1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches
Recent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research to improve the efficiency and performance of barcode recognition in Supply Chain Management (SCM). D-CNNs required real-world images embedded with ground truth data, which is often not readily available...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/22/8788 |
| _version_ | 1797463981741309952 |
|---|---|
| author | Teerawat Kamnardsiri Phasit Charoenkwan Chommaphat Malang Ratapol Wudhikarn |
| author_facet | Teerawat Kamnardsiri Phasit Charoenkwan Chommaphat Malang Ratapol Wudhikarn |
| author_sort | Teerawat Kamnardsiri |
| collection | DOAJ |
| description | Recent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research to improve the efficiency and performance of barcode recognition in Supply Chain Management (SCM). D-CNNs required real-world images embedded with ground truth data, which is often not readily available in the case of SCM barcode recognition. This study introduces two invented barcode datasets: InventBar and ParcelBar. The datasets contain labeled barcode images with 527 consumer goods and 844 post boxes in the indoor environment. To explore the influential capability of the datasets that affect recognition process, five existing D-CNN algorithms were applied and compared over a set of recently available barcode datasets. To confirm the model’s performance and accuracy, runtime and Mean Average Precision (mAP) were examined based on different IoU thresholds and image transformation settings. The results show that YOLO v5 works best for the ParcelBar in terms of speed and accuracy. The situation is different for the InventBar since Faster R-CNN could allow the model to learn faster with a small drop in accuracy. It is proven that the proposed datasets can be practically utilized for the mainstream D-CNN frameworks. Both are available for developing barcode recognition models and positively affect comparative studies. |
| first_indexed | 2024-03-09T18:01:25Z |
| format | Article |
| id | doaj.art-ca7f55c1bf3c47a492a2b38478abd81c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T18:01:25Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-ca7f55c1bf3c47a492a2b38478abd81c2023-11-24T09:55:48ZengMDPI AGSensors1424-82202022-11-012222878810.3390/s222287881D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network ApproachesTeerawat Kamnardsiri0Phasit Charoenkwan1Chommaphat Malang2Ratapol Wudhikarn3Department of Digital Game, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, ThailandDepartment of Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, ThailandDepartment of Digital Industry Integration, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, ThailandA Research Group of Modern Management and Information Technology, College of Arts, Media and Technology, Chiang Mai University, Chiang Mai 50200, ThailandRecent advancement in Deep Learning-based Convolutional Neural Networks (D-CNNs) has led research to improve the efficiency and performance of barcode recognition in Supply Chain Management (SCM). D-CNNs required real-world images embedded with ground truth data, which is often not readily available in the case of SCM barcode recognition. This study introduces two invented barcode datasets: InventBar and ParcelBar. The datasets contain labeled barcode images with 527 consumer goods and 844 post boxes in the indoor environment. To explore the influential capability of the datasets that affect recognition process, five existing D-CNN algorithms were applied and compared over a set of recently available barcode datasets. To confirm the model’s performance and accuracy, runtime and Mean Average Precision (mAP) were examined based on different IoU thresholds and image transformation settings. The results show that YOLO v5 works best for the ParcelBar in terms of speed and accuracy. The situation is different for the InventBar since Faster R-CNN could allow the model to learn faster with a small drop in accuracy. It is proven that the proposed datasets can be practically utilized for the mainstream D-CNN frameworks. Both are available for developing barcode recognition models and positively affect comparative studies.https://www.mdpi.com/1424-8220/22/22/8788barcode datasetdeep learningconvolutional neural networkbarcode recognitionbarcode detectionbenchmarking |
| spellingShingle | Teerawat Kamnardsiri Phasit Charoenkwan Chommaphat Malang Ratapol Wudhikarn 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches Sensors barcode dataset deep learning convolutional neural network barcode recognition barcode detection benchmarking |
| title | 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches |
| title_full | 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches |
| title_fullStr | 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches |
| title_full_unstemmed | 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches |
| title_short | 1D Barcode Detection: Novel Benchmark Datasets and Comprehensive Comparison of Deep Convolutional Neural Network Approaches |
| title_sort | 1d barcode detection novel benchmark datasets and comprehensive comparison of deep convolutional neural network approaches |
| topic | barcode dataset deep learning convolutional neural network barcode recognition barcode detection benchmarking |
| url | https://www.mdpi.com/1424-8220/22/22/8788 |
| work_keys_str_mv | AT teerawatkamnardsiri 1dbarcodedetectionnovelbenchmarkdatasetsandcomprehensivecomparisonofdeepconvolutionalneuralnetworkapproaches AT phasitcharoenkwan 1dbarcodedetectionnovelbenchmarkdatasetsandcomprehensivecomparisonofdeepconvolutionalneuralnetworkapproaches AT chommaphatmalang 1dbarcodedetectionnovelbenchmarkdatasetsandcomprehensivecomparisonofdeepconvolutionalneuralnetworkapproaches AT ratapolwudhikarn 1dbarcodedetectionnovelbenchmarkdatasetsandcomprehensivecomparisonofdeepconvolutionalneuralnetworkapproaches |