Image Recognition Using Scale Recurrent Neural Networks

03/25/2018
by   Dong-Qing Zhang, et al.
0

Convolutional Neural Network(CNN) has been widely used for image recognition with great success. However, there are a number of limitations of the current CNN based image recognition paradigm. First, the receptive field of CNN is generally fixed, which limits its recognition capacity when the input image is very large. Second, it lacks the computational scalability for dealing with images with different sizes. Third, it is quite different from human visual system for image recognition, which involves both feadforward and recurrent proprocessing. This paper proposes a different paradigm of image recognition, which can take advantages of variable scales of the input images, has more computational scalabilities, and is more similar to image recognition by human visual system. It is based on recurrent neural network (RNN) defined on image scale with an embeded base CNN, which is named Scale Recurrent Neural Network(SRNN). This RNN based approach makes it easier to deal with images with variable sizes, and allows us to borrow existing RNN techniques, such as LSTM and GRU, to further enhance the recognition accuracy. Our experiments show that the recognition accuracy of a base CNN can be significantly boosted using the proposed SRNN models. It also significantly outperforms the scale ensemble method, which integrate the results of performing CNN to the input image at different scales, although the computational overhead of using SRNN is negligible.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/09/2019

Image Recognition of Tea Leaf Diseases Based on Convolutional Neural Network

In order to identify and prevent tea leaf diseases effectively, convolut...
research
09/01/2018

Evaluation of Neural Networks for Image Recognition Applications: Designing a 0-1 MILP Model of a CNN to create adversarials

Image Recognition is a central task in computer vision with applications...
research
05/03/2023

Iranian License Plate Recognition Using a Reliable Deep Learning Approach

The issue of Automatic License Plate Recognition (ALPR) has been one of ...
research
06/10/2018

Smart Novel Computer-based Analytical Tool for Image Forgery Authentication

This paper presents an integration of image forgery detection with image...
research
06/28/2021

Deep Learning Image Recognition for Non-images

Powerful deep learning algorithms open an opportunity for solving non-im...
research
11/16/2018

Assessing four Neural Networks on Handwritten Digit Recognition Dataset (MNIST)

Although the image recognition has been a research topic for many years,...
research
08/27/2023

Image Coding for Machines with Object Region Learning

Compression technology is essential for efficient image transmission and...

Please sign up or login with your details

Forgot password? Click here to reset