Analyzing the Importance of Age-biased Data in Recognizing Emotions from Facial Expressions Using Custom Data Sets and CNN Algorithm | Chapter 3 | Recent Progress in Science and Technology Vol. 9

 This paper survey the importance of age-partial data in acknowledging emotions from facial verbalizations. A custom basic document file was created by separating existent data sets into women and kids. Three CNN architectures were tested, and the SE-ResNeXt50(32×4d) achieved the topmost accuracy at 79.42%. The age-located model outperformed the non-age-based model by 22.24%. The study highlights the impact adult-biased education data and algorithm types on concern recognition veracity, particularly for fear and neutral despairs.

Author(s) Details:

Hyungjoo Park,
Research Center for Advanced Convergence Technology, Korea Electronics-Machinery Convergence Technology Institute, Korea.

Youngha Shin,
Youngha Shin

Kyu Song,
Research Center for Advanced Convergence Technology, Korea Electronics-Machinery Convergence Technology Institute, Korea.

Channyeong Yun,
Research Center for Advanced Convergence Technology, Korea Electronics-Machinery Convergence Technology Institute, Korea.

Dongyoung Jang,
Korea Electronics-Machinery Convergence Technology Institute, Seoul National University of Science and Technology, Korea.

Please see the link here: https://stm.bookpi.org/RPST-V9/article/view/10264