Deep Learning Segmentation in Bulk Grain Images for Prediction of Grain Market Quality

Assadzadeh, Sahand; Walker, Cassandra K.; Panozzo, Joe

doi:10.1007/s11947-022-02840-1

Cited by 12 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Images of the grain and cotyledon samples were acquired for colour, separately using a Tagarno microscope (Tagarano, A/S, Horsens, Denmark) at 4.3× magnification with a resolution of 1920 × 1080 pixels and illuminated with a white LED ring light fixed to the camera lens as described by Assadzadeh et al [30]. The instrument was calibrated as per the manufacturer's requirements (Tagarano, A/S, Horsens, Denmark).…”

Section: Image Acquisitionmentioning

confidence: 99%

Storage Temperature and Grain Moisture Effects on Market and End Use Properties of Red Lentil

Bhattarai,

Walker,

Wallace

et al. 2023

Agronomy

Self Cite

View full text Add to dashboard Cite

Storing lentil is a strategy used by growers to manage price volatility. However, studies investigating the impact of storage conditions on the market and end use properties of lentil are limited. This study examined the effects of storage temperature (4, 15, 25, and 35 °C) and grain moisture (10 and 14%, w/w) on traits related to market (seed coat colour), viability (germination capacity), and end use properties (hydration capacity, milling efficiency, and cooking quality) in four red lentil cultivars (PBA Bolt, PBA Hallmark, PBA Hurricane, PBA Jumbo2) over 360 days. Storing lentil at 14% moisture content and 35 °C significantly (p = 0.05) darkened seed coat after 30 days, caused complete loss of viability within 180 days and reduced cooking quality (cooked firmness) after 120 days across all tested cultivars. Storing lentil at 10% moisture content and 35 °C reduced hydration capacity after 30 days, and milling efficiency after 120 days across all cultivars tested. PBA Jumbo2 exhibited a higher rate of degradation in hydration capacity and cooking quality, and a lower rate of degradation in the other traits studied. Storing lentil at ≤15 °C prevented degradation of all quality traits. These findings will support improved lentil storage protocols to maintain quality and improve economic outcomes for the pulse industry.

show abstract

Section: Image Acquisitionmentioning

confidence: 99%

Storage Temperature and Grain Moisture Effects on Market and End Use Properties of Red Lentil

Bhattarai,

Walker,

Wallace

et al. 2023

Agronomy

Self Cite

View full text Add to dashboard Cite

show abstract

“…During the measurement, a space was deliberately left between the grains because the grain arrangement greatly influences the overlap of the image frames, which affects the measurement accuracy. It has been proven that placing samples too close to each other, in our case grains (seeds), causes cross-contamination during measurement 38 .…”

Section: Methodsmentioning

confidence: 95%

The use of image analysis to study the effect of moisture content on the physical properties of grains

Gierz,

Al-Sammarraie,

Özbek

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Designing machines and equipment for post-harvest operations of agricultural products requires information about their physical properties. The aim of the work was to evaluate the possibility of introducing a new approach to predict the moisture content in bean and corn seeds based on measuring their dimensions using image analysis using artificial neural networks (ANN). Experimental tests were carried out at three levels of wet basis moisture content of seeds: 9, 13 and 17%. The analysis of the results showed a direct relationship between the wet basis moisture content and the main dimensions of the seeds. Based on the statistical analysis of the seed material, it was shown that the characteristics examined have a normal or close to normal distribution, and the seed material used in the investigation is representative. Furthermore, the use of artificial neural networks to predict the wet basis moisture content of seeds based on changes in their dimensions has an efficiency of 82%. The results obtained from the method used in this work are very promising for predicting the moisture content.

show abstract

“…This means different marking boxes do not represent independent mildewed regions, thus making it impossible to achieve convergence of object loss during model training. In contrast, in the study of the defect detection for bulk grain and soybean [ 33 , 34 ], lower object loss can be obtained using the CNN model because the objects segmented are intact bean grains, the shape of recognition targets is close to a circle, and the boundary delineation is clear. With an increase in the number of training epochs, the box loss of the model continuously decreases, and the degree of coincidence between the mildewed region resulting from the superposition of the output marker boxes and the manually marked mildewed region continues to improve.…”

Section: Discussionmentioning

confidence: 99%

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Sun

Zhang

Tong

et al. 2022

Foods

View full text Add to dashboard Cite

This study aims to develop a high-speed and nondestructive mildewed rice grain detection method. First, a set of microscopic images of rice grains contaminated by Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea are acquired to serve as samples, and the mildewed regions are marked. Then, three YOLO-v5 models for identifying regions of rice grain with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in microscopic images are established. Finally, the relationship between the proportion of mildewed regions and the total number of colonies is analyzed. The results show that the proposed YOLO-v5 models achieve accuracy levels of 89.26%, 91.15%, and 90.19% when detecting mildewed regions with contamination of Aspergillus niger, Penicillium citrinum, and Aspergillus cinerea in the microscopic images of the verification set. The proportion of the mildewed region area of rice grain with contamination of Aspergillus niger/Penicillium citrinum/Aspergillus cinerea is logarithmically correlated with the logarithm of the total number of colonies (TVC). The corresponding determination coefficients are 0.7466, 0.7587, and 0.8148, respectively. This study provides a reference for future research on high-speed mildewed rice grain detection methods based on MCV technology.

show abstract

Deep Learning Segmentation in Bulk Grain Images for Prediction of Grain Market Quality

Cited by 12 publications

References 20 publications

Storage Temperature and Grain Moisture Effects on Market and End Use Properties of Red Lentil

Storage Temperature and Grain Moisture Effects on Market and End Use Properties of Red Lentil

The use of image analysis to study the effect of moisture content on the physical properties of grains

Study on Rice Grain Mildewed Region Recognition Based on Microscopic Computer Vision and YOLO-v5 Model

Contact Info

Product

Resources

About