, while the best accuracy on the deep learning techniques was at 95.15% from InceptionResNetV2 models. In addition, we showed an improvement in the overall performance of the system in terms of data qualities involving seed orientation and quality screening. Our study demonstrated a practical design of rice classification using machine vision technology.

The rice kernel inside a hull is composed of the embryo and endosperm. The embryo or germ of the rice seed will grow and become the shoot and the root parts of a seedling, while the endosperm is an important nutrient source for the embryo in the early stages. Hence, the health of seedlings depends particularly on the sizes of the embryo and endosperm. In this work, we propose and experimentally demonstrate how the embryo and endosperm areas of brown rice can simply be determined. Our key idea is based on the utilization of a smart mobile device equipped with our specifically designed lens module arranged in a simple cross-polarization imaging configuration for acquiring a rice grain image upon the illumination of a white light source and then spatially analyzing the sizes of embryo and endosperm areas. The prototype shows promising results in identifying the sizes of the embryo and endosperm within 2 s per seed with a measurement error of < 9 % compared with the use of off-the-shelf image editing software. In addition, the prototype is in a small package of 20 × 32.5 × 6.5 c m 3 with 4 kg weight, thus showing high potential to perform in the real scenario.

In this paper, automatic fever screening system is proposed and experimentally implemented using an IR camera and a mobile phone. Our system locates position of patients automatically using face detection algorithm on RGB image and obtains temperature from IR image at detected location. Advantages are fast, portable, non-contacting and simultaneously temperature measurement. Furthermore, face detection algorithm allows the system to track patient's face position. Hence, robust and non-contacting temperature measurement can be properly done even patients are not stand still. Our system has been field-tested to measure temperature and screen ill patients at a children medical clinic. In this experiment, the system is calibrated to measure temperature of patients at 1 meter away and gives an alarm sound when the measured temperature is above the desired setting threshold. According to experimental results, the correlation coefficient between temperature obtained from our system and commercial infrared forehead skin thermometer [2] is more than 0.80. In addition, our system achieves a 100% sensitivity and 70% specificity. Although our approach loses specificity, all fever patients are identified correctly. Thus, they are significantly correlated. Therefore, this system can reliably estimate body temperature of patients and can be used for effectively pre-screening fever patients.

In this paper, a novel and simple method based on an all-pass filter is presented by using the benefits of a pole re-position technique. The gains at frequencies of of each single notch filter are adjusted by adding N 1 tuning variables. The proposed method ensures that the passband gains are uniformly flat, the notch frequencies exactly meet the specifications, and the realized 3 dB bandwidths are approximately the same as those specified. This technique is very useful for designers because there are only N 1 tuning variables required to adjust, and it does not need a complicated mathematical calculation. Although this technique is simple and easy to implement, it requires many iterations to find a suitable parameter for making the passband gain between two notch frequencies uniformly flat. Hence in this paper, three searching algorithms have been applied to reduce the number of iterations. We obtain a faster search and a closer frequency response to the ideal one.