An optimal defect recognition security-based terahertz low resolution image system using deep learning network
The physics of Terahertz (THz) technology is the electromagnetic (EM) spectrum band between the infrared and the microwave band with frequencies of about 0.1 to 30 THz. THz signals have gained adoption in medicine, telecommunications, security monitoring and imaging. THz imaging technology has the a...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-09-01
|
| Series: | Egyptian Informatics Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110866523000324 |
| _version_ | 1797729993093021696 |
|---|---|
| author | Samuel Akwasi Danso Shang Liping Deng Hu Samuel Afoakwa Eugene Louis Badzongoly Justice Odoom Owais Muhammad Muhammad Umer Mushtaq Abdul Qayoom Wenqing Zhou |
| author_facet | Samuel Akwasi Danso Shang Liping Deng Hu Samuel Afoakwa Eugene Louis Badzongoly Justice Odoom Owais Muhammad Muhammad Umer Mushtaq Abdul Qayoom Wenqing Zhou |
| author_sort | Samuel Akwasi Danso |
| collection | DOAJ |
| description | The physics of Terahertz (THz) technology is the electromagnetic (EM) spectrum band between the infrared and the microwave band with frequencies of about 0.1 to 30 THz. THz signals have gained adoption in medicine, telecommunications, security monitoring and imaging. THz imaging technology has the advantages of rapid imaging, strong penetration, and harmless to the human body hence widely used in a variety of security environments and has become an alternative technology for X-ray imaging. However, THz is characterized by low resolution of THz images of which noise is an integral factor constituting a defect. Clarity of THz image is therefore essential at various security checkpoints to avoid life’s dangers and treats. In this paper, we propose an efficient and high-performance defect detection model based on RetinaNet to recognize defects from captured images. The strategy of transfer learning is introduced to improve detection performance accuracy, which enhances the average precision (AP) by 19.2%. Contrary to existing THz image detection techniques on image recognition pertaining to the whole region of the image, we adopt a different approach via differential evolution search algorithm for optimization given the small proportion of defect area which improves the AP by 9.9% comparing with the fine-tuned model. For the problem of the lack of defect data samples, image augmentation is adopted to enrich our training samples, which improves the AP by 9.5%. As for the problem of low precision and recall in detecting blurred images, we firstly manually generate clear-blurred image pairs to train a GAN. Then, the blurred images are deblurred using a trained generator. We get 5.5% AP improvement on the testset using our approach. Compared with existing works, the optimized model based on RetinaNet has better detection performance, subsequently, proving the practicability and effectiveness of the proposed method. |
| first_indexed | 2024-03-12T11:37:37Z |
| format | Article |
| id | doaj.art-a55cb00739e8445ba72e5a6732473ae4 |
| institution | Directory Open Access Journal |
| issn | 1110-8665 |
| language | English |
| last_indexed | 2024-03-12T11:37:37Z |
| publishDate | 2023-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Egyptian Informatics Journal |
| spelling | doaj.art-a55cb00739e8445ba72e5a6732473ae42023-09-01T05:00:49ZengElsevierEgyptian Informatics Journal1110-86652023-09-01243100384An optimal defect recognition security-based terahertz low resolution image system using deep learning networkSamuel Akwasi Danso0Shang Liping1Deng Hu2Samuel Afoakwa3Eugene Louis Badzongoly4Justice Odoom5Owais Muhammad6Muhammad Umer Mushtaq7Abdul Qayoom8Wenqing Zhou9Ghana Communication Technology University, Ghana; Southwest University of Science and Technology-Mianyang -Sichuan, China; Corresponding author at: Ghana Communication Technology University, Ghana.Southwest University of Science and Technology-Mianyang -Sichuan, ChinaSouthwest University of Science and Technology-Mianyang -Sichuan, ChinaGhana Communication Technology University, GhanaGhana Communication Technology University, GhanaSouthwest University of Science and Technology-Mianyang -Sichuan, ChinaSouthwest University of Science and Technology-Mianyang -Sichuan, ChinaSouthwest University of Science and Technology-Mianyang -Sichuan, ChinaSouthwest University of Science and Technology-Mianyang -Sichuan, ChinaSouth China University of Technology, Guangzhou, ChinaThe physics of Terahertz (THz) technology is the electromagnetic (EM) spectrum band between the infrared and the microwave band with frequencies of about 0.1 to 30 THz. THz signals have gained adoption in medicine, telecommunications, security monitoring and imaging. THz imaging technology has the