scholarly journals A Discriminative Framework for Texture and Object Recognition Using Local Image Features

2006 ◽  
pp. 423-442 ◽  
Author(s):  
Svetlana Lazebnik ◽  
Cordelia Schmid ◽  
Jean Ponce
Keyword(s):  
Object Recognition ◽  
Image Features ◽  
Local Image ◽  
Local Image Features

Multiclass Object Recognition Using Object-based and Local Image Features Extractors

2015 ◽  
Author(s):  
Menna Maged Kamel ◽  
Mohamed Waleed Fakhr ◽  
H. I. Saleh ◽  
M. B. Abdelhalim
Keyword(s):  
Object Recognition ◽  
Image Features ◽  
Object Based ◽  
Local Image ◽  
Local Image Features

scholarly journals 3D Affine: An Embedding of Local Image Features for Viewpoint Invariance Using RGB-D Sensor Data

Sensors ◽  
2019 ◽  
Vol 19 (2) ◽  
pp. 291 ◽  
Author(s):  
Hamdi Sahloul ◽  
Shouhei Shirafuji ◽  
Jun Ota
Keyword(s):  
Low Cost ◽  
Image Features ◽  
Image Feature ◽  
Sensor Data ◽  
Invariant Representation ◽  
Depth Sensors ◽  
Viewpoint Invariance ◽  
Surface Discontinuities ◽  
Local Image ◽  
Local Image Features

Local image features are invariant to in-plane rotations and robust to minor viewpoint changes. However, the current detectors and descriptors for local image features fail to accommodate out-of-plane rotations larger than 25°–30°. Invariance to such viewpoint changes is essential for numerous applications, including wide baseline matching, 6D pose estimation, and object reconstruction. In this study, we present a general embedding that wraps a detector/descriptor pair in order to increase viewpoint invariance by exploiting input depth maps. The proposed embedding locates smooth surfaces within the input RGB-D images and projects them into a viewpoint invariant representation, enabling the detection and description of more viewpoint invariant features. Our embedding can be utilized with different combinations of descriptor/detector pairs, according to the desired application. Using synthetic and real-world objects, we evaluated the viewpoint invariance of various detectors and descriptors, for both standalone and embedded approaches. While standalone local image features fail to accommodate average viewpoint changes beyond 33.3°, our proposed embedding boosted the viewpoint invariance to different levels, depending on the scene geometry. Objects with distinct surface discontinuities were on average invariant up to 52.8°, and the overall average for all evaluated datasets was 45.4°. Similarly, out of a total of 140 combinations involving 20 local image features and various objects with distinct surface discontinuities, only a single standalone local image feature exceeded the goal of 60° viewpoint difference in just two combinations, as compared with 19 different local image features succeeding in 73 combinations when wrapped in the proposed embedding. Furthermore, the proposed approach operates robustly in the presence of input depth noise, even that of low-cost commodity depth sensors, and well beyond.

scholarly journals Local image features dominate responses of AM and AF face patch neurons

2019 ◽  
Vol 19 (10) ◽  
pp. 259b
Author(s):  
Elena Waidmann ◽  
Kenji W Koyano ◽  
Julie J Hong ◽  
Brian E Russ ◽  
David A Leopold
Keyword(s):  
Image Features ◽  
Local Image ◽  
Local Image Features

Data Hiding Method Based on Local Image Features

2012 ◽  
pp. 247-256 ◽  
Author(s):  
Xianquan Zhang ◽  
Zhenjun Tang ◽  
Tao Liang ◽  
Shichao Zhang ◽  
Yingjun Zhu ◽  
...  
Keyword(s):  
Data Hiding ◽  
Image Features ◽  
Local Image ◽  
Local Image Features

Motion estimation based on eigenvalue algorithm matching local image features

2003 ◽  
Vol 34 (14) ◽  
pp. 63-72 ◽  
Author(s):  
Yutaka Kaneko ◽  
Yoshiaki Shishikui ◽  
Yutaka Tanaka
Keyword(s):  
Motion Estimation ◽  
Image Features ◽  
Local Image ◽  
Local Image Features
Sign in / Sign up

Export Citation Format

Share Document