Pub Date : 2020-04-01DOI: 10.4018/ijdcf.2020040101
Jinsheng Xiao, Wenxin Xiong, Yuan Yao, Liang Li, R. Klette
Lane detection still demonstrates low accuracy and missing robustness when recorded markings are interrupted by strong light or shadows or missing marking. This article proposes a new algorithm using a model of road structure and an extended Kalman filter. The region of interest is set according to the vanishing point. First, an edge-detection operator is used to scan horizontal pixels and calculate edge-strength values. The corresponding straight line is detected by line parameters voted by edge points. From the edge points and lane mark candidates extracted above, and other constraints, these points are treated as the potential lane boundary. Finally, the lane parameters are estimated using the coordinates of the lane boundary points. They are updated by an extended Kalman filter to ensure the stability and robustness. Results indicate that the proposed algorithm is robust for challenging road scenes with low computational complexity.
{"title":"Lane Detection Algorithm Based on Road Structure and Extended Kalman Filter","authors":"Jinsheng Xiao, Wenxin Xiong, Yuan Yao, Liang Li, R. Klette","doi":"10.4018/ijdcf.2020040101","DOIUrl":"https://doi.org/10.4018/ijdcf.2020040101","url":null,"abstract":"Lane detection still demonstrates low accuracy and missing robustness when recorded markings are interrupted by strong light or shadows or missing marking. This article proposes a new algorithm using a model of road structure and an extended Kalman filter. The region of interest is set according to the vanishing point. First, an edge-detection operator is used to scan horizontal pixels and calculate edge-strength values. The corresponding straight line is detected by line parameters voted by edge points. From the edge points and lane mark candidates extracted above, and other constraints, these points are treated as the potential lane boundary. Finally, the lane parameters are estimated using the coordinates of the lane boundary points. They are updated by an extended Kalman filter to ensure the stability and robustness. Results indicate that the proposed algorithm is robust for challenging road scenes with low computational complexity.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"20 5 1","pages":"1-20"},"PeriodicalIF":0.7,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87678747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.4018/ijdcf.2020040102
Xinguo Yu, Wu Song, Xiaopan Lyu, Bin He, Nan Ye
This article presents an algorithm for reading both single and multiple digital video clocks by using a context-aware pixel periodicity method and a deep learning technique. Reading digital video clocks in real time is a very challenging problem. The first challenge is the clock digit localization. The existing pixel periodicity is not applicable to localizing multiple second-digit places. This article proposes a context-aware pixel periodicity method to identify the second-pixels of each clock. The second challenge is clock-digit recognition. For this task, the algorithms based a domain knowledge and deep learning technique is proposed to recognize clock digits. The proposed algorithm is better than the existing best one in two aspects. The first one is that it can read not only single digit video clock but also multiple digit video clocks. The other is that it requires a short length of a video clip. The experimental results show that the proposed algorithm can achieve 100% of accuracy in both localization and recognition for both single and multiple clocks.
{"title":"Reading Both Single and Multiple Digital Video Clocks Using Context-Aware Pixel Periodicity and Deep Learning","authors":"Xinguo Yu, Wu Song, Xiaopan Lyu, Bin He, Nan Ye","doi":"10.4018/ijdcf.2020040102","DOIUrl":"https://doi.org/10.4018/ijdcf.2020040102","url":null,"abstract":"This article presents an algorithm for reading both single and multiple digital video clocks by using a context-aware pixel periodicity method and a deep learning technique. Reading digital video clocks in real time is a very challenging problem. The first challenge is the clock digit localization. The existing pixel periodicity is not applicable to localizing multiple second-digit places. This article proposes a context-aware pixel periodicity method to identify the second-pixels of each clock. The second challenge is clock-digit recognition. For this task, the algorithms based a domain knowledge and deep learning technique is proposed to recognize clock digits. The proposed algorithm is better than the existing best one in two aspects. The first one is that it can read not only single digit video clock but also multiple digit video clocks. The other is that it requires a short length of a video clip. The experimental results show that the proposed algorithm can achieve 100% of accuracy in both localization and recognition for both single and multiple clocks.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"39 1","pages":"21-39"},"PeriodicalIF":0.7,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77395182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.4018/ijdcf.2020040103
Raouia Mokni, Hassen Drira, M. Kherallah
The security of people requires a beefy guarantee in our society, particularly, with the spread of terrorism throughout the world. In this context, palmprint identification based on texture analysis is amongst the pattern recognition applications to recognize people. In this article, the researchers investigated a deep texture analysis for the palmprint texture pattern representation based on a fusion between several texture information extractions through multiple descriptors, such as HOG and Gabor Filters, Fractal dimensions and GLCM corresponding respectively to the frequency, model, and statistical methodologies-based texture features. They assessed the proposed deep texture analysis method as well as the applicability of the dimensionality reduction techniques and the correlation concept between the features-based fusion on the challenging PolyU, CASIA and IIT-Delhi Palmprint databases. The experimental results show that the fusion of different texture types using the correlation concept for palmprint modality identification leads to promising results.
