A Multi-Strategy Vision Accurate Inspection Algorithm for Storage Pests

Author(s):  
Guicai Wang ◽  
Heran Zhao ◽  
Dan Wang
Keyword(s):  
2008 ◽  
Vol 115 (3) ◽  
pp. 129-133 ◽  
Author(s):  
V. Stejskal ◽  
R. Aulický ◽  
Z. Kučerová ◽  
J. Lukáš
Keyword(s):  

Foods ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 879
Author(s):  
Clíssia Barboza da Silva ◽  
Alysson Alexander Naves Silva ◽  
Geovanny Barroso ◽  
Pedro Takao Yamamoto ◽  
Valter Arthur ◽  
...  

The application of artificial intelligence (AI) such as deep learning in the quality control of grains has the potential to assist analysts in decision making and improving procedures. Advanced technologies based on X-ray imaging provide markedly easier ways to control insect infestation of stored products, regardless of whether the quality features are visible on the surface of the grains. Here, we applied contrast enhancement algorithms based on peripheral equalization and calcification emphasis on X-ray images to improve the detection of Sitophilus zeamais in maize grains. In addition, we proposed an approach based on convolutional neural networks (CNNs) to identity non-infested and infested classes using three different architectures; (i) Inception-ResNet-v2, (ii) Xception and (iii) MobileNetV2. In general, the prediction models developed based on the MobileNetV2 and Xception architectures achieved higher accuracy (≥0.88) in identifying non-infested grains and grains infested by maize weevil, with a correct classification from 0.78 to 1.00 for validation and test sets. Hence, the proposed approach using enhanced radiographs has the potential to provide precise control of Sitophilus zeamais for safe human consumption of maize grains. The proposed method can automatically recognize food contaminated with hidden storage pests without manual features, which makes it more reliable for grain inspection.


2018 ◽  
Vol 10 (8) ◽  
pp. 100
Author(s):  
Tadele Tefera ◽  
Addis Teshome ◽  
Charles Singano

A study was conducted for 12 months to evaluate the effectiveness of two improved hermetic storage structures against two maize storage pests Sitophilus zeamais and Prostephanus truncatus at Liwufu Research Station, Malawi. The storages were metal silo and hermetic bag; Actellic super dust was included as a control. The treatments (storages) were replicated four times under natural and artificial infestations. Grain stored in metal silo had the lowest mean percentage weight loss, 1.04% to 1.25%, 12 months after storage followed by hermetic bag, 2.46% to 6.64%. Grain treated with Actellic super had the highest weight loss, 4.86% to 18.72%. The study showed that hermetic storage structures can be promoted as effective alternative non-chemical methods of grain storage for small holder farmers in Malawi.


Author(s):  
Neelam Bhardwaj ◽  
Tanuja Kapoor ◽  
Parveen Sharma

Background: Ricebean [Vigna umbellata (Thunb.) Ohwi and Ohashi] is a multipurpose grain legume of Mid-Himalayan region mainly cultivated for food, fodder, green manure and has emerged as a good alternative to other pulse crops such as blackgram and greengram which do not flourish in this region due to their susceptibility to cold temperature stress. It is well reported that the nutritional value of ricebean is higher as compared to many other legumes of the Vigna family and has some superior qualities greater than greengram, blackgram and cowpea. It is also resistance to drought, diseases and pests specially the storage pests during growth period and possesses high percentage of seed viability. Despite having all the favourable traits, it is not much popular among the farmers due to the late maturity and indeterminate growth habit. Instead, farmers prefer other crops which fit easily into their cropping pattern and are easy to harvest. A little genetic improvement with respect to maturity and growth habit can revive its cultivation and show great results in its production as a valuable crop. Thus, the present investigation was formulated to introgress desired traits from mash and adzukibean into otherwise high yielding ricebean genotypes using inter-specific hybridization. Methods: The present investigation involves the inter-specific hybridization among three Vigna species viz, ricebean (Vigna umbellata), blackgram (Vigna mungo) and adzukibean (Vigna angularis). In the year 2017, six genotypes of ricebean (RBHP-36, RBHP-38, RBHP-43, RBHP-61, RBHP-107 and RBHP-108) were crossed with two genotypes of blackgram (HimMash-1 and Palampur-93) and one genotype of adzukibean (HPU-51) in glasshouse conditions. Result: The study revealed that successful crosses were possible only between ricebean and blackgram. All the Inter-specific crosses showed very low pod set percentage ranging from 0 -4% and F1 germination percentage ranging from 20-42%. Pod set percentage and pods harvested varied with combinations of two parental cultivars of each species for most of the inter-specific hybrids. The successful pod set was observed in 16 out of 36 inter-specific crosses. Highest crossability was observed in blackgram and ricebean crosses. Crossing of adzukibean with ricebean showed poor or no pod set among the entire cross combinations which are attributed to early embryo abortion and degeneration during embryogenesis.


Sign in / Sign up

Export Citation Format

Share Document