Convolutional Neural Networks

作者

Fiza Akram¹ , Rabia Riaz² , Kiran Iqbal² , Umm_e_Farwa Muhammad Anwar²

1. Riphah International University
2. Riphah International university Lahore.

会议/活动

2nd Workshop On Advancement Of Mathematics And Its Applications(WAMA-24), June 2024 (Lahore, Pakistan)

海报摘要

Convolutional Neural Networks (CNNs) are a class of deep learning algorithms primarily used for image recognition and classification. They mimic the human brain's visual processing by using layers that automatically and adaptively learn spatial hierarchies of features from input images. A typical CNN architecture includes convolutional layers, pooling layers, and fully connected layers. The convolutional layers apply filters to the input image, capturing features such as edges and textures. Pooling layers reduce the dimensionality, making the computation more efficient while preserving important information. Finally, the fully connected layers classify the images based on the learned features. CNNs are widely used in various applications, including facial recognition, medical image analysis, and self-driving cars. Their ability to learn and improve from large datasets has made them a powerful tool in the field of computer vision.

关键词

Convolutional Neural Networks, Facial Emotion Recognation, Deep Learning, Image Processing, Computer Vision, Facial Expressions

研究领域

Mathematics, Statistics, Computer and Information Science

参考文献

1. Albert Mehrabian. Silent Message univeristy of Calofornia Los Angeles,1971.
2. P. Ekman and W.V.Friesen University of Calofornia at San Francisco, 1983.

基金

暂无数据

补充材料

暂无数据

附加信息

利益冲突

No competing interests were disclosed.

数据可用性声明

The datasets generated during and / or analyzed during the current study are available from the corresponding author on reasonable request.

知识共享许可协议

Copyright © 2024 Akram et al. This is an open access work distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.