Criminal Scene Investigation Image Retrieval Based on Multi-bag Multi-instance Learning Algorithm
Authors: 
Daxiang Li, Xiaotong Zeng, Ying LiuAuthors Info & Claims
Pages 615 - 622
Abstract
Focus on the weak supervised learning problem in the criminal scene investigation (CSI) image retrieval, based on the random forest (RF) ensemble strategy, a novel multi-bag multi-instance learning (MB-MIL) algorithm is proposed. Firstly, by using Pyramid overlapping grid partitioning (POGP), a multi-bag multi-instance modeling scheme is designed to convert each CSI image into four different types multi-instance bags, so the CSI image retrieval problem was transformed into a MIL problem. Secondly, some discriminative instances are selected from the positive training bags by a defined criterion function to construct a discriminative instance set (DIS), and then based on the sparse coding and maximum pooling techniques, a discriminative coding feature (DCF) calculation method is proposed to convert every bag to a single sample, which allows the MIL problem to be solved directly by the RF algorithm. Finally, four RF classifiers are trained based on the four different DCFs, and they are integrated by a weighted fusion strategy to obtain the final MB-MIL classifier. Experimental results based on the CIIP-CSID-6000 and COREL1000 image sets show that the average AUC values of the MB-MIL algorithm are 7.6% and 6.0% higher than that of single-bag MIL algorithm, and its performance is superior to other MIL algorithms.
References
[1]
Schiliro, F., A. Beheshti, and N. Moustafa . "A Novel Cognitive Computing Technique Using Convolutional Networks for Automating the Criminal Investigation Process in Policing." Proceedings of SAI Intelligent Systems Conference Springer, Cham, 2020.
[2]
Horsman, G., B. Findlay, and T. James . "Developing a 'router examination at scene' standard operating procedure for crime scene investigators in the United Kingdom." Digital Investigation 28(2019):152-162.
[3]
Y. Liu, D. Hu, J. Fan. "A Survey of Crime Scene Investigation Image Retrieval. " Acta electronica sinica, 2018, 46(3):761-768.
[4]
Q. Qi, Q. M. Huo, and J. Y. Wang, “Personalized Sketch-Based Image Retrieval by Convolutional Neural Network and Deep Transfer Learning,” IEEE Access, vol. 7, pp. 16537-16549, Jan. 2019.
[5]
D. X. Li, N. Li, J. Wang, and T. G. Zhu, “Pornographic images recognition based on spatial pyramid partition and multi-instance ensemble learning,” Knowledge-Based Systems, vol. 84, no. 8, pp. 214-223, Aug. 2015.
[6]
D Li, and X. Bai . "Criminal Investigation Image Retrieval Based on Deep Learning." 2020 International Conference on Computer Network, Electronic and Automation (ICCNEA) 2020.
[7]
F. James and F. Eibe, “A review of multi-instance learning assumptions,” The Knowledge Engineering Review, vol. 25, no. 1, Mar. 2010, pp. 1-25.
[8]
S. Andrews, T. Hofmann, and I. Tsochantaridis, “Multiple instance learning with generalized support vector machines,” in Proc. Proceedings of the 18th National Conference on Artificial Intelligence, Edmonton, Canada, 2002, pp. 943-944.
[9]
Z. H. Zhou, Y. Y. Sun, and Y. F. Li, “Multi-instance learning by treating instances as non-i.i.d. samples,” in Proc. ICML, Montreal, Canada, 2009, pp. 1249-1256.
[10]
Y. X. Chen, J. Li, and J. Z. Wang, “Image categorization by learning and reasoning with regions,” Journal of Machine Learning Research, vol. 5, no. 8, pp. 913-939. Aug. 2004.
[11]
Y. X. Chen, J. B. Bo, and J. Z. Wang, “MILES: Multiple-Instance Learning via Embedded Instance Selection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 12, pp. 1931-1947. Jan. 2006.
[12]
X. S. Wei, J. X. Wu, and Z. H. Zhou, “Scalable algorithms for multi-instance learning,” IEEE Transactions on Neural Networks and Learning Systems, vol. 28, no. 4, pp. 975-987, Apr. 2017. 09/TNNLS.2016.2519102.
