Year-end Sale % OFF 
Abstract
Automatic logo based document image retrieval process is an essential and mostly used method in the feature extraction applications. In this paper the architecture of Convolutional Neural Network (CNN) was elaborately explained with pictorial representations in order to understand the complex Convolutional Neural Networks process in a simplified way. The main objective of this paper is to effectively utilize the CNN in the process of automatic logo based document image retrieval methods.
Highlights
IntroductionThe feature extraction is playing a vital role in the automatic logo based document image retrieval methods (Logo is a primary key feature for the image or picture or document identity) in the various primary and essential society needs like Semantic Segmentation, Image Patches, Hand Written Characters recognition, Automatic Scene Text Recognition, Sentiment Analysis of Short Texts, Generic Visual Recognition, Speech Recognition, Image Style Transfer, No-Reference Image Quality Assessment, Large Scale Video Classification, Face Detection, Person Re-Identification, Heterogeneous Multi-task Learning for Human Pose Estimation, Depth estimation from a Single Image, Learning Transferable Features, Online Detection and Classification of Dynamic Hand Gestures, Visual Tracking, Mid-Level Image Representations, Scene Labelling, Image Question Answering, Real-Time Single Image and Video Super-Resolution, Visual Document Analysis, Dropout, 3D Shape Recognition, Fine-grained Image Classification, Learning to Compare Image Patches and Computing the Stereo Matching Cost Closed Circuit Tele Vision (CCTV), Drones, Traffic Surveillance, and Video analysis
Even though the Convolutional Neural Network (CNN) was introduced in 1990s, due to its deep learning characteristics it is compatible to use in latest technologies of Object recognition, Computer Vision, Pattern Recognition, Image Classification, Deep Learning, Machine Learning, and Artificial Intelligence applications
The CNN is itself consists of a deep learning architecture which directly deals with the very fundamental particles called neurons
Summary
The feature extraction is playing a vital role in the automatic logo based document image retrieval methods (Logo is a primary key feature for the image or picture or document identity) in the various primary and essential society needs like Semantic Segmentation, Image Patches, Hand Written Characters recognition, Automatic Scene Text Recognition, Sentiment Analysis of Short Texts, Generic Visual Recognition, Speech Recognition, Image Style Transfer, No-Reference Image Quality Assessment, Large Scale Video Classification, Face Detection, Person Re-Identification, Heterogeneous Multi-task Learning for Human Pose Estimation, Depth estimation from a Single Image, Learning Transferable Features, Online Detection and Classification of Dynamic Hand Gestures, Visual Tracking, Mid-Level Image Representations, Scene Labelling, Image Question Answering, Real-Time Single Image and Video Super-Resolution, Visual Document Analysis, Dropout, 3D Shape Recognition, Fine-grained Image Classification, Learning to Compare Image Patches and Computing the Stereo Matching Cost Closed Circuit Tele Vision (CCTV), Drones, Traffic Surveillance, and Video analysis. The Convolutional Neural Network (CNN) is one of such new powerful method useful for the feature extraction. The CNN is itself consists of a deep learning architecture which directly deals with the very fundamental particles called neurons. In this Paper we have explained the architecture of CNN in the process of automatic logo based document image retrieval.
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Engineering & Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
