Measuring the contribution of filter bank layer to performance of convolutional neural networks
Object identification is essential in diverse automated applications such as in health, business, and national security. It relies on the ability of the image processing scheme to detect visual features under a wide variety of conditions such as the object rotation, translation and geometric transfo...
Saved in:
Main Authors: | , |
---|---|
Format: | text |
Published: |
Animo Repository
2017
|
Subjects: | |
Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/3011 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | De La Salle University |
id |
oai:animorepository.dlsu.edu.ph:faculty_research-4010 |
---|---|
record_format |
eprints |
spelling |
oai:animorepository.dlsu.edu.ph:faculty_research-40102022-04-21T00:23:29Z Measuring the contribution of filter bank layer to performance of convolutional neural networks Cordel, Macario O., II Azcarraga, Arnulfo P. Object identification is essential in diverse automated applications such as in health, business, and national security. It relies on the ability of the image processing scheme to detect visual features under a wide variety of conditions such as the object rotation, translation and geometric transformation. Machine learning methods, in this case, play an important role in improving the object identification performance by resolving whether the extracted visual patterns are from the possibly distorted target object or not. In recent works, systems that employ a Convolutional Neural Network (CNN) as the primary pattern recognition scheme demonstrate superior performance over other object identification systems based on handpicked shape-based features. Several studies credit this to the invariance of CNN to small distortion and spatial translation which in turn is attributed to its filter bank layer or the convolution layer. However, there has been no study to carefully test this claim. Towards studying the source of CNN's superior performance, a methodology is designed that tracks the CNN performance when spatial information for visual features (e.g. edges, corners and end points) are gradually removed. Using the MNIST dataset, results show that as the spatial correlation information among pixels is slowly decreased, the performance of the CNN in recognizing handwritten digits also correspondingly decreases. The drop in accuracy continues until the accuracy approximates the performance of the classifier that was obtained without the filter bank. Conducted using a more complex dataset consisting of images of land vehicles, a similar set of experiments show the same drop in classification performance as spatial information among pixels is slowly removed. © 2017 - IOS Press and the authors. All rights reserved. 2017-01-01T08:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/3011 Faculty Research Work Animo Repository Neural networks (Computer science) Pattern recognition systems Spatial analysis (Statistics) Electric filters, Bandpass Computer Sciences |
institution |
De La Salle University |
building |
De La Salle University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
De La Salle University Library |
collection |
DLSU Institutional Repository |
topic |
Neural networks (Computer science) Pattern recognition systems Spatial analysis (Statistics) Electric filters, Bandpass Computer Sciences |
spellingShingle |
Neural networks (Computer science) Pattern recognition systems Spatial analysis (Statistics) Electric filters, Bandpass Computer Sciences Cordel, Macario O., II Azcarraga, Arnulfo P. Measuring the contribution of filter bank layer to performance of convolutional neural networks |
description |
Object identification is essential in diverse automated applications such as in health, business, and national security. It relies on the ability of the image processing scheme to detect visual features under a wide variety of conditions such as the object rotation, translation and geometric transformation. Machine learning methods, in this case, play an important role in improving the object identification performance by resolving whether the extracted visual patterns are from the possibly distorted target object or not. In recent works, systems that employ a Convolutional Neural Network (CNN) as the primary pattern recognition scheme demonstrate superior performance over other object identification systems based on handpicked shape-based features. Several studies credit this to the invariance of CNN to small distortion and spatial translation which in turn is attributed to its filter bank layer or the convolution layer. However, there has been no study to carefully test this claim. Towards studying the source of CNN's superior performance, a methodology is designed that tracks the CNN performance when spatial information for visual features (e.g. edges, corners and end points) are gradually removed. Using the MNIST dataset, results show that as the spatial correlation information among pixels is slowly decreased, the performance of the CNN in recognizing handwritten digits also correspondingly decreases. The drop in accuracy continues until the accuracy approximates the performance of the classifier that was obtained without the filter bank. Conducted using a more complex dataset consisting of images of land vehicles, a similar set of experiments show the same drop in classification performance as spatial information among pixels is slowly removed. © 2017 - IOS Press and the authors. All rights reserved. |
format |
text |
author |
Cordel, Macario O., II Azcarraga, Arnulfo P. |
author_facet |
Cordel, Macario O., II Azcarraga, Arnulfo P. |
author_sort |
Cordel, Macario O., II |
title |
Measuring the contribution of filter bank layer to performance of convolutional neural networks |
title_short |
Measuring the contribution of filter bank layer to performance of convolutional neural networks |
title_full |
Measuring the contribution of filter bank layer to performance of convolutional neural networks |
title_fullStr |
Measuring the contribution of filter bank layer to performance of convolutional neural networks |
title_full_unstemmed |
Measuring the contribution of filter bank layer to performance of convolutional neural networks |
title_sort |
measuring the contribution of filter bank layer to performance of convolutional neural networks |
publisher |
Animo Repository |
publishDate |
2017 |
url |
https://animorepository.dlsu.edu.ph/faculty_research/3011 |
_version_ |
1731309235236503552 |