Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain
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 p...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/10/4/879 |
| _version_ | 1827694905868156928 |
|---|---|
| author | Clíssia Barboza da Silva Alysson Alexander Naves Silva Geovanny Barroso Pedro Takao Yamamoto Valter Arthur Claudio Fabiano Motta Toledo Thiago de Araújo Mastrangelo |
| author_facet | Clíssia Barboza da Silva Alysson Alexander Naves Silva Geovanny Barroso Pedro Takao Yamamoto Valter Arthur Claudio Fabiano Motta Toledo Thiago de Araújo Mastrangelo |
| author_sort | Clíssia Barboza da Silva |
| collection | DOAJ |
| description | 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 <i>Sitophilus zeamais</i> 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 <i>Sitophilus zeamais</i> 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. |
| first_indexed | 2024-03-10T12:14:18Z |
| format | Article |
| id | doaj.art-4544056ad5a64c4e9a1bdfd1c321cc1e |
| institution | Directory Open Access Journal |
| issn | 2304-8158 |
| language | English |
| last_indexed | 2024-03-10T12:14:18Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj.art-4544056ad5a64c4e9a1bdfd1c321cc1e2023-11-21T15:56:29ZengMDPI AGFoods2304-81582021-04-0110487910.3390/foods10040879Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize GrainClíssia Barboza da Silva0Alysson Alexander Naves Silva1Geovanny Barroso2Pedro Takao Yamamoto3Valter Arthur4Claudio Fabiano Motta Toledo5Thiago de Araújo Mastrangelo6Center for Nuclear Energy in Agriculture, University of São Paulo, Piracicaba 13416-000, SP, BrazilInstitute of Mathematics and Computer Sciences, University of São Paulo, São Carlos 13560-970, SP, BrazilDepartment of Entomology and Acarology, College of Agriculture Luiz de Queiroz, University of São Paulo, Piracicaba 13418-900, SP, BrazilDepartment of Entomology and Acarology, College of Agriculture Luiz de Queiroz, University of São Paulo, Piracicaba 13418-900, SP, BrazilCenter for Nuclear Energy in Agriculture, University of São Paulo, Piracicaba 13416-000, SP, BrazilInstitute of Mathematics and Computer Sciences, University of São Paulo, São Carlos 13560-970, SP, BrazilCenter for Nuclear Energy in Agriculture, University of São Paulo, Piracicaba 13416-000, SP, BrazilThe 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 <i>Sitophilus zeamais</i> 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 <i>Sitophilus zeamais</i> 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.https://www.mdpi.com/2304-8158/10/4/879deep learning architecturesMobileNetV2XceptionInception-ResNet-v2peripheral equalizationcalcification emphasis |
| spellingShingle | Clíssia Barboza da Silva Alysson Alexander Naves Silva Geovanny Barroso Pedro Takao Yamamoto Valter Arthur Claudio Fabiano Motta Toledo Thiago de Araújo Mastrangelo Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain Foods deep learning architectures MobileNetV2 Xception Inception-ResNet-v2 peripheral equalization calcification emphasis |
| title | Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain |
| title_full | Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain |
| title_fullStr | Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain |
| title_full_unstemmed | Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain |
| title_short | Convolutional Neural Networks Using Enhanced Radiographs for Real-Time Detection of <i>Sitophilus zeamais</i> in Maize Grain |
| title_sort | convolutional neural networks using enhanced radiographs for real time detection of i sitophilus zeamais i in maize grain |
| topic | deep learning architectures MobileNetV2 Xception Inception-ResNet-v2 peripheral equalization calcification emphasis |
| url | https://www.mdpi.com/2304-8158/10/4/879 |
| work_keys_str_mv | AT clissiabarbozadasilva convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT alyssonalexandernavessilva convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT geovannybarroso convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT pedrotakaoyamamoto convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT valterarthur convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT claudiofabianomottatoledo convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain AT thiagodearaujomastrangelo convolutionalneuralnetworksusingenhancedradiographsforrealtimedetectionofisitophiluszeamaisiinmaizegrain |