Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition
There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-09-01
|
| Series: | Fractal and Fractional |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-3110/8/10/551 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850205605117034496 |
|---|---|
| author | Dong Chan Lee Min Su Jeong Seong In Jeong Seung Yong Jung Kang Ryoung Park |
| author_facet | Dong Chan Lee Min Su Jeong Seong In Jeong Seung Yong Jung Kang Ryoung Park |
| author_sort | Dong Chan Lee |
| collection | DOAJ |
| description | There are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods. |
| format | Article |
| id | doaj-art-a136a1e4a9bc485f91b84f59742e17d0 |
| institution | OA Journals |
| issn | 2504-3110 |
| language | English |
| publishDate | 2024-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fractal and Fractional |
| spelling | doaj-art-a136a1e4a9bc485f91b84f59742e17d02025-08-20T02:11:04ZengMDPI AGFractal and Fractional2504-31102024-09-0181055110.3390/fractalfract8100551Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender RecognitionDong Chan Lee0Min Su Jeong1Seong In Jeong2Seung Yong Jung3Kang Ryoung Park4Division of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaDivision of Electronics and Electrical Engineering, Dongguk University, 30 Pildong-ro 1-gil, Jung-gu, Seoul 04620, Republic of KoreaThere are few studies utilizing only IR cameras for long-distance gender recognition, and they have shown low recognition performance due to their lack of color and texture information in IR images with a complex background. Therefore, a rough body segmentation-based gender recognition network (RBSG-Net) is proposed, with enhanced gender recognition performance achieved by emphasizing the silhouette of a person through a body segmentation network. Anthropometric loss for the segmentation network and an adaptive body attention module are also proposed, which effectively integrate the segmentation and classification networks. To enhance the analytic capabilities of the proposed framework, fractal dimension estimation was introduced into the system to gain insights into the complexity and irregularity of the body region, thereby predicting the accuracy of body segmentation. For experiments, near-infrared images from the Sun Yat-sen University multiple modality re-identification version 1 (SYSU-MM01) dataset and thermal images from the Dongguk body-based gender version 2 (DBGender-DB2) database were used. The equal error rates of gender recognition by the proposed model were 4.320% and 8.303% for these two databases, respectively, surpassing state-of-the-art methods.https://www.mdpi.com/2504-3110/8/10/551gender recognitioninfrared light imagesfractal dimensionbody segmentationsurveillance system |
| spellingShingle | Dong Chan Lee Min Su Jeong Seong In Jeong Seung Yong Jung Kang Ryoung Park Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition Fractal and Fractional gender recognition infrared light images fractal dimension body segmentation surveillance system |
| title | Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition |
| title_full | Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition |
| title_fullStr | Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition |
| title_full_unstemmed | Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition |
| title_short | Estimation of Fractal Dimension and Segmentation of Body Regions for Deep Learning-Based Gender Recognition |
| title_sort | estimation of fractal dimension and segmentation of body regions for deep learning based gender recognition |
| topic | gender recognition infrared light images fractal dimension body segmentation surveillance system |
| url | https://www.mdpi.com/2504-3110/8/10/551 |
| work_keys_str_mv | AT dongchanlee estimationoffractaldimensionandsegmentationofbodyregionsfordeeplearningbasedgenderrecognition AT minsujeong estimationoffractaldimensionandsegmentationofbodyregionsfordeeplearningbasedgenderrecognition AT seonginjeong estimationoffractaldimensionandsegmentationofbodyregionsfordeeplearningbasedgenderrecognition AT seungyongjung estimationoffractaldimensionandsegmentationofbodyregionsfordeeplearningbasedgenderrecognition AT kangryoungpark estimationoffractaldimensionandsegmentationofbodyregionsfordeeplearningbasedgenderrecognition |