Feature-Level vs. Score-Level Fusion in the Human Identification System

Abstract

The design of a robust human identification system is in high demand in most modern applications such as internet banking and security, where the multifeature biometric system, also called feature fusion biometric system, is one of the common solutions that increases the system reliability and improves recognition accuracy. This paper implements a comprehensive comparison between two fusion methods, named the feature-level fusion and score-level fusion, to determine which method highly improves the overall system performance. The comparison takes into consideration the image quality for the six combination datasets as well as the type of the applied feature extraction method. The four feature extraction methods, local binary pattern (LBP), gray-level co-occurrence matrix (GLCM), principle component analysis (PCA), and Fourier descriptors (FDs), are applied separately to generate the face-iris machine vector dataset. The experimental results highlighted that the recognition accuracy has been significantly improved when the texture descriptor method, such as LBP, or the statistical method, such as PCA, is utilized with the score-level rather than feature-level fusion for all combination datasets. The maximum recognition accuracy is obtained at 97.53% with LBP and score-level fusion where the Euclidean distance (ED) is considered to measure the maximum accuracy rate at the minimum equal error rate (EER) value.

Exploring Score-Level and Decision-Level Fusion of Inertial and Video Data for Intake Gesture Detection

“…Hence, using the same architecture to extract features (i.e., fusion at sensor-level) or process separately extracted features (i.e., fusion at featurelevel) in the context of fundamentally different data modalities (e.g., inertial and video data) may be more challenging than using the outputs of the individual models (i.e., fusion at scorelevel and decision-level). This may also explain why research in multimodal biometric identification systems found scorelevel fusion to be more promising than feature-level fusion [30]- [32]. However, further research needs to clarify whether score-level fusion of inertial and video data also outperforms sensor-level and feature-level fusion for intake gesture detection.…”

“…The matching scores (e.g., probability estimates) indicate the similarity between the input feature set and the ground truth. Comparison studies in multimodal biometric identification system [30]- [32] found score-level fusion to outperform feature-level fusion. Score-level fusion approaches can be broadly categorized into two groups [8].…”

Human recognition system through major and minor finger knuckle pattern fusion by symmetric-sum method

“…The first is PCA, which entails three steps: calculating eigenvalues, eigenvectors, and feature vector covariance matrices. These templates can be made smaller while still retaining the most critical features using an approach that combines feature extraction with dimension reduction 21 . To calculate PCA, the following formula is used: mean(A¯)=1n∑i=1nai,where ai is the pixel value in i and n is the total number of pixels in an image.…”

Enhanced kinship verification analysis based on color and texture handcrafted techniques

“…Then, the fusion process is performed using the concatenation of different extracted feature pointsets as seen in Eq. 9 where the plus (+) symbol refers to that concatenation operation 54,55 .…”