Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods
Abstract Recent attention to facial alignment and landmark detection methods, particularly with application of deep convolutional neural networks, have yielded notable improvements. Neither these neural-network nor more traditional methods, though, have been tested directly regarding performance dif...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2021-03-01
|
| Series: | EURASIP Journal on Image and Video Processing |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13640-021-00549-3 |
| _version_ | 1818436229817958400 |
|---|---|
| author | Xiang Li Jianzheng Liu Jessica Baron Khoa Luu Eric Patterson |
| author_facet | Xiang Li Jianzheng Liu Jessica Baron Khoa Luu Eric Patterson |
| author_sort | Xiang Li |
| collection | DOAJ |
| description | Abstract Recent attention to facial alignment and landmark detection methods, particularly with application of deep convolutional neural networks, have yielded notable improvements. Neither these neural-network nor more traditional methods, though, have been tested directly regarding performance differences due to camera-lens focal length nor camera viewing angle of subjects systematically across the viewing hemisphere. This work uses photo-realistic, synthesized facial images with varying parameters and corresponding ground-truth landmarks to enable comparison of alignment and landmark detection techniques relative to general performance, performance across focal length, and performance across viewing angle. Recently published high-performing methods along with traditional techniques are compared in regards to these aspects. |
| first_indexed | 2024-12-14T17:05:28Z |
| format | Article |
| id | doaj.art-b97e9bb7397e4eb0ad0c8ab65232fc50 |
| institution | Directory Open Access Journal |
| issn | 1687-5281 |
| language | English |
| last_indexed | 2024-12-14T17:05:28Z |
| publishDate | 2021-03-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Image and Video Processing |
| spelling | doaj.art-b97e9bb7397e4eb0ad0c8ab65232fc502022-12-21T22:53:45ZengSpringerOpenEURASIP Journal on Image and Video Processing1687-52812021-03-012021111810.1186/s13640-021-00549-3Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methodsXiang Li0Jianzheng Liu1Jessica Baron2Khoa Luu3Eric Patterson4School of Computing, Clemson UniversityCollege of Computer Science & Information Engineering, Tianjin University of Science & TechnologySchool of Computing, Clemson UniversityDepartment of Computer Science and Computer Engineering, University of ArkansasSchool of Computing, Clemson UniversityAbstract Recent attention to facial alignment and landmark detection methods, particularly with application of deep convolutional neural networks, have yielded notable improvements. Neither these neural-network nor more traditional methods, though, have been tested directly regarding performance differences due to camera-lens focal length nor camera viewing angle of subjects systematically across the viewing hemisphere. This work uses photo-realistic, synthesized facial images with varying parameters and corresponding ground-truth landmarks to enable comparison of alignment and landmark detection techniques relative to general performance, performance across focal length, and performance across viewing angle. Recently published high-performing methods along with traditional techniques are compared in regards to these aspects.https://doi.org/10.1186/s13640-021-00549-3Facial alignment and landmarkingConvolutional neural networksFocal lengthView angleComparisonEvaluation |
| spellingShingle | Xiang Li Jianzheng Liu Jessica Baron Khoa Luu Eric Patterson Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods EURASIP Journal on Image and Video Processing Facial alignment and landmarking Convolutional neural networks Focal length View angle Comparison Evaluation |
| title | Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| title_full | Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| title_fullStr | Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| title_full_unstemmed | Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| title_short | Evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| title_sort | evaluating effects of focal length and viewing angle in a comparison of recent face landmark and alignment methods |
| topic | Facial alignment and landmarking Convolutional neural networks Focal length View angle Comparison Evaluation |
| url | https://doi.org/10.1186/s13640-021-00549-3 |
| work_keys_str_mv | AT xiangli evaluatingeffectsoffocallengthandviewingangleinacomparisonofrecentfacelandmarkandalignmentmethods AT jianzhengliu evaluatingeffectsoffocallengthandviewingangleinacomparisonofrecentfacelandmarkandalignmentmethods AT jessicabaron evaluatingeffectsoffocallengthandviewingangleinacomparisonofrecentfacelandmarkandalignmentmethods AT khoaluu evaluatingeffectsoffocallengthandviewingangleinacomparisonofrecentfacelandmarkandalignmentmethods AT ericpatterson evaluatingeffectsoffocallengthandviewingangleinacomparisonofrecentfacelandmarkandalignmentmethods |