scholarly journals Occluded Image Object Recognition using Localized Nonnegative Matrix Factorization Methods

10.5772/14124 ◽  
2011 ◽  
Author(s):  
Ivan Bajla ◽  
Daniel Soukup ◽  
Svorad Stolc
Keyword(s):  
Object Recognition ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Factorization Methods ◽  
Image Object

Multi-view clustering based on graph-regularized nonnegative matrix factorization for object recognition

2018 ◽  
Vol 432 ◽  
pp. 463-478 ◽  
Author(s):  
Xinyu Zhang ◽  
Hongbo Gao ◽  
Guopeng Li ◽  
Jianhui Zhao ◽  
Jianghao Huo ◽  
...  
Keyword(s):  
Object Recognition ◽  
Matrix Factorization ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix

scholarly journals A Model for Learning Topographically Organized Parts-Based Representations of Objects in Visual Cortex: Topographic Nonnegative Matrix Factorization

2009 ◽  
Vol 21 (9) ◽  
pp. 2605-2633 ◽  
Author(s):  
Kenji Hosoda ◽  
Masataka Watanabe ◽  
Heiko Wersing ◽  
Edgar Körner ◽  
Hiroshi Tsujino ◽  
...  
Keyword(s):  
Visual Cortex ◽  
Object Recognition ◽  
Matrix Factorization ◽  
Object Representation ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Basis Functions ◽  
Topographic Map ◽  
Data Set ◽  
View Change

Object representation in the inferior temporal cortex (IT), an area of visual cortex critical for object recognition in the primate, exhibits two prominent properties: (1) objects are represented by the combined activity of columnar clusters of neurons, with each cluster representing component features or parts of objects, and (2) closely related features are continuously represented along the tangential direction of individual columnar clusters. Here we propose a learning model that reflects these properties of parts-based representation and topographic organization in a unified framework. This model is based on a nonnegative matrix factorization (NMF) basis decomposition method. NMF alone provides a parts-based representation where nonnegative inputs are approximated by additive combinations of nonnegative basis functions. Our proposed model of topographic NMF (TNMF) incorporates neighborhood connections between NMF basis functions arranged on a topographic map and attains the topographic property without losing the parts-based property of the NMF. The TNMF represents an input by multiple activity peaks to describe diverse information, whereas conventional topographic models, such as the self-organizing map (SOM), represent an input by a single activity peak in a topographic map. We demonstrate the parts-based and topographic properties of the TNMF by constructing a hierarchical model for object recognition where the TNMF is at the top tier for learning high-level object features. The TNMF showed better generalization performance over NMF for a data set of continuous view change of an image and more robustly preserving the continuity of the view change in its object representation. Comparison of the outputs of our model with actual neural responses recorded in the IT indicates that the TNMF reconstructs the neuronal responses better than the SOM, giving plausibility to the parts-based learning of the model.

scholarly journals On identifying kinematic and muscle synergies: a comparison of matrix factorization methods using experimental data from the healthy population

2017 ◽  
Vol 117 (1) ◽  
pp. 290-302 ◽  
Author(s):  
Navid Lambert-Shirzad ◽  
H. F. Machiel Van der Loos
Keyword(s):  
Principal Component Analysis ◽  
Matrix Factorization ◽  
Muscle Activation ◽  
Nonnegative Matrix Factorization ◽  
Nonnegative Matrix ◽  
Principal Component ◽  
Component Analysis ◽  
Data Sets ◽  
Motor Synergies ◽  
Factorization Methods

Human motor behavior is highly goal directed, requiring the central nervous system to coordinate different aspects of motion generation to achieve the motion goals. The concept of motor synergies provides an approach to quantify the covariation of joint motions and of muscle activations, i.e., elemental variables, during a task. To analyze goal-directed movements, factorization methods can be used to reduce the high dimensionality of these variables while accounting for much of the variance in large data sets. Three factorization methods considered in this paper are principal component analysis (PCA), nonnegative matrix factorization (NNMF), and independent component analysis (ICA). Bilateral human reaching data sets are used to compare the methods, and advantages of each are presented and discussed. PCA and NNMF had a comparable performance on both EMG and joint motion data and both outperformed ICA. However, NNMF's nonnegativity condition for activation of basis vectors is a useful attribute in identifying physiologically meaningful synergies, making it a more appealing method for future studies. A simulated data set is introduced to clarify the approaches and interpretation of the synergy structures returned by the three factorization methods.NEW & NOTEWORTHY Literature on comparing factorization methods in identifying motor synergies using numerically generated, simulation, and muscle activation data from animal studies already exists. We present an empirical evaluation of the performance of three of these methods on muscle activation and joint angles data from human reaching motion: principal component analysis, nonnegative matrix factorization, and independent component analysis. Using numerical simulation, we also studied the meaning and differences in the synergy structures returned by each method. The results can be used to unify approaches in identifying and interpreting motor synergies.

Sign in / Sign up

Export Citation Format

Share Document