当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Improving Face Recognition Performance using TeCS2 Dictionary
Pattern Recognition Letters ( IF 3.255 ) Pub Date : 2021-01-13 , DOI: 10.1016/j.patrec.2020.12.022
Saksham Suri; Anush Sankaran; Mayank Vatsa; Richa Singh

Human mind processes the different primitive components of image signals such as color, shape, texture, and symmetry in a parallel and complex fashion. Deep neural networks aim to learn all these components from the image in an unsupervised manner. However, learning the primitive features is not formally assured in a deep learning formulation, and, adding these feature explicitly would improve the performance. Especially in face recognition, humans intuitively and implicitly employ the usage of primitive features such as color, shape, texture, and symmetry of faces. Inspired from this observation, this paper presents a novel approach in building a learning based TeCS2 space. This space consists of meta-level features obtained from dictionary learning and combining it with task specific deep learning classifiers (such as DenseNet) for object recognition. Confidence based fusion mechanism is presented to supplement the task specific deep learning classifier with the proposed TeCS2 features. The effectiveness of the proposed framework is evaluated on four benchmark face recognition datasets: (i) Disguised Faces in the Wild (DFW), (ii) Labeled faces in the wild (LFW), (iii) IIITD Plastic Surgery dataset, and (iv) Point and Shoot Challenge (PaSC).



中文翻译:

使用TeCS改善人脸识别性能2 字典

人脑以并行和复杂的方式处理图像信号的不同原始成分,例如颜色,形状,纹理和对称性。深度神经网络旨在以无人监督的方式从图像中学习所有这些成分。但是,在深度学习公式中不能正式保证学习原始功能,并且明确添加这些功能将提高性能。尤其是在人脸识别中,人类会直观,隐式地使用原始特征(例如颜色,形状,纹理和人脸对称性)的用法。从这一观察中得到启发,本文提出了一种构建基于学习的TeCS的新颖方法2空间。该空间包括从字典学习中获得的元级功能,并将其与特定于任务的深度学习分类器(例如DenseNet)相结合,以进行对象识别。提出了基于置信度的融合机制,以使用拟议的TeCS补充任务特定的深度学习分类器2特征。在四个基准人脸识别数据集上评估了所提出框架的有效性:(i)野外变相人脸(DFW),(ii)野外有标签人脸(LFW),(iii)IIITD整形外科数据集和(iv )指向射击挑战赛(PaSC)。

更新日期:2021-01-13
全部期刊列表>>
微生物研究
亚洲大洋洲地球科学
NPJ欢迎投稿
自然科研论文编辑
ERIS期刊投稿
欢迎阅读创刊号
自然职场,为您触达千万科研人才
spring&清华大学出版社
城市可持续发展前沿研究专辑
Springer 纳米技术权威期刊征稿
全球视野覆盖
施普林格·自然新
chemistry
物理学研究前沿热点精选期刊推荐
自然职位线上招聘会
欢迎报名注册2020量子在线大会
化学领域亟待解决的问题
材料学研究精选新
GIANT
ACS ES&T Engineering
ACS ES&T Water
屿渡论文,编辑服务
阿拉丁试剂right
上海中医药大学
浙江大学
西湖大学
化学所
北京大学
清华
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
清华大学-1
武汉大学
浙江大学
天合科研
x-mol收录
试剂库存
down
wechat
bug