Pointer Meter Reading Recognition by Joint Detection and Segmentation
To handle the task of pointer meter reading recognition, in this paper, we propose a deep network model that can accurately detect the pointer meter dial and segment the pointer as well as the reference points from the located meter dial. Specifically, our proposed model is composed of three stages:...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/4/1443 |
| _version_ | 1797299025707270144 |
|---|---|
| author | Ying Li Xuemei Li Caiming Zhang |
| author_facet | Ying Li Xuemei Li Caiming Zhang |
| author_sort | Ying Li |
| collection | DOAJ |
| description | To handle the task of pointer meter reading recognition, in this paper, we propose a deep network model that can accurately detect the pointer meter dial and segment the pointer as well as the reference points from the located meter dial. Specifically, our proposed model is composed of three stages: meter dial location, reference point segmentation, and dial number reading recognition. In the first stage, we translate the task of meter dial location into a regression task, which aims to separate bounding boxes by an object detection network. This results in the accurate and fast detection of meter dials. In the second stage, the dial region image determined by the bounding box is further processed by using a deep semantic segmentation network. After that, the segmented output is used to calculate the relative position between the pointer and reference points in the third stage, which results in the final output of reading recognition. Some experiments were conducted on our collected dataset, and the experimental results show the effectiveness of our method, with a lower computational burden compared to some existing works. |
| first_indexed | 2024-03-07T22:43:33Z |
| format | Article |
| id | doaj.art-7325f83761834e998f503e650702912d |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-07T22:43:33Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-7325f83761834e998f503e650702912d2024-02-23T15:06:00ZengMDPI AGApplied Sciences2076-34172024-02-01144144310.3390/app14041443Pointer Meter Reading Recognition by Joint Detection and SegmentationYing Li0Xuemei Li1Caiming Zhang2School of Software, Shandong University, Jinan 250100, ChinaSchool of Software, Shandong University, Jinan 250100, ChinaSchool of Software, Shandong University, Jinan 250100, ChinaTo handle the task of pointer meter reading recognition, in this paper, we propose a deep network model that can accurately detect the pointer meter dial and segment the pointer as well as the reference points from the located meter dial. Specifically, our proposed model is composed of three stages: meter dial location, reference point segmentation, and dial number reading recognition. In the first stage, we translate the task of meter dial location into a regression task, which aims to separate bounding boxes by an object detection network. This results in the accurate and fast detection of meter dials. In the second stage, the dial region image determined by the bounding box is further processed by using a deep semantic segmentation network. After that, the segmented output is used to calculate the relative position between the pointer and reference points in the third stage, which results in the final output of reading recognition. Some experiments were conducted on our collected dataset, and the experimental results show the effectiveness of our method, with a lower computational burden compared to some existing works.https://www.mdpi.com/2076-3417/14/4/1443pointer meter readingobject detectiondeep convolutional networksemantic segmentation |
| spellingShingle | Ying Li Xuemei Li Caiming Zhang Pointer Meter Reading Recognition by Joint Detection and Segmentation Applied Sciences pointer meter reading object detection deep convolutional network semantic segmentation |
| title | Pointer Meter Reading Recognition by Joint Detection and Segmentation |
| title_full | Pointer Meter Reading Recognition by Joint Detection and Segmentation |
| title_fullStr | Pointer Meter Reading Recognition by Joint Detection and Segmentation |
| title_full_unstemmed | Pointer Meter Reading Recognition by Joint Detection and Segmentation |
| title_short | Pointer Meter Reading Recognition by Joint Detection and Segmentation |
| title_sort | pointer meter reading recognition by joint detection and segmentation |
| topic | pointer meter reading object detection deep convolutional network semantic segmentation |
| url | https://www.mdpi.com/2076-3417/14/4/1443 |
| work_keys_str_mv | AT yingli pointermeterreadingrecognitionbyjointdetectionandsegmentation AT xuemeili pointermeterreadingrecognitionbyjointdetectionandsegmentation AT caimingzhang pointermeterreadingrecognitionbyjointdetectionandsegmentation |