Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning

@article{Han2019TattooIS,
  title={Tattoo Image Search at Scale: Joint Detection and Compact Representation Learning},
  author={Hu Han and J. Li and Anil K. Jain and S. Shan and Xilin Chen},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2019},
  volume={41},
  pages={2333-2348}
}
  • Hu Han, J. Li, Xilin Chen
  • Published 1 November 2018
  • Computer Science
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
The explosive growth of digital images in video surveillance and social media has led to the significant need for efficient search of persons of interest in law enforcement and forensic applications. Despite tremendous progress in primary biometric traits (e.g., face and fingerprint) based person identification, a single biometric trait alone can not meet the desired recognition accuracy in forensic scenarios. Tattoos, as one of the important soft biometric traits, have been found to be… 
Deep Generic Features for Tattoo Identification
TLDR
This work asses several publicly available CNNs models, pre-trained on large generic image databases, for the task of tattoo identification, believing that, since tattoos mostly depict objects of the real world, their semantic and visual features might be related to those learned from a generic image database with real objects.
A Transfer Learning Approach for the Tattoo Detection Problem
TLDR
This work presents a deep learning model based on transfer learning for the identification problem, which is defined as: given an image of a person, determine if there is a tattoo or not, and results were satisfactory, given the complexity of the problem.
Tasks Integrated Networks: Joint Detection and Retrieval for Image Search
TLDR
An end-to-end Integrated Net is introduced, called DC-I-Net, which outperforms the state-of-the-art tasks-integrated and tasks-separated image search models and makes two new contributions: two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed.
Semi-Supervised Natural Face De-Occlusion
TLDR
Experimental evaluations on the widely used CelebA dataset and a dataset with natural occlusions the authors collected show that the proposed approach can outperform the state of the art methods in natural face de-occlusion.
Aurora Image Search With a Saliency-Weighted Region Network
TLDR
By considering the imaging principle and geomagnetic information, a saliency-weighted region network (SWRN) is presented and introduced into the Mask R-CNN pipeline, and a compact CNN feature is generated to represent the aurora image.
FCSR-GAN: Joint Face Completion and Super-Resolution via Multi-Task Learning
TLDR
This work proposes a deep generative adversarial network (FCSR-GAN) for performing joint face completion and face super-resolution via multi-task learning and shows good generalization ability in cross-database testing.
Correlation Filtering-Based Hashing for Fine-Grained Image Retrieval
TLDR
This letter proposes a correlation filtering hashing (CFH) method to learn discrete binary codes, which can adequately take advantage of the cross-modal correlation between the semantic information and the visual features for discriminative region localization.
Deep Gait Recognition: A Survey
TLDR
A novel taxonomy made up of four separate dimensions namely body representation, temporal representation, feature representation, and neural architecture is proposed to help characterize and organize the research landscape and literature in gait recognition.
Colour Neural Descriptors for Instance Retrieval Using CNN Features and Colour Models
TLDR
This work introduces colour neural descriptors that are made of convolutional neural networks features obtained by combining different colour spaces and colour channels, and takes advantage of an object detector to optimize the proposed instance retrieval architecture to generate features at both local and global scales.
Joint Pedestrian and Body Part Detection via Semantic Relationship Learning
TLDR
A Body Part Indexed Feature (BPIF) representation is proposed to encode the semantic relationship between individual body parts and highlight per body part features, providing robustness against partial occlusions to the whole body.
...
...

References

SHOWING 1-10 OF 83 REFERENCES
Tattoo detection and localization using region-based deep learning
TLDR
A tattoo detector is trained from the Tatt-C and PASCAL VOC 2007 image datasets using region-based deep learning to effectively determine if an image contains tattoos and the locations of tattoo regions, achieving a better detection error trade-off curve.
Tattoo Detection for Soft Biometric De-identification Based on Convolutional Neural Networks
TLDR
A method for tattoo detection in unconstrained images, intended to serve as a first step for soft biometric de-identification, based on a deep convolutional neural network that discriminates between tattoo and non-tattoo image patches and it can be used to produce a mask of tattoo candidate regions.
Tattoo detection based on CNN and remarks on the NIST database
TLDR
The experimental results demonstrate that the CNN outperforms the MorphoTrak's algorithm by 2.5%, achieving accuracy of 98.8% on the NIST database, implying that the Nist database is not an ideal database for training algorithms to detect tattoo images in IT devices of suspects.
Joint Detection and Identification Feature Learning for Person Search
TLDR
A new deep learning framework for person search that jointly handles pedestrian detection and person re-identification in a single convolutional neural network and converges much faster and better than the conventional Softmax loss.
Deep Tattoo Recognition
  • Xing Di, Vishal M. Patel
  • Computer Science
    2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
  • 2016
TLDR
Deep convolutional neural network-based methods for automatic matching of tattoo images based on the AlexNet and Siamese networks are presented and it is shown that rather than using a simple contrastive loss function, triplet loss function can significantly improve the performance of a tattoo matching system.
Large-Scale Tattoo Image Retrieval
  • D. Manger
  • Computer Science
    2012 Ninth Conference on Computer and Robot Vision
  • 2012
TLDR
This paper shows how recent advances in CBIR can be utilized to build up a large-scale tattoo image retrieval system and chose a different approach to circumvent the loss of accuracy caused by the bag-of-word quantization.
Detecting and classifying scars, marks, and tattoos found in the wild
TLDR
This work introduces a new methodology for detecting and classifying scars, marks and tattoos found in unconstrained imagery typical of forensics scenarios, and considers the “open set” nature of the classification problem, and describes an appropriate machine learning methodology that addresses it.
End-to-End Spatial Transform Face Detection and Recognition
Learning Face Representation from Scratch
TLDR
A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF.
Tattoo based identification: Sketch to image matching
TLDR
This paper proposes a method to match tattoo sketches to tattoo images using local invariant features using local feature based sparse representation classification scheme and shows that the proposed method achieves significant improvement compared to a state-of-the-art tattoo image-to-image matching system.
...
...