Smartphone assist deep neural network model to recognize the high-quality tea using leaf maturity and its effect on leaf chlorophyll

Immature and tender tea leaves always produce high-quality tea than mature tea leaves. Depending on the maturity and age of the leaf, the colour and texture of the tea leaf are different. The photosynthesis capacity of the tea leaf also changes with the change of leaf maturity. Though the tea farmer plucks, classifies, and recognizes the best tea leaves (immature and tender) by viewing the visual symptoms and position of the leaves, the method is not authentic all time and leads to the overall degradation of the tea quality. The present study presents a smartphone assist tea leaf recognition system by analyzing the colour and texture properties of the tea leaf. The six different colour features and 4 Haralick texture features were extracted in the colour and grey domain of the leaf images. Three types of tea leaves, i.e., mature, immature, and tender, were classified using Deep Neural Network (DNN) with ADAM (Adaptive Moment Estimation) optimizer. With an accuracy of 97%, the DNN outperformed the Support Vector Machine (SVM) and K Nearest Neighbor (KNN). The SVM and KNN reported a total of 94.42% and 95.53% accuracy, respectively. The investigated system using DNN with an average precision and recall value of 98.67 and 98.34, respectively, may detect and classify the tea leaf maturity status. The system also can be used in AI-based tea plucking robotic systems or machines.

A Potential Role of Coumestrol in Soybean Leaf Senescence and Its Interaction With Phytohormones

Coumestrol is a natural organic compound synthesized in soy leaves and functions as a phytoalexin. The coumestrol levels in plants are reported to increase upon insect attack. This study investigates the correlation between coumestrol, senescence, and the effect of phytohormones on the coumestrol levels in soybean leaves. Our analysis involving high-performance liquid chromatography and 2-D gel electrophoresis indicated a significant difference in the biochemical composition of soybean leaves at various young and mature growth stages. Eight chemical compounds were specifically detected in young leaves (V1) only, whereas three different coumestans isotrifoliol, coumestrol, and phaseol were detected only in mature, yellow leaves of the R6 and R7 growth stage. MALDI-TOF-MS analysis was used to identify two proteins 3,9 -dihydroxypterocarpan 6A-monooxygenase (CYP93A1) and isoflavone reductase homolog 2 (IFR2) only in mature leaves, which are key components of the coumestrol biosynthetic pathway. This indicates that senescence in soybean is linked to the accumulation of coumestrol. Following the external application of coumestrol, the detached V1-stage young leaves turned yellow and showed an interesting development of roots at the base of the midrib. Additionally, the application of phytohormones, including SA, methyl jasmonate (MeJA), and ethephon alone and in various combinations induced yellowing within 5 days of the application with a concomitant significant increase in endogenous coumestrol accumulation. This was also accompanied by a significant increase in the expression of genes CYP81E28 (Gm08G089500), CYP81E22 (Gm16G149300), GmIFS1, and GmIFS2. These results indicate that various coumestans, especially coumestrol, accumulate during leaf maturity, or senescence in soybean.

An improved lightweight network architecture for identifying tobacco leaf maturity based on Deep learning

The classification of fresh tobacco leaves during the picking process plays an important role in the subsequent roasting. In this paper, a lightweight convolutional neural network is used to detect the maturity of tobacco leaves quickly. Fresh tobacco leaves in the datasets are divided into 3 categories by the picking position, and each category is divided into 4 maturity levels and finally gets 12 types of tobacco leaves with different maturity. To ensure the lightweight of the model, the new network is based on the MobileNetV2 to establish. By utilizing shortcut operation, the shallow network information is preserved, and network degradation is suppressed. In the tobacco leaf datasets we obtained, the improved network has superior performance and compared with other classic networks, the model size and the number of operations have been reduced.

Discrimination of Fresh Tobacco Leaves with Different Maturity Levels by Near-Infrared (NIR) Spectroscopy and Deep Learning

The maturity affects the yield, quality, and economic value of tobacco leaves. Leaf maturity level discrimination is an important step in manual harvesting. However, the maturity judgment of fresh tobacco leaves by grower visual evaluation is subjective, which may lead to quality loss and low prices. Therefore, an objective and reliable discriminant technique for tobacco leaf maturity level based on near-infrared (NIR) spectroscopy combined with a deep learning approach of convolutional neural networks (CNNs) is proposed in this study. To assess the performance of the proposed maturity discriminant model, four conventional multiclass classification approaches—K-nearest neighbor (KNN), backpropagation neural network (BPNN), support vector machine (SVM), and extreme learning machine (ELM)—were employed for a comparative analysis of three categories (upper, middle, and lower position) of tobacco leaves. Experimental results showed that the CNN discriminant models were able to precisely classify the maturity level of tobacco leaves for the above three data sets with accuracies of 96.18%, 95.2%, and 97.31%, respectively. Moreover, the CNN models with strong feature extraction and learning ability were superior to the KNN, BPNN, SVM, and ELM models. Thus, NIR spectroscopy combined with CNN is a promising alternative to overcome the limitations of sensory assessment for tobacco leaf maturity level recognition. The development of a maturity-distinguishing model can provide an accurate, reliable, and scientific auxiliary means for tobacco leaf harvesting.

Affinity of class I and class III peroxidases for H2O2 in pepper leaves of different maturity

Paper deals with activities of Class III peroxidases (POX, EC 1.11.1.7) and Class I peroxidases (ascorbate peroxidase, APX, EC 1.11.1.11) as well as the Km of these enzymes for hydrogen peroxide (H2O2) in the pepper leaves of different maturity. The obtained results suggest that the youngest pepper leaves compared to more mature ones have different strategies for H2O2 removal. There was an increase in APX activity with leaf maturity, while POX activity had the opposite trend, and its lowest activity was observed in the oldest leaves. The accumulation of reducing substrates i.e., ascorbate and total phenols was in positive correlation with corresponding enzymes following leaf maturity. The comparison of POX and APX affinity for H2O2 in pepper leaves of different maturity and their relationship between these enzymes' activities were showed.

THE POTENTIAL OF MATURE PANDAN LEAVES AS A SOURCE OF CHLOROPHYLL FOR NATURAL FOOD COLORANTS

Plant leaves are the primary source of natural colorants for food, mainly due to their chlorophyll content. However, the plant types and the degree of leaf maturity determine the quality and quantity of the chlorophyll. This study aimed to determine the best maturity level of pandan (Pandanus amaryllifolius Roxb.) leaves that serves as potential source of chlorophyll for natural food colorants. Eighty three pandan plants obtained from six different farming locations in Bantul Regency, Yogyakarta, Indonesia were used as samples. The leaves were grouped into four levels of maturity using descriptive statistics based on their morphology, anatomy, color, and chlorophyll contents. The results showed that the average number of leaves ranged from 20-24 leaves per plant (at 95% confidence interval), and 96.4% of the plant had a maximum of 24 leaves. The leaf maturity was grouped into (1) young, (2) medium, (3) mature, and (4) over mature, corresponding to leaf number 1-6, 7-12, 13-18, and 19-24, respectively. The higher the leaf maturity, the higher the chlorophyll content. However, the over mature leaves were only slightly different from the mature ones. In addition, pandan leaves have specific flavor and contain carotenoid, phenolic, and flavonoid substances. Anatomically, the mesophyll’s size was greatest in the mature leaves, while the size of chloroplast was not significantly different from medium to over mature leaves. Based on the chlorophyll content and mesophyll size, it was concluded that mature pandan leaves were the best source of chlorophyll, containing chlorophyll of 623.08 mg/100 g dry weight (DW).