[13]
T Vu, P Lai, R Raich, A Novel Attribute-Based Symmetric Multiple Instance Learning for His-topathological Image Analysis[J]. IEEE Transactions on Medical Imaging, 2020, 23*2:121-132.
[14]
D. X. Li, J. Wang, Y. Liu, and X. Q. Zhao, “Pyramid match kernel and classifier ensemble-based MIL algorithm for pornographic images filtering,” International Journal of Pattern Recognition and Artificial Intelligence, vol. 28, no. 1, pp. 18-28. Apr. 2014.
[15]
Z. M. Li, D. Jiang, Y. J. Liu, and H. Li, “Spatial Context and Locality-constraint Based Linear Feature Coding,” Journal of Computer Aided Design & Computer Graphics, vol. 29, no. 2, pp. 254-261, Feb. 2017.
[16]
Y. X. Zhang and B.Yuan, “Supervised Online Dictionary Learning for Image Separation Using OMP,” in Proc. ICIC, Lanzhou, China, 2016, pp. 557-568.
[17]
Y. Q. Zhang, G. Cao, X. S. Li, and B. S. Wang, “Cascaded Random Forest for Hyperspectral Image Classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 99, pp. 1-13, Mar. 2018.
[18]
J. S. Jun, G. Pedram, Y. Naoto, and A. Iwasaki, “Random Forest Ensembles and Extended Multiextinction Profiles for Hyperspectral Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 56, no. 1, pp. 202-2[], Aug. 2017. 9/TGRS.2017.2744662.
[19]
X, Liu, M. L. Song, D. C. Tao, and Z. C. Liu, “Random Forest Construction With Robust Semi-supervised Node Splitting,” IEEE Transactions on Image Processing, vol. 24, no. 1, pp. 471-483, Jan. 2015.
[20]
A. Shrivastava, V. M. Patel, and J. K. Pillai, “Generalized Dictionaries for Multiple Instance Learning,” International Journal of Computer Vision, vol. 114, no. 2-3, pp. 288-305, Sept. 2015.
[21]
Yanshan Xiao and Xiaozhou Yang and Bo Liu. "A new self-paced method for multiple instance boosting learning". Information Sciences 515(2020): 80-90.
[22]
Ren Lingyu "Grey-based multiple instance learning with multiple bag-representative". AI Communications 33.2(2020): 59-73.
Index Terms
- Criminal Scene Investigation Image Retrieval Based on Multi-bag Multi-instance Learning Algorithm
Recommendations
A Novel Bag Generator for Image Database Retrieval With Multi-Instance Learning Techniques
ICTAI '03: Proceedings of the 15th IEEE International Conference on Tools with Artificial IntelligenceIn multi-instance learning, the training examples are bags composed of instances without labels and the task is to predict the labels of unseen bags through analyzing the training bags with known labels. In content-based image retrieval (CBIR), the query ...
A multi-instance multi-label learning algorithm based on instance correlations
Existing multi-instance multi-label learning algorithms generally assume that instances in a bag are independent of each other, which is difficult to be guaranteed in practical applications. A novel multi-instance multi-label learning algorithm is ...
Graph-based multiple-instance learning for object-based image retrieval
MIR '08: Proceedings of the 1st ACM international conference on Multimedia information retrievalWe study in this paper the problem of using multiple-instance semi-supervised learning to solve object-based image retrieval problem, in which the user is only interested in a portion of the image, and the rest of the image is considered as irrelevant. ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
September 2022
1221 pages
ISBN:9781450396899
DOI:10.1145/3573942
Copyright © 2022 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]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 16 May 2023
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
AIPR 2022
AIPR 2022: 2022 5th International Conference on Artificial Intelligence and Pattern Recognition
September 23 - 25, 2022
Xiamen, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 24Total Downloads
- Downloads (Last 12 months)4
- Downloads (Last 6 weeks)0
Reflects downloads up to 31 Jan 2025
Other 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.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format