A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks
Heated metal mark is an important trace to identify the cause of fire. However, traditional methods mainly focus on the knowledge of physics and chemistry for qualitative analysis and make it still a challenging problem. This paper presents a case study on attribute recognition of the heated metal m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/6/1871 |
| _version_ | 1811302448993665024 |
|---|---|
| author | Keming Mao Duo Lu Dazhi E Zhenhua Tan |
| author_facet | Keming Mao Duo Lu Dazhi E Zhenhua Tan |
| author_sort | Keming Mao |
| collection | DOAJ |
| description | Heated metal mark is an important trace to identify the cause of fire. However, traditional methods mainly focus on the knowledge of physics and chemistry for qualitative analysis and make it still a challenging problem. This paper presents a case study on attribute recognition of the heated metal mark image using computer vision and machine learning technologies. The proposed work is composed of three parts. Material is first generated. According to national standards, actual needs and feasibility, seven attributes are selected for research. Data generation and organization are conducted, and a small size benchmark dataset is constructed. A recognition model is then implemented. Feature representation and classifier construction methods are introduced based on deep convolutional neural networks. Finally, the experimental evaluation is carried out. Multi-aspect testings are performed with various model structures, data augments, training modes, optimization methods and batch sizes. The influence of parameters, recognitio efficiency and execution time are also analyzed. The results show that with a fine-tuned model, the recognition rate of attributes metal type, heating mode, heating temperature, heating duration, cooling mode, placing duration and relative humidity are 0.925, 0.908, 0.835, 0.917, 0.928, 0.805 and 0.92, respectively. The proposed method recognizes the attribute of heated metal mark with preferable effect, and it can be used in practical application. |
| first_indexed | 2024-04-13T07:28:00Z |
| format | Article |
| id | doaj.art-9b58b74ca6454720a07e5628162bd898 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T07:28:00Z |
| publishDate | 2018-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-9b58b74ca6454720a07e5628162bd8982022-12-22T02:56:26ZengMDPI AGSensors1424-82202018-06-01186187110.3390/s18061871s18061871A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural NetworksKeming Mao0Duo Lu1Dazhi E2Zhenhua Tan3College of Software, Northeastern University, Shenyang 110004, ChinaCollege of Software, Northeastern University, Shenyang 110004, ChinaShenyang Fire Research Institute, Ministry of Public Security, Shenyang 110034, ChinaCollege of Software, Northeastern University, Shenyang 110004, ChinaHeated metal mark is an important trace to identify the cause of fire. However, traditional methods mainly focus on the knowledge of physics and chemistry for qualitative analysis and make it still a challenging problem. This paper presents a case study on attribute recognition of the heated metal mark image using computer vision and machine learning technologies. The proposed work is composed of three parts. Material is first generated. According to national standards, actual needs and feasibility, seven attributes are selected for research. Data generation and organization are conducted, and a small size benchmark dataset is constructed. A recognition model is then implemented. Feature representation and classifier construction methods are introduced based on deep convolutional neural networks. Finally, the experimental evaluation is carried out. Multi-aspect testings are performed with various model structures, data augments, training modes, optimization methods and batch sizes. The influence of parameters, recognitio efficiency and execution time are also analyzed. The results show that with a fine-tuned model, the recognition rate of attributes metal type, heating mode, heating temperature, heating duration, cooling mode, placing duration and relative humidity are 0.925, 0.908, 0.835, 0.917, 0.928, 0.805 and 0.92, respectively. The proposed method recognizes the attribute of heated metal mark with preferable effect, and it can be used in practical application.http://www.mdpi.com/1424-8220/18/6/1871attribute recognitionheated metal markconvolutional neural networks |
| spellingShingle | Keming Mao Duo Lu Dazhi E Zhenhua Tan A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks Sensors attribute recognition heated metal mark convolutional neural networks |
| title | A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks |
| title_full | A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks |
| title_fullStr | A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks |
| title_full_unstemmed | A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks |
| title_short | A Case Study on Attribute Recognition of Heated Metal Mark Image Using Deep Convolutional Neural Networks |
| title_sort | case study on attribute recognition of heated metal mark image using deep convolutional neural networks |
| topic | attribute recognition heated metal mark convolutional neural networks |
| url | http://www.mdpi.com/1424-8220/18/6/1871 |
| work_keys_str_mv | AT kemingmao acasestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT duolu acasestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT dazhie acasestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT zhenhuatan acasestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT kemingmao casestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT duolu casestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT dazhie casestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks AT zhenhuatan casestudyonattributerecognitionofheatedmetalmarkimageusingdeepconvolutionalneuralnetworks |