Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113, which is very promising for the forensic field.

/pdf/assessment-and-estimation-of-face-detection-performance-285f09ty9x.pdf

Assessment and Estimation of Face Detection Performance Based on Deep Learning for Forensic Applications

https://www.jstage.jst.go.jp/article/jsprs1975/37/6/37_6_39/_pdf

1998 IEEE International Conference on SMCに参加して

Machine vision intelligence for product defect inspection based on deep learning and Hough transform

Learning visual relationship and context-aware attention for image captioning

A method for learning local affine-covariant regions is presented. We show that maximizing geometric repeatability does not lead to local regions, a.k.a features,that are reliably matched and this necessitates descriptor-based learning. We explore factors that influence such learning and registration: the loss function, descriptor type, geometric parametrization and the trade-off between matchability and geometric accuracy and propose a novel hard negative-constant loss function for learning of affine regions. The affine shape estimator -- AffNet -- trained with the hard negative-constant loss outperforms the state-of-the-art in bag-of-words image retrieval and wide baseline stereo. The proposed training process does not require precisely geometrically aligned patches.The source codes and trained weights are available at this https URL

Repeatability Is Not Enough: Learning Affine Regions via Discriminability

In this paper, we propose SummCoder, a novel methodology for generic extractive text summarization of single documents. The approach generates a summary according to three sentence selection metrics formulated by us: sentence content relevance, sentence novelty, and sentence position relevance. The sentence content relevance is measured using a deep auto-encoder network, and the novelty metric is derived by exploiting the similarity among sentences represented as embeddings in a distributed semantic space. The sentence position relevance metric is a hand-designed feature, which assigns more weight to the first few sentences through a dynamic weight calculation function regulated by the document length. Furthermore, a sentence ranking and a selection technique are developed to generate the document summary by ranking the sentences according to the final score obtained through the fusion of the three sentences selection metrics. We also introduce a new summarization benchmark, Tor Illegal Documents Summarization (TIDSumm) dataset, especially to assist Law Enforcement Agencies (LEAs), that contains two sets of ground truth summaries, manually created, for 100 web documents extracted from onion websites in Tor (The Onion Router) network. Empirical results show that, on DUC 2002, on Blog Summarization, and on TIDSumm datasets, our text summarization approach obtains comparable or better performance than the state-of-the-art methods for different ROUGE metrics.

SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders

This paper presents a reliable machine vision system to automatically detect inserts and determine if they are broken. Unlike the machining operations studied in the literature, we are dealing with edge milling head tools for aggressive machining of thick plates (up to 12 centimetres) in a single pass. The studied cutting head tool is characterised by its relatively high number of inserts (up to 30) which makes the localisation of inserts a key aspect. The identification of broken inserts is critical for a proper tool monitoring system. In the method that we propose, we first localise the screws of the inserts and then we determine the expected position and orientation of the cutting edge by applying some geometrical operations. We compute the deviations from the expected cutting edge to the real edge of the inserts to determine if an insert is broken. We evaluated the proposed method on a new dataset that we acquired and made public. The obtained result (a harmonic mean of precision and recall 91.43%) shows that the machine vision system that we present is effective and suitable for the identification of broken inserts in machining head tools and ready to be installed in an on-line system. HighlightsA novel machine-vision-based method that detects broken inserts in milling heads.Unlike other methods, this approach does not require comparison to reference images.We demonstrate its effectiveness on a new data set of 144 images with 180 inserts.It is very efficient and it can be used without delaying any machining operations.

Machine-vision-based identification of broken inserts in edge profile milling heads

The Tor network hosts a significant amount of hidden services related to suspicious activities. Law Enforcement Agencies need to monitor and to investigate crimes hidden behind the anonymity provided by Tor. In this paper, we propose a new algorithm, named ToRank, that ranks hidden services in Tor better than the known algorithms used for the Surface Web. We also thoroughly analyze the content present in Tor, creating a dataset, DUTA-10K, that extends the previous Darknet Usage Text Address (DUTA) dataset. We quantitatively compared ToRank with some of the most popular ranking algorithms, like PageRank, HITS, and Katz. Results showed that our proposal obtains a higher harm to the Tor network robustness than all of them, what indicates its superiority for this problem. The analysis of DUTA-10K reveals that only 20% of the hidden services that can be accessed are related to suspicious activities, and 48% are associated with normal ones. We also discovered that domains related to suspicious activities usually present multiple clones under different addresses, what could be used as an additional feature for identifying them. We consider that our new algorithm, the extended dataset, and the findings obtained from the analysis carried out are helpful for LEAs to fight against crimes that take place in the Tor hidden services.

ToRank: Identifying the most influential suspicious domains in the Tor network

Local oriented statistical information booster (LOSIB) is a descriptor enhancer based on the extraction of the gray level differences along several orientations. Specifically, the mean of the differences along particular orientations is considered. In this paper we have carried out some experiments using several classical texture descriptors to show that classification results are better when they are combined with LOSIB, than without it. Both parametric and non-parametric classifiers, Support Vector Machine and k-Nearest Neighbourhoods respectively, were applied to assess this new method. Furthermore, two different texture dataset were evaluated: KTH-Tips-2a and Brodatz32 to prove the robustness of LOSIB. Global descriptors such as WCF4 (Wavelet Co-occurrence Features), that extracts Haralick features from the Wavelet Transform, have been combined with LOSIB obtaining an improvement of 16.94% on KTH and 7.55% on Brodatz when classifying with SVM. Moreover, LOSIB was used together with state-of-the-art local descriptors such as LBP (Local Binary Pattern) and several of its recent variants. Combined with CLBP (Complete LBP), the LOSIB booster results were improved in 5.80% on KTH-Tips 2a and 7.09% on the Brodatz dataset. For all the tested descriptors, we have observed that a higher performance has been achieved, with the two classifiers on both datasets, when using some LOSIB settings.

Local Oriented Statistics Information Booster (LOSIB) for Texture Classification

Object detection is the key module in most visual-based surveillance applications and security systems. In crime scene analysis, the images and videos play a significant role in providing visual documentation of a scene. It allows police officers to recreate a scene for later analysis by detecting objects related to a specific crime. However, due to the presence of a large volume of data, the task of detecting objects of interest is very tedious for law enforcement agencies. In this work, we present a Faster R-CNN (Region-based Convolutional Neural Network) based real-time system, which automatically detects objects which might be found in an indoor environment. To test the effectiveness of the proposed system, we applied it to a subset of ImageNet containing 12 object classes and Karina dataset. We achieved an average accuracy of 74.33%, and the mean time taken to detect objects per image was 0.12 s in Nvidia-TitanX GPU.

Laura Fernández-Robles

Papers

SummCoder: An unsupervised framework for extractive text summarization based on deep auto-encoders

Machine-vision-based identification of broken inserts in edge profile milling heads

ToRank: Identifying the most influential suspicious domains in the Tor network

Local Oriented Statistics Information Booster (LOSIB) for Texture Classification

Object Detection for Crime Scene Evidence Analysis Using Deep Learning