Realizing Book Retrieval Using Image Matching Based on HWT-IQA and DSP-SIFT
Authors: 
Baolin Song, Chengwei Huang, Ke Li, Li ZhaoAuthors Info & Claims
Baolin Song, Chengwei Huang, Ke Li, Li ZhaoAuthors Info & ClaimsPages 164 - 168
Abstract
In order to reduce the interference perspective changes and nonlinear deformation caused by camera shooting, we proposed an approach based on HWT-IQA and DSP-SIFT to realize image matching in book retrieval. Extensive experiments are conducted with different IQA algorithms and DSP-SIFT features in image matching for book retrieval. Experimental results demonstrated the effectiveness of our proposed approach. Adding HWT-IQA algorithm before using DSP-SIFT in image matching, the accuracy rate of image matching for book retrieval is improved greatly.
References
[1]
Schnabel, Julia A., et al. "Advances and challenges in deformable image registration: From image fusion to complex motion modelling." (2016): 145--148.
[2]
Konidaris T, Märgner V, Mohammed H A et al. Efficient Keypoint Reduction for Document Image Matching[J]. 2019.
[3]
Dorling J, Abbott J, Berrington J, et al. Study Protocol The SIFT Study. Speed of Increasing Milk Feeds: A randomised controlled trial[J]. 2017.
[4]
Li Y, Li Q Liu Y, et al. A spatial-spectral SIFT for hyperspectral image matching and classification[J]. Pattern Recognition Letters, 2019, 127: 18--26.
[5]
Faraj A Danijela R D, Axel G.VF-SIFT: Very fast SIFT feature matching. Proc of the 32nd DAGM Symposium. Darmstadt, Germany, 2010: 222--231.
[6]
Garcia Vincent, Debreuve Eric, Nielsen Frank, Barlaud Michel. K-nearest neighbor search: Fast GPU-based implementations and application to high-dimensional feature matching. 2010 17th IEEE International Conference on Image Processing. Hong Kong China, 2010: 3757--3760.
[7]
Warn Seth, Apon Amy, Cothren Jackson Accelerating SIFT on Hybrid Clusters. Proceedings of the ACM SIGSPATIAL 2nd International Workshop on High Performance and Distributed Geographic Information Systems 2011, Chicago, IL, United states 2011: 2--9.
[8]
Fan Z, Liu Z, Qu Z, et al. ASP-SIFT: Using Analog Signal Processing Architecture to Accelerate Keypoint Detection of SIFT Algorithm[J]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 2019.
[9]
Jingming Dong, Stefano Soatto. Domain-Size Pooling in Local Descriptors: DSP-SIFT. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 5097--5106.
[10]
Y.Y. Tang, L. Yang and J. Liu, "Characterization of Dirac-Structure Edges with Wavelet Transform," IEEE Trans. Systems, Man and Cybernetics, Part B, February 2000, pp. 93--109.
[11]
H. Tong M. Li, H Zhang J. He, and C Zhang. Blur detection for digital images using wavelet transform. In Proceedings of International Conference on Multimedia and Expo, 2004.
[12]
Dong J, Soatto S. Domain-size pooling in local descriptors: DSP-SIFT[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: 5097--5106.
[13]
M. Muja and D Lowe. Scalable Nearest Neighbor Algorithms for High Dimensional Data. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36, 2014
[14]
A. Mttal, A. K Moorthy, and A. C. Bovik, "No-Reference Image Quality Assessment in the Spatial Domain," submitted to TIP 2012.
[15]
L. Zhang L. Zhang AC. Bovik, A feature-enriched completely blind image quality evaluator, IEEE Trans. Image Process. 24 (August (8)) (2015)2579-2591.
[16]
A. Mittal, R Soundararajan, and A. C. Bovik, "Making a completely blind image quality analyzer," IEEE Signal Processing Letters, vol. 20, no. 3, pp. 209--212, 2013.
Recommendations
Research on SIFT Image Matching Based on MLESAC Algorithm
ICDSP '18: Proceedings of the 2nd International Conference on Digital Signal ProcessingThe difference of sensor devices and the camera position offset will lead the geometric differences of the matching images. The traditional SIFT image matching algorithm has a large number of incorrect matching point pairs and the matching accuracy is ...
The Method of Image Matching by Taking Every Fixed Match Pixel
ISCID '12: Proceedings of the 2012 Fifth International Symposium on Computational Intelligence and Design - Volume 02A method of image matching by taking every fixed match pixel was proposed, then the images could be matched accurately in case of noise. the method was based on gray feature-based template matching, it took a long time for basic template matching to ...
Blurred Template Matching Based on Cascaded Network
Image and GraphicsAbstractTemplate matching is widely used in computer vision applications, but most matching methods simply assume the ideal images without real-word degradations, such as Gaussian blur. Traditional methods for blurred template matching either first resort ...
Comments
Information & Contributors
Information
Published In
April 2020
234 pages
ISBN:9781450377713
DOI:10.1145/3398329
Copyright © 2020 ACM.
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
- University of Salamanca: University of Salamanca
- The University of Adelaide, Australia
- Edinburgh Napier University, UK: Edinburgh Napier University, UK
- University of Sydney Australia
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 31 May 2020
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CNIOT2020
CNIOT2020: 2020 International Conference on Computing, Networks and Internet of Things
April 24 - 26, 2020
Sanya, China
Acceptance Rates
CNIOT '20 Paper Acceptance Rate 39 of 82 submissions, 48%;
Overall Acceptance Rate 39 of 82 submissions, 48%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 44Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Sep 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in