Query Based Object Retrieval Using Neural Codes

et al. 2020

Self Cite

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.

Section: Introductionmentioning

confidence: 99%

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

Chaves

Fidalgo

et al. 2020

Self Cite

“…Thus, multiple objects can be detected and classified within an image with high performance. Image classification techniques allow for the identification of specific content [ 8 ], which can be further explored through object detection [ 9 , 10 , 11 ] and object recognition techniques [ 12 , 13 ].…”

Section: Introductionmentioning

confidence: 99%

Rectification and Super-Resolution Enhancements for Forensic Text Recognition

Blanco‐Medina

Fidalgo

et al. 2020

Self Cite

Retrieving text embedded within images is a challenging task in real-world settings. Multiple problems such as low-resolution and the orientation of the text can hinder the extraction of information. These problems are common in environments such as Tor Darknet and Child Sexual Abuse images, where text extraction is crucial in the prevention of illegal activities. In this work, we evaluate eight text recognizers and, to increase the performance of text transcription, we combine these recognizers with rectification networks and super-resolution algorithms. We test our approach on four state-of-the-art and two custom datasets (TOICO-1K and Child Sexual Abuse (CSA)-text, based on text retrieved from Tor Darknet and Child Sexual Exploitation Material, respectively). We obtained a 0.3170 score of correctly recognized words in the TOICO-1K dataset when we combined Deep Convolutional Neural Networks (CNN) and rectification-based recognizers. For the CSA-text dataset, applying resolution enhancements achieved a final score of 0.6960. The highest performance increase was achieved on the ICDAR 2015 dataset, with an improvement of 4.83% when combining the MORAN recognizer and the Residual Dense resolution approach. We conclude that rectification outperforms super-resolution when applied separately, while their combination achieves the best average improvements in the chosen datasets.

“…Most works related to CBIR aim at finding objects in datasets of images. Research groups face this problem using different approaches such as invariant local features (SIFT [ 11 , 12 ], SURF [ 13 ]), color description [ 14 , 15 ], template matching [ 16 , 17 ] or, more recently, deep learning techniques [ 18 , 19 , 20 ]. Nonetheless, these techniques may fail when the object does not present a rigid shape or it has a plain shape, as it is the case of textiles.…”

Section: Introductionmentioning

confidence: 99%

Textile Retrieval Based on Image Content from CDC and Webcam Cameras in Indoor Environments

García-Olalla

Fernández-Robles

et al. 2018

Self Cite

Textile based image retrieval for indoor environments can be used to retrieve images that contain the same textile, which may indicate that scenes are related. This makes up a useful approach for law enforcement agencies who want to find evidence based on matching between textiles. In this paper, we propose a novel pipeline that allows searching and retrieving textiles that appear in pictures of real scenes. Our approach is based on first obtaining regions containing textiles by using MSER on high pass filtered images of the RGB, HSV and Hue channels of the original photo. To describe the textile regions, we demonstrated that the combination of HOG and HCLOSIB is the best option for our proposal when using the correlation distance to match the query textile patch with the candidate regions. Furthermore, we introduce a new dataset, TextilTube, which comprises a total of 1913 textile regions labelled within 67 classes. We yielded 84.94% of success in the 40 nearest coincidences and 37.44% of precision taking into account just the first coincidence, which outperforms the current deep learning methods evaluated. Experimental results show that this pipeline can be used to set up an effective textile based image retrieval system in indoor environments.