Feature fusion: parallel strategy vs. serial strategy

By Jian Yang, Jing-yu Yang, David Dapeng Zhang, Jianfeng Lu. Pattern Recognition, 2003

450 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Discriminant Correlation Analysis: Real-Time Feature Level Fusion for Multimodal Biometric Recognition (2016, methodology): “serial feature fusion [6] and parallel feature fusion [7], [8].”
A Survey of Decision Fusion and Feature Fusion Strategies for Pattern Classification (2010, methodology): “In other cases, the ratio of number of features in two feature sets can be used for weightage calculation [17].”
KPCA plus LDA: a complete kernel Fisher discriminant framework for feature extraction and recognition (2005, methodology): “Here, our experiment is performed based on 256-dimensional Gabor transformation features [43], [44], which turned out to be effective for handwritten digit classification.”
A new method of feature fusion and its application in image recognition (2005, methodology): “Another one is to combine two sets of feature vectors by a complex vector [5,6], and then to extract features in the complex vector space.”
Deep Feature Fusion for VHR Remote Sensing Scene Classification (2017, background): “2) Parallel strategy [36], [37] that combines the two features vector into a complex vector z = x + iy where i is the imaginary unit.”