Fig 3 - uploaded by Md Towfiqur Rahman
Content may be subject to copyright.
Source publication
Tea (Camellia sinensis) has been found as an important medicinal beverage for human which is consumed all over the world. Primarily, the majority of tea is being cultivated in Asia and Africa, however it is commercially produced by more than 60 countries. Though substantial amount is produced, its processing system is still un-derdeveloped which le...
Context in source publication
Context 1
... into 8-bit gray level image. After then the image segmentation was done by thresholding which leads to search for adjacent pixels which have similar properties and within the ranges of defined threshold values. Region based 2 color threshold binarization was done to each image where the suitable threshold value (T) was found 42-162 as shown in Fig. 3. The binary images were then loaded into ImageJ Ver. 1.8.0 (Open-source Java based image processing program) software. From image features option under image measure was selected for obtaining the image pixel information from each granule. Image particle features like projected area, feret diameter, roundness and solidity [17] ...
Citations
... Computer vision technologies have emerged as promising tools for agricultural applications, including plant phenotyping, disease detection, and identification [7][8][9]. Over the years, numerous research initiatives on agricultural product processing have been initiated, with several techniques developed to identify and characterize leaf defects [9][10]. Recent literature highlights the widespread and efficient use of image processing techniques for disease detection in agriculture [11][12][13][14]. ...
In Bangladesh, tomato cultivation faces significant challenges due to its susceptibility to various microorganisms, parasites, and bacterial infections. Typically, the early symptoms of these diseases first appear in roots and leaves, complicating timely detection. This study addresses the challenge of timely and accurate detection of diseases in tomato plants, crucial for effective plant protection management. Conventional manual inspection methods are time-consuming and subjective, resulting in delays in implementing necessary protection measures. Therefore, an image processing technique and machine learning algorithms were used for rapid and robust detection of diseases in tomato plant leaves, aiming to streamline the detection process for chemical application responses. A dataset containing 250 images of tomato plant leaves were captured under varying light intensities, eye-level angles, and distances. Image augmentation techniques were applied to increase the dataset, resulting in a total of 529 images. These images were converted to LAB color images and then OTSU algorithm was used to segment leaf images and estimate the percentage of affected diseased areas. Various textural features were also extracted from segmented leaf images to create a training dataset. Machine learning algorithms, including Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and decision trees, were trained and evaluated using this dataset to classify images as healthy or diseased. The Quadratic SVM algorithm provided the highest test accuracy of 97.7% for the dataset. This nondestructive processing holds immense promise for improving disease detection efficiency and reducing losses in tomato production, both locally in Bangladesh and globally. ABSTRAK Di Bangladesh, budidaya tomat menghadapi tantangan yang signifikan karena kerentanannya terhadap berbagai mikroorganisme, parasit, dan infeksi bakteri. Biasanya, gejala awal penyakit-penyakit ini pertama kali muncul di akar dan daun, sehingga menyulitkan deteksi tepat waktu. Penelitian ini membahas tantangan deteksi penyakit yang tepat waktu dan akurat pada tanaman tomat, yang sangat penting untuk manajemen perlindungan tanaman yang efektif. Metode inspeksi manual konvensional memakan waktu dan subjektif, sehingga mengakibatkan penundaan dalam menerapkan tindakan perlindungan yang diperlukan. Oleh karena itu, teknik pemrosesan gambar dan algoritma pembelajaran mesin digunakan untuk mendeteksi penyakit pada daun tanaman tomat dengan cepat dan kuat, yang bertujuan untuk merampingkan proses deteksi untuk respons aplikasi kimia. Sebuah dataset yang berisi 250 gambar daun tanaman tomat diambil di bawah berbagai intensitas cahaya, sudut pandang, dan jarak. Teknik augmentasi gambar diterapkan untuk meningkatkan dataset, menghasilkan total 529 gambar. Gambar-gambar ini diubah menjadi gambar berwarna LAB dan kemudian algoritma OTSU digunakan untuk mensegmentasi gambar daun dan memperkirakan persentase area yang terkena penyakit. Berbagai fitur tekstur juga diekstraksi dari gambar daun yang telah disegmentasi untuk membuat dataset pelatihan. Algoritma pembelajaran mesin, termasuk Support Vector Machines (SVM), K-Nearest Neighbors (KNN), dan pohon keputusan, dilatih dan dievaluasi dengan menggunakan set data ini untuk mengklasifikasikan gambar sebagai gambar yang sehat atau sakit. Algoritma Quadratic SVM memberikan akurasi pengujian tertinggi sebesar 97.7% untuk dataset. Pemrosesan nondestruktif ini sangat menjanjikan untuk meningkatkan efisiensi pendeteksian penyakit dan mengurangi kerugian dalam produksi tomat, baik secara lokal di Bangladesh maupun global.