advantages of rapid imaging, strong penetration, and harmless to the human body hence widely used in a variety of security environments and has become an alternative technology for X-ray imaging. However, THz is characterized by low resolution of THz images of which noise is an integral factor constituting a defect. Clarity of THz image is therefore essential at various security checkpoints to avoid life’s dangers and treats. In this paper, we propose an efficient and high-performance defect detection model based on RetinaNet to recognize defects from captured images. The strategy of transfer learning is introduced to improve detection performance accuracy, which enhances the average precision (AP) by 19.2%. Contrary to existing THz image detection techniques on image recognition pertaining to the whole region of the image, we adopt a different approach via differential evolution search algorithm for optimization given the small proportion of defect area which improves the AP by 9.9% comparing with the fine-tuned model. For the problem of the lack of defect data samples, image augmentation is adopted to enrich our training samples, which improves the AP by 9.5%. As for the problem of low precision and recall in detecting blurred images, we firstly manually generate clear-blurred image pairs to train a GAN. Then, the blurred images are deblurred using a trained generator. We get 5.5% AP improvement on the testset using our approach. Compared with existing works, the optimized model based on RetinaNet has better detection performance, subsequently, proving the practicability and effectiveness of the proposed method.http://www.sciencedirect.com/science/article/pii/S1110866523000324Defect recognitionDifferential evolution search algorithmFeature pyramid networkGenerative adversarial networkLow resolutionTerahertz image |
| spellingShingle | Samuel Akwasi Danso Shang Liping Deng Hu Samuel Afoakwa Eugene Louis Badzongoly Justice Odoom Owais Muhammad Muhammad Umer Mushtaq Abdul Qayoom Wenqing Zhou An optimal defect recognition security-based terahertz low resolution image system using deep learning network Egyptian Informatics Journal Defect recognition Differential evolution search algorithm Feature pyramid network Generative adversarial network Low resolution Terahertz image |
| title | An optimal defect recognition security-based terahertz low resolution image system using deep learning network |
| title_full | An optimal defect recognition security-based terahertz low resolution image system using deep learning network |
| title_fullStr | An optimal defect recognition security-based terahertz low resolution image system using deep learning network |
| title_full_unstemmed | An optimal defect recognition security-based terahertz low resolution image system using deep learning network |
| title_short | An optimal defect recognition security-based terahertz low resolution image system using deep learning network |
| title_sort | optimal defect recognition security based terahertz low resolution image system using deep learning network |
| topic | Defect recognition Differential evolution search algorithm Feature pyramid network Generative adversarial network Low resolution Terahertz image |
| url | http://www.sciencedirect.com/science/article/pii/S1110866523000324 |
| work_keys_str_mv | AT samuelakwasidanso anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT shangliping anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT denghu anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT samuelafoakwa anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT eugenelouisbadzongoly anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT justiceodoom anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT owaismuhammad anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT muhammadumermushtaq anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT abdulqayoom anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT wenqingzhou anoptimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT samuelakwasidanso optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT shangliping optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT denghu optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT samuelafoakwa optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT eugenelouisbadzongoly optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT justiceodoom optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT owaismuhammad optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT muhammadumermushtaq optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT abdulqayoom optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork AT wenqingzhou optimaldefectrecognitionsecuritybasedterahertzlowresolutionimagesystemusingdeeplearningnetwork |