Classification of X-Ray images of shipping containers

Abdolshah, Majid; Teimouri, Mehdi; Rahmani, Rohallah

doi:10.1016/j.eswa.2017.01.030

Cited by 19 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For many years, researchers have explored the machine learning techniques to tackle the HS Code prediction task. Abdolshah et al [3] presented a system classifying the shipping containers X-Ray images in order to investigate whether the imports have been correctly declared. Other work depends on the multimodal deep learning approach where both image and textual information have been taken into consideration.…”

Section: Related Workmentioning

confidence: 99%

The use of machine learning to identify the correctness of HS Code for the customs import declarations

Chen¹,

Rijnsoever

Molenhuis

et al. 2021

2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

As an increasing volume of international trade activities around the world, the amount of cross-boarder import declarations grows rapidly, resulting in an unprecedented scale of potentially fraudulent transactions, in particular false commodity code (e.g., HS Code). The incorrect HS Code will cause duty risk and adversely impact the revenue collection. Physical investigation by the customs administrations is impractical due to the substantial quantity of declarations. This paper provides an automatic approach by harnessing the power of machine learning techniques to relief the burden of customs targeting officers. We introduced a novel model based on the off-theshelf embedding encoder to identify the correctness of HS Code without any human effort. Determining whether the HS Code is correctly matched with commodity description is a classification task, so the labelled data is typically required. However, the lack of gold standard labelled data sets in customs domain limits the development of supervised-based approach. Our model is developed by the unsupervised mechanism and trained on the unlabelled historical declaration records, which is robust and able to be smoothly adapted by the different customs administrations. Rather than typically classifying whether the HS Code is correct or not, our model predicts the score to indicate the degree of the HS Code being correct. We have evaluated our proposed model on the ground-truth data set provided by Dutch customs officers. Results show promising performance of 71% overall accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

The use of machine learning to identify the correctness of HS Code for the customs import declarations

Chen¹,

Rijnsoever

Molenhuis

et al. 2021

2021 IEEE 8th International Conference on Data Science and Advanced Analytics (DSAA)

View full text Add to dashboard Cite

show abstract

“…Rovetta [20] analyzed the difficult relationship between General Agreement on Trade in Services and the HS and interpreted the reason behind the migration of customs classification disputes from the WCO to the World Trade Organization. Abdolshah et al [21] proposed a new classification method for X-Ray images of shipping containers to help borders and customs inspect illegal act. However, few scholars have given attention to the accuracy and efficiency of customs classification.…”

Section: Literature Reviewmentioning

confidence: 99%

Customs classification for cross-border e-commerce based on text-image adaptive convolutional neural network

2019

Electron Commer Res

View full text Add to dashboard Cite

Customs classification is an essential international procedure to import cross-border goods traded by various companies and individuals. Proper classification of such goods with high efficiency in light of the rapidly increasing amount of international trade is still challenging. The current abundant e-commence data and advanced machine learning techniques provide an opportunity for cross-border e-commerce sellers to classify goods efficiently. Thus, in this paper, we propose a text-image adaptive convolutional neural network to effectively utilize website information and facilitate the customs classification process. The proposed model includes two independent submodels: one for text and the other for image. The submodels are fused by a novel method, which can adjust the value of parameters according to the model training result. Finally, we conduct a case study and comparison experiments based on a group of customs tariff codes and a data set from an e-commerce website. Experiment results indicate the effectiveness of text and image combination in performance improvement, the outperformance of the adaptive fusion method, as well as the potential of this approach when applied to customs classification.

show abstract

“…For image classification through texture descriptors, the literature presents the improvement of local binary patterns in texture analysis ( Kwak, Xu, & Wood, 2015 ). In are evaluated feature from images using descriptors ( Oliva, Lee, Spolaôr, Coy, & Wu, 2016 ), proposes a method based on the use of scale invariant features transform ( Abdolshah, Teimouri, & Rahmani, 2017 ) for classifications containers x-ray images. In the table is presented the main contributions in this area.…”

Section: Related Workmentioning

confidence: 99%

“…The outputs are: KNN Neubauer (1998) handwritten and face neocog-KNN, MLP Makantasis, Protopapadakis, Doulamis, Doulamis, and Loupos (2015) visual tunnel inspection CNN-SVM,KNN, DT Norlander, Grahn, and Maki (2015) wooden knot detection CNN Park, Kwon, Park, and Kang (2016) material inspection CNN Oliva, Lee, Spolaôr, Coy, and Wu (2016) medical images Haralick Chong, Han, and Park (2017) market analysis Deep Learning Yousefi-Azar and Hamey (2017) email messages CNN Kwak, Xu, and Wood (2015) high dimensional space LBP Gibert, Patel, and Chellappa (2017) Railway Inspection LBP and Gabor Ferreira and Giraldi (2017) Granite Classification GLCM, HOG and LBP Abdolshah, Teimouri, and Rahmani (2017) X-rays containers SIFT Considering the IDM Texture descriptor, for instance, it is possible to verify that image type-A forms a cluster. However, its descriptor is not enough to classify the images type B and C.…”

Section: Feature Extractionmentioning

confidence: 99%

Deep learning for biological image classification

Affonso

Rossi

Vieira

et al. 2017

Expert Systems with Applications

244

View full text Add to dashboard Cite

A number of industries use human inspection to visually classify the quality of their products and the raw materials used in the production process, this process could be done automatically through digital image processing. The industries are not always interested in the most accurate technique for a given problem, but most appropriate for the expected results, there must be a balance between accuracy and computational cost. This paper investigates the classification of the quality of wood boards based on their images. For such, it compares the use of deep learning, particularly Convolutional Neural Networks, with the combination of texture-based feature extraction techniques and traditional techniques: Decision tree induction algorithms, Neural Networks, Nearest neighbors and Support vector machines. Reported studies show that Deep Learning techniques applied to image processing tasks have achieved predictive performance superior to traditional classification techniques, mainly in high complex scenarios. One of the reasons pointed out is their embedded feature extraction mechanism. Deep Learning techniques directly identify and extract features, considered by them to be relevant, in a given image dataset. However, empirical results for the image data set have shown that the texture descriptor method proposed, regardless of the strategy employed is very competitive when compared with Convolutional Neural Network for all the performed experiments. The best performance of the texture descriptor method could be caused by the nature of the image dataset. Finally are pointed out some perspectives of futures developments with the application of Active learning and Semi supervised methods.

show abstract

Classification of X-Ray images of shipping containers

Cited by 19 publications

References 12 publications

The use of machine learning to identify the correctness of HS Code for the customs import declarations

The use of machine learning to identify the correctness of HS Code for the customs import declarations

Customs classification for cross-border e-commerce based on text-image adaptive convolutional neural network

Deep learning for biological image classification

Contact Info

Product

Resources

About