... Partial least squares regression (PLSR) was used to model the relationship between the data and saffron purity, presenting distribution plots related to saffron purity. M. T. Rahman et al. (2021) captured high-resolution images of tea particles with a digital color camera and analyzed the images to extract physical characteristics including projected area, roundness, circularity, diameter, aspect ratio, and firmness for quality assessment grading of tea (Camellia sinensis). Jia et al. (2022) used a digital camera to capture images of salmon eyes to nondestructively evaluate and predict salmon freshness. ...
Food fraud undermines consumer trust, creates economic risk, and jeopardizes human health. Therefore, it is essential to develop efficient technologies for rapid and reliable analysis of food quality and safety for food authentication. Machine vision–based methods have emerged as promising solutions for the rapid and nondestructive analysis of food authenticity and quality. The Industry 4.0 revolution has introduced new trends in this field, including the use of deep learning (DL), a subset of artificial intelligence, which demonstrates robust performance and generalization capabilities, effectively extracting features, and processing extensive data. This paper reviews recent advances in machine vision and various DL‐based algorithms for food authentication, including DL and lightweight DL, used for food authenticity analysis such as adulteration identification, variety identification, freshness detection, and food quality identification by combining them with a machine vision system or with smartphones and portable devices. This review explores the limitations of machine vision and the challenges of DL, which include overfitting, interpretability, accessibility, data privacy, algorithmic bias, and design and deployment of lightweight DLs, and miniaturization of sensing devices. Finally, future developments and trends in this field are discussed, including the development of real‐time detection systems that incorporate a combination of machine vision and DL methods and the expansion of databases. Overall, the combination of vision‐based techniques and DL is expected to enable faster, more affordable, and more accurate food authentication methods.
... With the rapid development of information technology, computer vision (Chouhan et al., 2020a(Chouhan et al., , 2021a) as a noncontact nondestructive detection technology has been gradually used to grade the quality of agricultural products such as citrus (Chakraborty et al., 2023), tea (Rahman et al., 2021), carrots (Deng et al., 2021), and apples (Mansuri et al., 2022). It has good safety performance and high detection accuracy. ...
Jujube is susceptible to biotic and abiotic adversity stresses resulting in abnormal phenotypic defects. Therefore, abnormal phenotype fruits should be removed during postharvest sorting to increase added value. An improved maximum horizontal diameter linear regression (MHD‐LR) method for size grading of jujube prior to detection of abnormal phenotypic defects was developed. The accuracy of the MHD‐LR model is 95%, with an error of only 0.95 mm. In addition, a method for detecting abnormal phenotypic defects in jujube was established. It can effectively and accurately classify seven kinds of jujube phenotypes (regular, irregular, wrinkled, moldy, hole‐broken, skin‐broken, and scarred). The data augmentation method based on linear interpolation can effectively expand the dataset with a variance of only 0.0006. Support vector machine‐decision tree (SVMDT), logistic regression, back propagation neural network, and long short‐term memory network models were established to classify jujube samples with different phenotypes, with accuracies of 99.57%, 99.00%, 99.14%, and 99.29%, respectively. The results showed that the SVMDT model had higher accuracy and explainability. This research is expected to provide a new method to improve the precise classification of abnormal phenotypic defects in postharvest jujube.
... Automated vision inspection systems are widely used in various industrial areas, e.g., in checking the quality of wooden floors [2], textiles [3], cigarette packs [4], metal elements [5,6], and 3D prints [7]. Food quality evaluation, for example, beef [8], cheese [9], fruit, [10] tea [11], blueberries [12], and wafers [13], can also be performed with this method. Also, such systems are commonly used for dimension [14] and volume [15] measurements of various objects, curved surface inspection [16], and assembly process control [17,18]. ...