{"title":"Deep-Analysis of Palmprint Representation Based on Correlation Concept for Human Biometrics Identification","authors":"Raouia Mokni, Hassen Drira, M. Kherallah","doi":"10.4018/ijdcf.2020040103","DOIUrl":"https://doi.org/10.4018/ijdcf.2020040103","url":null,"abstract":"The security of people requires a beefy guarantee in our society, particularly, with the spread of terrorism throughout the world. In this context, palmprint identification based on texture analysis is amongst the pattern recognition applications to recognize people. In this article, the researchers investigated a deep texture analysis for the palmprint texture pattern representation based on a fusion between several texture information extractions through multiple descriptors, such as HOG and Gabor Filters, Fractal dimensions and GLCM corresponding respectively to the frequency, model, and statistical methodologies-based texture features. They assessed the proposed deep texture analysis method as well as the applicability of the dimensionality reduction techniques and the correlation concept between the features-based fusion on the challenging PolyU, CASIA and IIT-Delhi Palmprint databases. The experimental results show that the fusion of different texture types using the correlation concept for palmprint modality identification leads to promising results.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"20 1","pages":"40-58"},"PeriodicalIF":0.7,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81774881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-04-01DOI: 10.4018/ijdcf.2020040104
Wenjun Huang, Chao Liang, Chunxia Xiao, Zhen Han
Video-based person re-identification (re-id) has recently attracted widespread attentions because extra space-time information and more appearance cues in videos can be used to improve the performance of image-based person re-id. Most existing approaches equally treat person video images, ignoring their individual discrepancy. However, in real scenarios, captured images are usually contaminated by various noises, especially occlusions, resulting in a series of unregulated sequences. Through investigating the impact of unregulated sequences to feature representation of video-based person re-id, the authors find a remarkable promotion by eliminating noisy sub sequences. Based on this interesting finding, an adaptive unregulated sub sequence detection and refinement method is proposed to purify original video sequence and obtain a more effective and discriminative feature representation for video-based person re-id. Experimental results on two public datasets demonstrate that the proposed method outperforms the state-of-the-art work.
{"title":"Video-Based Person Re-Identification With Unregulated Sequences","authors":"Wenjun Huang, Chao Liang, Chunxia Xiao, Zhen Han","doi":"10.4018/ijdcf.2020040104","DOIUrl":"https://doi.org/10.4018/ijdcf.2020040104","url":null,"abstract":"Video-based person re-identification (re-id) has recently attracted widespread attentions because extra space-time information and more appearance cues in videos can be used to improve the performance of image-based person re-id. Most existing approaches equally treat person video images, ignoring their individual discrepancy. However, in real scenarios, captured images are usually contaminated by various noises, especially occlusions, resulting in a series of unregulated sequences. Through investigating the impact of unregulated sequences to feature representation of video-based person re-id, the authors find a remarkable promotion by eliminating noisy sub sequences. Based on this interesting finding, an adaptive unregulated sub sequence detection and refinement method is proposed to purify original video sequence and obtain a more effective and discriminative feature representation for video-based person re-id. Experimental results on two public datasets demonstrate that the proposed method outperforms the state-of-the-art work.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"19 1","pages":"59-76"},"PeriodicalIF":0.7,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79712231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.4018/ijdcf.2020010104
Ahmed Almutairi, Behzad Shoarian Satari, Carlos Rivas, Cristian Florin Stanciu, Mozhdeh Yamani, Zahra Zohoorsaadat, Serguei A. Mokhov
In this article, the authors successfully created two new plugins one for Autopsy Forensic Tool, and the other for Volatility Framework. Both plugins are useful for encoding digital evidences in Forensic Lucid which is the goal of this work. The first plugin was integrated in Autopsy to generate a report for the case of a Brute Force Authentication attack by looking for evidence in server logs based on a key search. On the other hand, the second plugin named ForensicLucidDeviceTree aims to find whether a device stack has been infected by a root-kit or not expression is implied by the previous statement. The results of both plugins are shown in Forensic Lucid Format and were successfully compiled using GIPC compiler.
