DETECTION OF TEXT OBJECTS IN IMAGES OF REAL SCENES BASED ON CONVOLUTIONAL NEURAL NETWORK MODEL
A model of text image detector based on a convolutional neural network architecture is presented, capable of synthesizing high-level features of images in the «black box» mode. An implementation of the detector application, based on algorithms of multi-scale scanning and local responses interpretati...
Main Author: | N. N. Kuzmitsky |
---|---|
Format: | Article |
Language: | Russian |
Published: |
The United Institute of Informatics Problems of the National Academy of Sciences of Belarus
2016-09-01
|
Series: | Informatika |
Online Access: | https://inf.grid.by/jour/article/view/15 |
Similar Items
-
Convolutional neural model in a TASK of classification images of the isolated digits
by: N. N. Kuzmitsky
Published: (2019-06-01) -
Construction of universal russian characters classifiers BASED ON CONVOLUTIONAL NEURAL NETWORKs
by: N. N. Kuzmitsky
Published: (2019-06-01) -
Deep Convolutional Neural Network with Scene-centric and Object-centric Information for Object Detection
by: Zong-Ying Shen, et al.
Published: (2017) -
Fully Convolutional Networks for Text Understanding in Scene Images
by: Dena Bazazian
Published: (2020-02-01) -
Multi-scene road pothole image detection based on convolutional neural network
by: CHEN Peng, et al.
Published: (2020-02-01)