Tactile Object Recognition Using Joint Sparse Coding

2018 ◽  
pp. 47-69
Author(s):  
Huaping Liu ◽  
Fuchun Sun
Keyword(s):  
Object Recognition ◽  
Sparse Coding

Learning Optimized Features for Hierarchical Models of Invariant Object Recognition

2003 ◽  
Vol 15 (7) ◽  
pp. 1559-1588 ◽  
Author(s):  
Heiko Wersing ◽  
Edgar Körner
Keyword(s):  
Object Recognition ◽  
Sparse Coding ◽  
Hierarchical Models ◽  
Feature Detection ◽  
Recognition Performance ◽  
Feature Representation ◽  
Translation Invariance ◽  
Hierarchical Network ◽  
Data Set ◽  
Invariant Object Recognition

There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.

Biological modeling of human visual system for object recognition using GLoP filters and sparse coding on multi-manifolds

2018 ◽  
Vol 29 (6) ◽  
pp. 965-977 ◽  
Author(s):  
Limiao Deng ◽  
Yanjiang Wang ◽  
Baodi Liu ◽  
Weifeng Liu ◽  
Yujuan Qi
Keyword(s):  
Object Recognition ◽  
Visual System ◽  
Sparse Coding ◽  
Human Visual System ◽  
Biological Modeling

Object Recognition Using Tactile Measurements: Kernel Sparse Coding Methods

2016 ◽  
Vol 65 (3) ◽  
pp. 656-665 ◽  
Author(s):  
Huaping Liu ◽  
Di Guo ◽  
Fuchun Sun
Keyword(s):  
Object Recognition ◽  
Sparse Coding

Research on Bioinformatics with Sparse Feature Fusion for Object Recognition

2013 ◽  
Vol 830 ◽  
pp. 485-489
Author(s):  
Shu Fang Wu ◽  
Jie Zhu ◽  
Zhao Feng Zhang
Keyword(s):  
Object Recognition ◽  
Sparse Coding ◽  
Feature Fusion ◽  
Image Representation ◽  
Experimental Results ◽  
Bag Of Words ◽  
Fusion Algorithm ◽  
Fusion Methods

Combining multiple bioinformatics such as shape and color is a challenging task in object recognition. Usually, we believe that if more different bioinformatics are considered in object recognition, then we could get better result. Bag-of-words-based image representation is one of the most relevant approaches; many feature fusion methods are based on this model. Sparse coding has attracted a considerable amount of attention in many domains. A novel sparse feature fusion algorithm is proposed to fuse multiple bioinformatics to represent the images. Experimental results show good performance of the proposed algorithm.

scholarly journals Fast Approximation for Sparse Coding with Applications to Object Recognition

Sensors ◽  
2021 ◽  
Vol 21 (4) ◽  
pp. 1442 ◽  
Author(s):  
Zhenzhen Sun ◽  
Yuanlong Yu
Keyword(s):  
Object Recognition ◽  
Sparse Coding ◽  
Recognition Performance ◽  
Computational Cost ◽  
Ground Truth ◽  
Computational Time ◽  
Small Scale ◽  
Training Samples ◽  
Hidden Layer ◽  
Sparse Features

Sparse Coding (SC) has been widely studied and shown its superiority in the fields of signal processing, statistics, and machine learning. However, due to the high computational cost of the optimization algorithms required to compute the sparse feature, the applicability of SC to real-time object recognition tasks is limited. Many deep neural networks have been constructed to low fast estimate the sparse feature with the help of a large number of training samples, which is not suitable for small-scale datasets. Therefore, this work presents a simple and efficient fast approximation method for SC, in which a special single-hidden-layer neural network (SLNNs) is constructed to perform the approximation task, and the optimal sparse features of training samples exactly computed by sparse coding algorithm are used as ground truth to train the SLNNs. After training, the proposed SLNNs can quickly estimate sparse features for testing samples. Ten benchmark data sets taken from UCI databases and two face image datasets are used for experiment, and the low root mean square error (RMSE) results between the approximated sparse features and the optimal ones have verified the approximation performance of this proposed method. Furthermore, the recognition results demonstrate that the proposed method can effectively reduce the computational time of testing process while maintaining the recognition performance, and outperforms several state-of-the-art fast approximation sparse coding methods, as well as the exact sparse coding algorithms.

Sign in / Sign up

Export Citation Format

Share Document