Off-flavor profiling of cultured salmonids using hyperspectral imaging combined with machine learning.

Off-flavors can have significant impacts on the quality of salmonid products. This study investigated the possibility of comprehensive off-flavor profiling considering both olfactory and taste sensory perspectives by combining near-infrared hyperspectral imaging (NIR-HSI) and machine/deep learning. Four feature extraction algorithms were employed for the extraction and interpretation of spectral fingerprint information regarding off-flavor-related compounds. Classification models, including the partial least squares discriminant analysis, least-squares support vector machine, extreme learning machine, and one-dimensional convolutional neural network (1DCNN) were constructed using the full wavelengths and selected spectral features for the identification of off-flavor salmonids. The 1DCNN achieved the highest discrimination accuracy with full and selected wavelengths (i.e., 91.11 and 86.39 %, respectively). Furthermore, the prediction and visualization of off-flavor-related compounds were achieved with acceptable performances (R2 > 0.6) for practical applications. These results indicate the potential of NIR-HSI for the off-flavor profiling of salmonid muscle samples for producers and researchers.

Structure analysis and non-invasive detection of cadmium-phytochelatin2 complexes in plant by deep learning Raman spectrum.

Plants synthesize phytochelatins to chelate in vivo toxic heavy metal ions and produce nontoxic complexes for tolerating the stress. Detection of the complexes would simplify the identification of high phytoremediation cultivars, as well as assessment of plant food for safe consumption. Thus, a confocal Raman spectroscopy combined with density functional theory and deep learning was used for characterizing phytochelatin2 (PC2), and Cd-PC2 mixtures. Results showed the PC2 chelate Cd2+ in a 2:1 ratio to produce Cd(PC2)2; Cd-S bonds of the Cd(PC2)2 have signature Raman vibrations at 305 and 610 cm-1 which are the most distinctive spectral signatures for varieties of Cd-PCs complexes. The PC2 was used as a natural probe to stabilize the chemical status of Cd, and to enrich and magnify Raman signature of the trace Cd for deep learning models which enabled condition of the Cd(PC2)2 in pak choi leaf to be visualized, quantified, and classified by directly using raw spectra of the leaf. This study provides a general protocol by using Raman information for structure analysis and non-invasive detection of heavy metal-PCs complexes in plants and provides a novel idea for simplifying identification of high phytoremediation cultivars, as well as assessment of heavy metal related food safeties.

Analyzing cadmium-phytochelatin2 complexes in plant using terahertz and circular dichroism information.

Phytochelatins are plants' small metal-binding peptides which chelate internal heavy metals to form nontoxic complexes. Detecting the complexes in plants would simplify identification of cultivars with both high tolerance and enrichment capabilities for heavy metals which represent phytoextraction performance. Thus, a terahertz spectroscopy combined with density functional theory, chemometrics and circular dichroism was used for characterization of phytochelatin2 (PC2), Cd-PC2 mixture standards, and pak choi (Brassica chinensis) leaves as a plant model. Results showed PC2 chelates Cd2+ in a 2:1 ratio to form Cd(PC2)2 complex; Cd connected to thoils of PC2 and changed ß-turn and random coil of PC2 peptide chain to ß-Sheet which presented as terahertz vibrations of PC2 around 1.03 and 1.71 THz being suppressed; the best models for detecting the complex in pak choi were obtained by partial least squares regression modeling combined with successive projections algorithm selection; the models used PC2 as a natural probe for visualizing and quantifying chelated Cd in pak choi leaf and achieved a limit of detection up to 1.151 ppm. This study suggested that terahertz information of the heavy metal-PCs complexes is qualified for representing a simpler alternative to classical index for evaluating phytoextraction performance of plant; it provided a general protocol for structure analysis and detection of heavy metal-PCs complexes in plant by terahertz absorbance.

A Novel Greenhouse-Based System for the Detection and Plumpness Assessment of Strawberry Using an Improved Deep Learning Technique.

The automated harvesting of strawberry brings benefits such as reduced labor costs, sustainability, increased productivity, less waste, and improved use of natural resources. The accurate detection of strawberries in a greenhouse can be used to assist in the effective recognition and location of strawberries for the process of strawberry collection. Furthermore, being able to detect and characterize strawberries based on field images is an essential component in the breeding pipeline for the selection of high-yield varieties. The existing manual examination method is error-prone and time-consuming, which makes mechanized harvesting difficult. In this work, we propose a robust architecture, named "improved Faster-RCNN," to detect strawberries in ground-level RGB images captured by a self-developed "Large Scene Camera System." The purpose of this research is to develop a fully automatic detection and plumpness grading system for living plants in field conditions which does not require any prior information about targets. The experimental results show that the proposed method obtained an average fruit extraction accuracy of more than 86%, which is higher than that obtained using three other methods. This demonstrates that image processing combined with the introduced novel deep learning architecture is highly feasible for counting the number of, and identifying the quality of, strawberries from ground-level images. Additionally, this work shows that deep learning techniques can serve as invaluable tools in larger field investigation frameworks, specifically for applications involving plant phenotyping.

A Monitoring System for the Segmentation and Grading of Broccoli Head Based on Deep Learning and Neural Networks.

Achieving the non-contact and non-destructive observation of broccoli head is the key step to realize the acquisition of high-throughput phenotyping information of broccoli. However, the rapid segmentation and grading of broccoli head remains difficult in many parts of the world due to low equipment development level. In this paper, we combined an advanced computer vision technique with a deep learning architecture to allow the acquisition of real-time and accurate information about broccoli head. By constructing a private image dataset with 100s of broccoli-head images (acquired using a self-developed imaging system) under controlled conditions, a deep convolutional neural network named "Improved ResNet" was trained to extract the broccoli pixels from the background. Then, a yield estimation model was built based on the number of extracted pixels and the corresponding pixel weight value. Additionally, the Particle Swarm Optimization Algorithm (PSOA) and the Otsu method were applied to grade the quality of each broccoli head according to our new standard. The trained model achieved an Accuracy of 0.896 on the test set for broccoli head segmentation, demonstrating the feasibility of this approach. When testing the model on a set of images with different light intensities or with some noise, the model still achieved satisfactory results. Overall, our approach of training a deep learning model using low-cost imaging devices represents a means to improve broccoli breeding and vegetable trade.

Automated Counting of Rice Panicle by Applying Deep Learning Model to Images from Unmanned Aerial Vehicle Platform.

The number of panicles per unit area is a common indicator of rice yield and is of great significance to yield estimation, breeding, and phenotype analysis. Traditional counting methods have various drawbacks, such as long delay times and high subjectivity, and they are easily perturbed by noise. To improve the accuracy of rice detection and counting in the field, we developed and implemented a panicle detection and counting system that is based on improved region-based fully convolutional networks, and we use the system to automate rice-phenotype measurements. The field experiments were conducted in target areas to train and test the system and used a rotor light unmanned aerial vehicle equipped with a high-definition RGB camera to collect images. The trained model achieved a precision of 0.868 on a held-out test set, which demonstrates the feasibility of this approach. The algorithm can deal with the irregular edge of the rice panicle, the significantly different appearance between the different varieties and growing periods, the interference due to color overlapping between panicle and leaves, and the variations in illumination intensity and shading effects in the field. The result is more accurate and efficient recognition of rice-panicles, which facilitates rice breeding. Overall, the approach of training deep learning models on increasingly large and publicly available image datasets presents a clear path toward smartphone-assisted crop disease diagnosis on a global scale.