Deep Learning Similarity-based 1:1 Matching Method for Real Product Image and Drawing Image (딥러닝 유사도 기반 현품 영상과 도면 영상의 1:1 매칭 방법)

Gi-Tae Han (한기태)

doi:10.9708/jksci.2022.27.12.059

Deep Learning Similarity-based 1:1 Matching Method for Real Product Image and Drawing Image

Journal of The Korea Society of Computer and Information
Abbr : JKSCI
2022, 27(12), pp.59-68
DOI : 10.9708/jksci.2022.27.12.059
Publisher : The Korean Society Of Computer And Information
Research Area : Engineering > Computer Science
Received : November 21, 2022
Accepted : December 12, 2022
Published : December 30, 2022

Gi-Tae Han ¹

¹가천대학교

Accredited

ABSTRACT

This paper presents a method for 1:1 verification by comparing the similarity between the given real product image and the drawing image. The proposed method combines two existing CNN-based deep learning models to construct a Siamese Network. After extracting the feature vector of the image through the FC (Fully Connected) Layer of each network and comparing the similarity, if the real product image and the drawing image (front view, left and right side view, top view, etc) are the same product, the similarity is set to 1 for learning and, if it is a different product, the similarity is set to 0. The test (inference) model is a deep learning model that queries the real product image and the drawing image in pairs to determine whether the pair is the same product or not. In the proposed model, through a comparison of the similarity between the real product image and the drawing image, if the similarity is greater than or equal to a threshold value (Threshold: 0.5), it is determined that the product is the same, and if it is less than or equal to, it is determined that the product is a different product. The proposed model showed an accuracy of about 71.8% for a query to a product (positive: positive) with the same drawing as the real product, and an accuracy of about 83.1% for a query to a different product (positive: negative). In the future, we plan to conduct a study to improve the matching accuracy between the real product image and the drawing image by combining the parameter optimization study with the proposed model and adding processes such as data purification.

KEYWORDS

Deep Learning, CNN(Convolutional Neural Network), Drawing Image, Real Product Image, Siamese Network, 1:1 Verification

Citation status

* References for papers published after 2023 are currently being built.

[confproc] Karen Simonyan / 2015 / Very Deep Convolutional Networks for large-scale image recognition'(VGGNet) / Computer Vision and Pattern Recognition

[report] Kaiming He / 2015 / Deep Residual Learning for Image Recognition / Computer Vision and Pattern Recognition : 770~778

[confproc] Gao Huang / 2017 / Densely Connected Convolutional Networks / Computer Vision and Pattern Recognition

[confproc] Mingxing Tan / 2019 / EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks / ICML 2019

[confproc] Zhuang Liu / 2022 / A ConvNet for the 2020s / CVPR 2022

[confproc] Andrew G. Howard / 2017 / MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications / CVPR 2017

[confproc] Gregory Koch / 2015 / Ruslan Salakhutdinov, ”Siamese Neural Networks for One-shot Image Recognition / Proceedings of the 32nd International Conference on Machine Learning 37

[journal] Seong-Hoon Kim / 2020 / Hyperparameter optimization method based on harmony search algorithm to improve performance of 1D CNN human respiration pattern recognition system / Sensors 20 : 3697~

[confproc] Weijian Deng / 2018 / Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification / CVPR 2018

[journal] Grigori Sidorov / 2014 / Soft Similarity and Soft Cosine Measure:Similarity of Features in Vector Space Model / Computacionary Sistemas 18(3) : 491~504

[confproc] Raia Hadsell / 2006 / Dimensionality Reduction by Learning an Invariant Mapping / 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)

[confproc] Florian Schroff / 2015 / FaceNet:A Unified Embedding for Face Recognition and Clustering / Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

[confproc] Conghui Hu / 2022 / Feature Representation Learning for Unsupervised Cross-domain Image Retrieval / ECCV 2022

[journal] Qingjie Meng / 2020 / Unsupervised Cross-domain Image Classification by Distance Metric Guided Feature Alignment / Machine Learning

[journal] Xiaoping Zhou / 2022 / Cross-domain image retrieval: methods and applications / International Journal of Multimedia Information Retrieval 11 : 199~218

This paper was written with support from the National Research Foundation of Korea.

KJCKorea
Journal Central

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep Learning Similarity-based 1:1 Matching Method for Real Product Image and Drawing Image

ABSTRACT

KEYWORDS

Citation status

* References for papers published after 2023 are currently being built.

Journal of The Korea Society of Computer and Information 2023 KCI Impact Factor : 0.65

Deep Learning Similarity-based 1:1 Matching Method for Real Product Image and Drawing Image

ABSTRACT

KEYWORDS

Statistics

Tools

Issue List

Citation status

KCI Citation Counts (0)

REFERENCES (15) * References for papers published after 2023 are currently being built.

Search PDF

Citation

* References for papers published after 2023 are currently being built.