In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods.
[confproc]
Redmon, J.
/ 2016
/ You only look once: Unified, real-time object detection
/ Proceedings of the IEEE conference on computer vision and pattern recognition
: 779~788
[confproc]
Chandrappa, D. N.
/ 2011
/ Face detection in color images using skin color model algorithm based on skin color information
/ 2011 3rd International Conference on Electronics Computer Technology
/ IEEE
1
: 254~258
[other]
Joseph Redmon
/ 2018
/ Yolov3: An incremental improvement
/ arXiv preprint arXiv:1804.02767
[confproc]
Zhou, D
/ 2019
/ Iou loss for 2d/3d object detection
/ 2019International Conference on 3D Vision (3DV)
/ IEEE
: 85~94
[other]
Kingma, D. P.
/ 2014
/ Adam: A method for stochastic optimization
/ arXiv preprint arXiv:1412.6980
[confproc]
Jamil, N.
/ 2008
/ Noise removal and enhancement of binary images using morphological operations
/ 2008 International Symposium on Information Technology
/ IEEE
4
: 1~6
@article{ART002740824}, author={Chang-Hyun Lee and Hyun-Ji Lee and Seung-Hyun Lee and Joon-Taek Oh and PARK SEUNGBO}, title={Face Detection Using Shapes and Colors in Various Backgrounds}, journal={Journal of The Korea Society of Computer and Information}, issn={1598-849X}, year={2021}, volume={26}, number={7}, pages={19-27}, doi={10.9708/jksci.2021.26.07.019}
TY - JOUR AU - Chang-Hyun Lee AU - Hyun-Ji Lee AU - Seung-Hyun Lee AU - Joon-Taek Oh AU - PARK SEUNGBO TI - Face Detection Using Shapes and Colors in Various Backgrounds JO - Journal of The Korea Society of Computer and Information PY - 2021 VL - 26 IS - 7 PB - The Korean Society Of Computer And Information SP - 19 EP - 27 SN - 1598-849X AB - In this paper, we propose a method for detecting characters in images and detecting facial regions, which consists of two tasks. First, we separate two different characters to detect the face position of the characters in the frame. For fast detection, we use You Only Look Once (YOLO), which finds faces in the image in real time, to extract the location of the face and mark them as object detection boxes. Second, we present three image processing methods to detect accurate face area based on object detection boxes. Each method uses HSV values extracted from the region estimated by the detection figure to detect the face region of the characters, and changes the size and shape of the detection figure to compare the accuracy of each method. Each face detection method is compared and analyzed with comparative data and image processing data for reliability verification. As a result, we achieved the highest accuracy of 87% when using the split rectangular method among circular, rectangular, and split rectangular methods. KW - Facial Region Detection;Face Detection;Open CV;Image Processing;Character Classification DO - 10.9708/jksci.2021.26.07.019 ER -
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh and PARK SEUNGBO. (2021). Face Detection Using Shapes and Colors in Various Backgrounds. Journal of The Korea Society of Computer and Information, 26(7), 19-27.
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh and PARK SEUNGBO. 2021, "Face Detection Using Shapes and Colors in Various Backgrounds", Journal of The Korea Society of Computer and Information, vol.26, no.7 pp.19-27. Available from: doi:10.9708/jksci.2021.26.07.019
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh, PARK SEUNGBO "Face Detection Using Shapes and Colors in Various Backgrounds" Journal of The Korea Society of Computer and Information 26.7 pp.19-27 (2021) : 19.
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh, PARK SEUNGBO. Face Detection Using Shapes and Colors in Various Backgrounds. 2021; 26(7), 19-27. Available from: doi:10.9708/jksci.2021.26.07.019
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh and PARK SEUNGBO. "Face Detection Using Shapes and Colors in Various Backgrounds" Journal of The Korea Society of Computer and Information 26, no.7 (2021) : 19-27.doi: 10.9708/jksci.2021.26.07.019
Chang-Hyun Lee; Hyun-Ji Lee; Seung-Hyun Lee; Joon-Taek Oh; PARK SEUNGBO. Face Detection Using Shapes and Colors in Various Backgrounds. Journal of The Korea Society of Computer and Information, 26(7), 19-27. doi: 10.9708/jksci.2021.26.07.019
Chang-Hyun Lee; Hyun-Ji Lee; Seung-Hyun Lee; Joon-Taek Oh; PARK SEUNGBO. Face Detection Using Shapes and Colors in Various Backgrounds. Journal of The Korea Society of Computer and Information. 2021; 26(7) 19-27. doi: 10.9708/jksci.2021.26.07.019
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh, PARK SEUNGBO. Face Detection Using Shapes and Colors in Various Backgrounds. 2021; 26(7), 19-27. Available from: doi:10.9708/jksci.2021.26.07.019
Chang-Hyun Lee, Hyun-Ji Lee, Seung-Hyun Lee, Joon-Taek Oh and PARK SEUNGBO. "Face Detection Using Shapes and Colors in Various Backgrounds" Journal of The Korea Society of Computer and Information 26, no.7 (2021) : 19-27.doi: 10.9708/jksci.2021.26.07.019