An Efficient Deep Convolutional Neural Network Approach for Object Detection and Recognition Using a Multi-Scale Anchor Box in Real-Time
Deep learning is a relatively new branch of machine learning in which computers are taught to recognize patterns in massive volumes of data. It primarily describes learning at various levels of representation, which aids in understanding data that includes text, voice, and visuals. Convolutional neu...
Main Authors: | Vijayakumar Varadarajan, Dweepna Garg, Ketan Kotecha |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Future Internet |
Subjects: | |
Online Access: | https://www.mdpi.com/1999-5903/13/12/307 |
Similar Items
-
An Efficient Multi-Scale Anchor Box Approach to Detect Partial Faces from a Video Sequence
by: Dweepna Garg, et al.
Published: (2022-01-01) -
Dataset: Variable Message Signal Annotated Images for Object Detection
by: Enrique Puertas, et al.
Published: (2022-04-01) -
Deep learning for object recognition: A comprehensive review of models and algorithms
by: Paschalis Tsirtsakis, et al.
Published: (2025-12-01) -
BengaliNet: A Low-Cost Novel Convolutional Neural Network for Bengali Handwritten Characters Recognition
by: Abu Sayeed, et al.
Published: (2021-07-01) -
Image-based facial emotion recognition using convolutional neural network on emognition dataset
by: Erlangga Satrio Agung, et al.
Published: (2024-06-01)