research-article

Recognition of Object Hardness from Images Using a Capsule Network

Authors:

Shota Shindo,

Takaaki Goto,

Kensei TsuchidaAuthors Info & Claims

ACIT '19: Proceedings of the 7th ACIS International Conference on Applied Computing and Information Technology

Article No.: 3, Pages 1 - 5

https://doi.org/10.1145/3325291.3325358

Published: 29 May 2019 Publication History

Get Access

Abstract

Hardness is often used as an index to compare similar objects. To measure an object's hardness, a hardness meter is required and certain conditions must be met. The object and the hardness meter corresponding to that object have to be close at hand. This research proposes a method to measure hardness from the object's image. The method employs machine learning using the capsule network of a neural network model.

References

[1]

Geoffrey E. Hinton, Sara Sabour, Nicholas Frosst, "Dynamic Rouring Between Capsules", arXiv preprint arXiv:1710.09829, 2017.

Google Scholar

[2]

Youngjoo Kim, Peng Wang, Yifei Zhu, and Lyudmila Mihaylova, "A Capsule Network for Traffic Speed Prediction in Complex Road Networks", arXiv preprint arXiv:1807.10603v2, 2018.

Google Scholar

[3]

Spyros Gidaris, Nikos Komodakis, "Object detection via a multi-region and semantic segmentation-aware CNN model", ICCV, pp. 1134--1142, 2015.

Digital Library

Google Scholar

[4]

Shun Miao et al, "A CNN Regression Approach for Real-Time 2D/3D Registration", Proc. of IEEE Transactions on Medical Imaging, Vol.35, pp. 1352--1363, 2016.

Crossref

Google Scholar

[5]

Jun Yuan, Bingbing Ni, Ashraf A.Kassim, "Half-CNN: A General Framework for Whole-Image Regression", arXiv preprint arXiv:1412.6885, 2014.

Google Scholar

[6]

J. Li, J, Tan, P. Shatadal, "Classification of tough and tender beef by image texture analysis", Proc. of Meat Science, Vol.57, pp. 341--346, 2001.

Crossref

Google Scholar

[7]

Adel Mahamood Hassan, et al, "Prediction of density, porosity and hardness in aluminum--copper-based composite materials using artificial neural network", Proc. of Journal of Materials Processing Technology, Vol.209, pp. 894--899, 2009.

Crossref

Google Scholar

[8]

Blial M. Zahran, "Using Neural Networks to Predict the Hardness of Aluminum Alloys", Proc. of ETASR, Vol.5, pp. 757--759, 2015.

Google Scholar

[9]

Wataru Shimoda, Keiji Yanai, "Gathering and Analyzing Material Images on the Web with DCNN features", Proc. of IEICE technical report, Vol.114, pp. 67--72, 2015.

Google Scholar

[10]

Zhanpeng Zhang, et al, "Facial Landmark Detection by Deep Multi-task Learning", Proc. of ECCV, Part VI, pp. 94--108, 2014.

Google Scholar

[11]

Geoffrey E. Hinton, Sara Sabour, Nicholas Frosst, "Matrix capsules with EM routing", In ICLR, 2018.

Google Scholar

Recommendations

Hardness amplification proofs require majority
STOC '08: Proceedings of the fortieth annual ACM symposium on Theory of computing

Hardness amplification is the fundamental task of converting a δ-hard function f : (0, 1)ⁿ -> (0, 1) into a (1/2-ε)-hard function Amp(f), where f is γ-hard if small circuits fail to compute f on at least a γ fraction of the inputs. Typically, ε,δ are ...
Query Complexity in Errorless Hardness Amplification

An errorless circuit for a Boolean function is one that outputs the correct answer or "don't know" on each input (and never outputs the wrong answer). The goal of errorless hardness amplification is to show that if f has no size s errorless circuit that ...
On the hardness of learning intersections of two halfspaces

We show that unless NP=RP, it is hard to (even) weakly PAC-learn intersection of two halfspaces in R^n using a hypothesis which is a function of up to @? halfspaces (linear threshold functions) for any integer @?. Specifically, we show that for every ...

Comments

Information & Contributors

Information

Published In

ACIT '19: Proceedings of the 7th ACIS International Conference on Applied Computing and Information Technology

May 2019

248 pages

ISBN:9781450371735

DOI:10.1145/3325291

Conference Chair:
Kensei Tsuchida

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

In-Cooperation

SIGITE: ACM Special Interest Group on Information Technology Education

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 29 May 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

ACIT 2019

ACIT 2019: 7th ACIS International Conference on Applied Computing and Information Technology

May 29 - 31, 2019

HI, Honolulu, USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

0
Total Citations
76
Total Downloads

Downloads (Last 12 months)1
Downloads (Last 6 weeks)0

Reflects downloads up to 05 Mar 2025

Other Metrics

View Author Metrics

Citations

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Abstract

References

Recommendations

Hardness amplification proofs require majority

Query Complexity in Errorless Hardness Amplification

On the hardness of learning intersections of two halfspaces

Comments

Information

Published In

In-Cooperation

Publisher

Publication History

Permissions

Check for updates

Author Tags

Qualifiers

Conference

Contributors

Other Metrics

Bibliometrics

Article Metrics

Other Metrics

Citations

Login options

Full Access

View options

PDF

eReader

Share

Share this Publication link

Share on social media

Affiliations