Image analysis is becoming increasingly popular in many industries. Its use is perfect for, among other things, assessing the quality of products on or off the production line. Highly automated, high-performance systems can be used for this purpose. However, there are situations in which automated vision systems cannot be used on the production line due to the specific nature of the process. One such situation is testing the resistance of paint applied to glass when washing in automatic dishwashers. It is carried out outside the production line, and typical production vision systems are not used here. An attempt was made to develop a cheap and easy-to-implement research method enabling quantitative measurement of paint loss on glass when testing the coating’s resistance to automatic washing. For this purpose, analysis of images taken during the study was carried out. The developed method is based on taking a series of photos of the tested object between each stage of the wash resistance test. The obtained photographic material is then analyzed by measuring the size of paint losses expressed in the number of pixels. Then, the percentage of paint loss is calculated. This method is cheap to implement and highly accurate. Statistical analysis of the results confirmed the method’s accuracy at 98%.
... HIS-R is the calibrated reflectance of the hyperspectral image acquired with respect to the spatial information 'x' and 'y' for the wavelength 'k' as shown in (3). Reflectance is calculated from the references and the light source distribution in various spectral bands [24]. Where the raw spectral capture is represented as SI-R with respect to x and y spatial information and k spectral information. ...
Tea, a commonly consumed beverage, is susceptible to being sold in adulterated or expired forms by third-party vendors. Hyperspectral imaging across different wavelength bands has proven to precisely assess the diverse types of tea and their corresponding financial gains. This study aims to employ a deep learning methodology in conjunction with hyperspectral imaging for efficiently classifying tea leaves. A novel approach is proposed, wherein a waveband convolutional neural network is utilized to generate hyper spectral images of tea leaf samples with enhanced resolution. The model known as optimized-convolutional neural network-random forest O- (ConvNet-RF) demonstrated exceptional performance, achieving high accuracy, impressive recall, F1 score, and notable sensitivity rate, outperforming existing alternative methods. The tea leaf types, namely green, yellow, and black, were accurately identified using a combination of the random forest (RF) model and the O-ConvNet-RF model. The tree-based classification method for the identification of tea leaves demonstrated superior performance as compared to alternative machine learning models. In general, this study presents a successful methodology for the classification of tea leaves, with potential implications for consumer processing and distributor profit analysis.
... Computer vision technologies have emerged as promising tools for agricultural applications, including plant phenotyping, disease detection, and identification [7][8][9]. Over the years, numerous research initiatives on agricultural product processing have been initiated, with several techniques developed to identify and characterize leaf defects [9][10]. Recent literature highlights the widespread and efficient use of image processing techniques for disease detection in agriculture [11][12][13][14]. ...
... Nowadays, a lot of packaging houses employ machine vision system (MVS) [18], [19] applications to automatically grade and sort vast quantities of produce based on size, color, shape, texture, and surface flaws in a non-destructive and economical manner. To create an automated grading system [20], a straightforward MVS was built to measure the various color characteristics of the mango fruit surface [20], [21]. Research found that on Mango photos were taken using a CCD camera [22] and a fluorescent illumination system [23], [24]. ...
Qualitative approach for automated grading and quality assessment of fruits, machine learning techniques are crucial in agricultural applications. Automation enhances a nation’s agricultural quality, production, and economic prosperity. Fruit quality grading, particularly the surface fault identification of a fruit, is a crucial indicator in the export market. This is particularly important for mangoes, which are quite well-liked inBangladesh. On the other hand, the physical grading of mangoes is a procedure that is labor-intensive, prone to error, and very subjective. In this paper, we proposed a YOLOv7 integrated Discrete wave transformation computer vision system. The proposed model includes support vector machine (SVM) and decision tree for the classification of high-quality mangoes. The results of the experiments show that the proposed solution obtained 96.25% accuracy when the system was trained and tested using a publicly accessible mango database.
... The experiments showed that the texture features of tea particles could better distinguish tea grades under dark field illumination conditions. In order to comprehensively assess tea quality, Rahman et al. (2021) studied methods for assessing tea quality using features such as color, texture, and shape. Statistical methods were used to find that four different qualities of tea particles could be clearly distinguished in terms of area, circumference, roundness, and diameter. ...