{"title":"Evaluation of Autopsy and Volatility for Cybercrime Investigation: A Forensic Lucid Case Study","authors":"Ahmed Almutairi, Behzad Shoarian Satari, Carlos Rivas, Cristian Florin Stanciu, Mozhdeh Yamani, Zahra Zohoorsaadat, Serguei A. Mokhov","doi":"10.4018/ijdcf.2020010104","DOIUrl":"https://doi.org/10.4018/ijdcf.2020010104","url":null,"abstract":"In this article, the authors successfully created two new plugins one for Autopsy Forensic Tool, and the other for Volatility Framework. Both plugins are useful for encoding digital evidences in Forensic Lucid which is the goal of this work. The first plugin was integrated in Autopsy to generate a report for the case of a Brute Force Authentication attack by looking for evidence in server logs based on a key search. On the other hand, the second plugin named ForensicLucidDeviceTree aims to find whether a device stack has been infected by a root-kit or not expression is implied by the previous statement. The results of both plugins are shown in Forensic Lucid Format and were successfully compiled using GIPC compiler.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"49 1","pages":"58-89"},"PeriodicalIF":0.7,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77850746","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.4018/ijdcf.2020010108
Dan-E Huang, Fangjun Huang
Recently, a reversible data hiding (RDH) method was proposed based on local histogram shifting. This method selects the peak bin of the local histogram as a reference and expands the two neighboring bins of the peak bin to carry the message bits. Since the peak bin keeps unchanged during the embedding process, the neighboring bins can be easily identified at the receiver end, and the original image can be restored completely while extracting the embedded data. In this article, as an extension of the algorithm, the authors propose an RDH scheme based on adaptive block selection strategy. Via a new block selection strategy, those blocks of the carrier image may carry more message bits whereas introducing less distortion will take precedence over data hiding. Experimental results demonstrate that higher visual quality can be obtained compared with the original method, especially when the embedding rate is low.
{"title":"Reversible Data Hiding Based on Adaptive Block Selection Strategy","authors":"Dan-E Huang, Fangjun Huang","doi":"10.4018/ijdcf.2020010108","DOIUrl":"https://doi.org/10.4018/ijdcf.2020010108","url":null,"abstract":"Recently, a reversible data hiding (RDH) method was proposed based on local histogram shifting. This method selects the peak bin of the local histogram as a reference and expands the two neighboring bins of the peak bin to carry the message bits. Since the peak bin keeps unchanged during the embedding process, the neighboring bins can be easily identified at the receiver end, and the original image can be restored completely while extracting the embedded data. In this article, as an extension of the algorithm, the authors propose an RDH scheme based on adaptive block selection strategy. Via a new block selection strategy, those blocks of the carrier image may carry more message bits whereas introducing less distortion will take precedence over data hiding. Experimental results demonstrate that higher visual quality can be obtained compared with the original method, especially when the embedding rate is low.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"4 1","pages":"157-168"},"PeriodicalIF":0.7,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75248089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.4018/ijdcf.2020010105
Mahmoud Kalash, Mrigank Rochan, N. Mohammed, Neil D. B. Bruce, Yang Wang, Farkhund Iqbal
In this article, the authors propose a deep learning framework for malware classification. There has been a huge increase in the volume of malware in recent years which poses serious security threats to financial institutions, businesses, and individuals. In order to combat the proliferation of malware, new strategies are essential to quickly identify and classify malware samples. Nowadays, machine learning approaches are becoming popular for malware classification. However, most of these approaches are based on shallow learning algorithms (e.g. SVM). Recently, convolutional neural networks (CNNs), a deep learning approach, have shown superior performance compared to traditional learning algorithms, especially in tasks such as image classification. Inspired by this, the authors propose a CNN-based architecture to classify malware samples. They convert malware binaries to grayscale images and subsequently train a CNN for classification. Experiments on two challenging malware classification datasets, namely Malimg and Microsoft, demonstrate that their method outperforms competing state-of-the-art algorithms.
