Improved salient object detection using hybrid Convolution Recurrent Neural Network

2021 ◽  
Vol 166 ◽  
pp. 114064
Author(s):  
NalliyannaV. Kousik ◽  
Yuvaraj Natarajan ◽  
R. Arshath Raja ◽  
Suresh Kallam ◽  
Rizwan Patan ◽  
...  
2019 ◽  
Vol 26 (1) ◽  
pp. 114-118 ◽  
Author(s):  
Wenlong Guan ◽  
Tiantian Wang ◽  
Jinqing Qi ◽  
Lihe Zhang ◽  
Huchuan Lu

2021 ◽  
pp. 104243
Author(s):  
Zhenyu Wang ◽  
Yunzhou Zhang ◽  
Yan Liu ◽  
Shichang Liu ◽  
Sonya Coleman ◽  
...  

2015 ◽  
Vol 115 (3) ◽  
pp. 330-344 ◽  
Author(s):  
Shengfeng He ◽  
Rynson W. H. Lau ◽  
Wenxi Liu ◽  
Zhe Huang ◽  
Qingxiong Yang

2019 ◽  
Vol 363 ◽  
pp. 46-57 ◽  
Author(s):  
Zhengyi Liu ◽  
Song Shi ◽  
Quntao Duan ◽  
Wei Zhang ◽  
Peng Zhao

2016 ◽  
Vol 25 (8) ◽  
pp. 3919-3930 ◽  
Author(s):  
Xi Li ◽  
Liming Zhao ◽  
Lina Wei ◽  
Ming-Hsuan Yang ◽  
Fei Wu ◽  
...  

2021 ◽  
pp. 1-10
Author(s):  
T. Revathi ◽  
T.M. Rajalaxmi ◽  
R. Sundara Rajan ◽  
Wilhelm Passarella Freire

Salient object detection plays a vital role in image processing applications like image retrieval, security and surveillance in authentic-time. In recent times, advances in deep neural network gained more attention in the automatic learning system for various computer vision applications. In order to decrement the detection error for efficacious object detection, we proposed a detection classifier to detect the features of the object utilizing a deep neural network called convolutional neural network (CNN) and discrete quaternion Fourier transform (DQFT). Prior to CNN, the image is pre-processed by DQFT in order to handle all the three colors holistically to evade loss of image information, which in-turn increase the effective use of object detection. The features of the image are learned by training model of CNN, where the CNN process is done in the Fourier domain to quicken the method in productive computational time, and the image is converted to spatial domain before processing the fully connected layer. The proposed model is implemented in the HDA and INRIA benchmark datasets. The outcome shows that convolution in the quaternion Fourier domain expedite the process of evaluation with amended detection rate. The comparative study is done with CNN, discrete Fourier transforms CNN, RNN ad masked RNN.


Sign in / Sign up

Export Citation Format

Share Document