Tea is rich in polyphenols, vitamins, and protein, which is good for health and tastes great. As a result, tea is very popular and has become the second most popular beverage in the world after water. For this reason, it is essential to improve the yield and quality of tea. In this paper, we review the application of computer vision and machine learning in the tea industry in the last decade, covering three crucial stages: cultivation, harvesting, and processing of tea. We found that many advanced artificial intelligence algorithms and sensor technologies have been used in tea, resulting in some vision-based tea harvesting equipment and disease detection methods. However, these applications focus on the identification of tea buds, the detection of several common diseases, and the classification of tea products. Clearly, the current applications have limitations and are insufficient for the intelligent and sustainable development of the tea field. The current fruitful developments in technologies related to UAVs, vision navigation, soft robotics, and sensors have the potential to provide new opportunities for vision-based tea harvesting machines, intelligent tea garden management, and multimodal-based tea processing monitoring. Therefore, research and development combining computer vision and machine learning is undoubtedly a future trend in the tea industry.
... The biochemical components in tea can be analyzed by UV-visible spectrophotometer (Johnson et al., 2022), high performance liquid chromatography (HPLC) (Beer et al., 2021), liquid chromatography-mass spectrometry (LC-MS) (Alnaimat et al., 2019), gas chromatography-mass spectrometry (GC-MS) (Wang et al., 2022b), nuclear magnetic resonance spectroscopy (NMR) (Zhang et al., 2019d) and other instruments. In recent years, some emerging technologies such as computer vision system (Rahman et al., 2021), near infrared spectroscopy , hyperspectral imaging , electronic nose (Lu et al., 2019;Ou et al., 2019) and electronic tongue have been used in tea quality analysis. The quality assessment of quinoa tea can be performed by using a combination of traditional and emerging technologies ; Figure 2). ...
Abstract Quinoa is a kind of pseudocereal with rich nutrient, unique flavor and antioxidant ingredients. In recent years, it has received widespread attention all over the world, however, the problem of single quinoa product is increasingly prominent. Tea is one of the most popular functional beverages globally, so the development of quinoa tea has a broad market prospect. In the present review, the preparation methods of quinoa seed tea, quinoa malt tea, quinoa leaf tea, quinoa whole plant tea, quinoa fermented tea and quinoa compound tea were summarized, and the current situation and existing problems were analyzed. Based on the above investigations, some suggestions for improving the product performance were put forward.
... Since tea farmers have strict requirements on the quality and the number of tea buds, etc (Gill et al., 2013;Rahman et al., 2021). When picking, we used mobilenet_v2 algorithm and embeds it into OpenMV smart camera to classify the buds using the camera and conveyor belt. ...
Famous tea industry which need to harvest tea buds has great economic benefits. However, the harvesting is time-consuming and labor-intensive, especially with the shortage of labor currently, an intelligent tea bud picking robot is urgently needed. The vision system is a precursor to the development of a tea bud picking robot. To resolve such issues, we applied robotics and deep learning technologies to develop a computer vision system for intelligent picking of tea buds. The system was designed to recognize tea buds and extract their picking points. A method for locating the picking points was proposed based on a combination of YOLO-v3 algorithm, semantic segmentation algorithm, skeleton extraction and minimum bounding rectangle. An intelligent tea end-effector based on Personal Computer and microcontroller collaborative control was designed to solve the picking problem like complex shading and easy breakage. Thus, the picking rate of the overall system was improved. Based on Openmv smart camera embedded mobilenet_v2 algorithm as the visual model of the classification device, so that the quality of tea buds was preliminatively classified. Finally, the effects of different shooting angles and shooting methods as well as the accuracy of target detection and semantic segmentation algorithms on the extraction of tea bud picking points were investigated. The results show that the average accuracy of YOLO-v3 for identification of tea buds is 71.96% and the average horizontal positioning error of the robotic arm is 2.4 mm. Also, the average depth positioning error is 4.2 mm and the accuracy of tea bud picking point extraction is 83%. After the test, the successful picking rate of tea buds is 80% by this computer vision system of robot. The results of this study is potential to develop a machine-based tea picking system for industry and would contribute to the development of precision agriculture.
