Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map
The thousand grain weight is an index of size, fullness and quality in crop seed detection and is an important basis for field yield prediction. To detect the thousand grain weight of rice requires the accurate counting of rice. We collected a total of 5670 images of three different types of rice se...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/6/721 |
| _version_ | 1797531239994884096 |
|---|---|
| author | Ao Feng Hongxiang Li Zixi Liu Yuanjiang Luo Haibo Pu Bin Lin Tao Liu |
| author_facet | Ao Feng Hongxiang Li Zixi Liu Yuanjiang Luo Haibo Pu Bin Lin Tao Liu |
| author_sort | Ao Feng |
| collection | DOAJ |
| description | The thousand grain weight is an index of size, fullness and quality in crop seed detection and is an important basis for field yield prediction. To detect the thousand grain weight of rice requires the accurate counting of rice. We collected a total of 5670 images of three different types of rice seeds with different qualities to construct a model. Considering the different shapes of different types of rice, this study used an adaptive Gaussian kernel to convolve with the rice coordinate function to obtain a more accurate density map, which was used as an important basis for determining the results of subsequent experiments. A Multi-Column Convolutional Neural Network was used to extract the features of different sizes of rice, and the features were fused by the fusion network to learn the mapping relationship from the original map features to the density map features. An advanced prior step was added to the original algorithm to estimate the density level of the image, which weakened the effect of the rice adhesion condition on the counting results. Extensive comparison experiments show that the proposed method is more accurate than the original MCNN algorithm. |
| first_indexed | 2024-03-10T10:41:02Z |
| format | Article |
| id | doaj.art-7256005df5974bd682cc89c9783f5992 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T10:41:02Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-7256005df5974bd682cc89c9783f59922023-11-21T22:55:27ZengMDPI AGEntropy1099-43002021-06-0123672110.3390/e23060721Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density MapAo Feng0Hongxiang Li1Zixi Liu2Yuanjiang Luo3Haibo Pu4Bin Lin5Tao Liu6College of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaThe thousand grain weight is an index of size, fullness and quality in crop seed detection and is an important basis for field yield prediction. To detect the thousand grain weight of rice requires the accurate counting of rice. We collected a total of 5670 images of three different types of rice seeds with different qualities to construct a model. Considering the different shapes of different types of rice, this study used an adaptive Gaussian kernel to convolve with the rice coordinate function to obtain a more accurate density map, which was used as an important basis for determining the results of subsequent experiments. A Multi-Column Convolutional Neural Network was used to extract the features of different sizes of rice, and the features were fused by the fusion network to learn the mapping relationship from the original map features to the density map features. An advanced prior step was added to the original algorithm to estimate the density level of the image, which weakened the effect of the rice adhesion condition on the counting results. Extensive comparison experiments show that the proposed method is more accurate than the original MCNN algorithm.https://www.mdpi.com/1099-4300/23/6/721ricethousand grain weightdensity mapmulti-column convolutional neural networkadvanced priori |
| spellingShingle | Ao Feng Hongxiang Li Zixi Liu Yuanjiang Luo Haibo Pu Bin Lin Tao Liu Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map Entropy rice thousand grain weight density map multi-column convolutional neural network advanced priori |
| title | Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map |
| title_full | Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map |
| title_fullStr | Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map |
| title_full_unstemmed | Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map |
| title_short | Research on a Rice Counting Algorithm Based on an Improved MCNN and a Density Map |
| title_sort | research on a rice counting algorithm based on an improved mcnn and a density map |
| topic | rice thousand grain weight density map multi-column convolutional neural network advanced priori |
| url | https://www.mdpi.com/1099-4300/23/6/721 |
| work_keys_str_mv | AT aofeng researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT hongxiangli researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT zixiliu researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT yuanjiangluo researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT haibopu researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT binlin researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap AT taoliu researchonaricecountingalgorithmbasedonanimprovedmcnnandadensitymap |