{"title":"A Deep Learning Framework for Malware Classification","authors":"Mahmoud Kalash, Mrigank Rochan, N. Mohammed, Neil D. B. Bruce, Yang Wang, Farkhund Iqbal","doi":"10.4018/ijdcf.2020010105","DOIUrl":"https://doi.org/10.4018/ijdcf.2020010105","url":null,"abstract":"In this article, the authors propose a deep learning framework for malware classification. There has been a huge increase in the volume of malware in recent years which poses serious security threats to financial institutions, businesses, and individuals. In order to combat the proliferation of malware, new strategies are essential to quickly identify and classify malware samples. Nowadays, machine learning approaches are becoming popular for malware classification. However, most of these approaches are based on shallow learning algorithms (e.g. SVM). Recently, convolutional neural networks (CNNs), a deep learning approach, have shown superior performance compared to traditional learning algorithms, especially in tasks such as image classification. Inspired by this, the authors propose a CNN-based architecture to classify malware samples. They convert malware binaries to grayscale images and subsequently train a CNN for classification. Experiments on two challenging malware classification datasets, namely Malimg and Microsoft, demonstrate that their method outperforms competing state-of-the-art algorithms.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"12 1","pages":"90-108"},"PeriodicalIF":0.7,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85219744","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-01DOI: 10.4018/ijdcf.2020010101
Áine MacDermott, T. Baker, Paul Buck, Farkhund Iqbal, Qi Shi
The Internet of Things (IoT) represents the seamless merging of the real and digital world, with new devices created that store and pass around data. Processing large quantities of IoT data will proportionately increase workloads of data centres, leaving providers with new security, capacity, and analytics challenges. Handling this data conveniently is a critical challenge, as the overall application performance is highly dependent on the properties of the data management service. This article explores the challenges posed by cybercrime investigations and digital forensics concerning the shifting landscape of crime – the IoT and the evident investigative complexity – moving to the Internet of Anything (IoA)/Internet of Everything (IoE) era. IoT forensics requires a multi-faceted approach where evidence may be collected from a variety of sources such as sensor devices, communication devices, fridges, cars and drones, to smart swarms and intelligent buildings.
{"title":"The Internet of Things: Challenges and Considerations for Cybercrime Investigations and Digital Forensics","authors":"Áine MacDermott, T. Baker, Paul Buck, Farkhund Iqbal, Qi Shi","doi":"10.4018/ijdcf.2020010101","DOIUrl":"https://doi.org/10.4018/ijdcf.2020010101","url":null,"abstract":"The Internet of Things (IoT) represents the seamless merging of the real and digital world, with new devices created that store and pass around data. Processing large quantities of IoT data will proportionately increase workloads of data centres, leaving providers with new security, capacity, and analytics challenges. Handling this data conveniently is a critical challenge, as the overall application performance is highly dependent on the properties of the data management service. This article explores the challenges posed by cybercrime investigations and digital forensics concerning the shifting landscape of crime – the IoT and the evident investigative complexity – moving to the Internet of Anything (IoA)/Internet of Everything (IoE) era. IoT forensics requires a multi-faceted approach where evidence may be collected from a variety of sources such as sensor devices, communication devices, fridges, cars and drones, to smart swarms and intelligent buildings.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"14 1","pages":"1-13"},"PeriodicalIF":0.7,"publicationDate":"2020-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82384290","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：