Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks

Similar documents
Lecture 6: CNNs for Detection, Tracking, and Segmentation Object Detection

Lecture 6: Classification & Localization. boris. ginzburg@intel.com

Steven C.H. Hoi School of Information Systems Singapore Management University

Image and Video Understanding

Supporting Online Material for

Bert Huang Department of Computer Science Virginia Tech

Pedestrian Detection with RCNN

CS 1699: Intro to Computer Vision. Deep Learning. Prof. Adriana Kovashka University of Pittsburgh December 1, 2015

Compacting ConvNets for end to end Learning

T O B C A T C A S E G E O V I S A T DETECTIE E N B L U R R I N G V A N P E R S O N E N IN P A N O R A MISCHE BEELDEN

Image Classification for Dogs and Cats

Learning and transferring mid-level image representions using convolutional neural networks

MulticoreWare. Global Company, 250+ employees HQ = Sunnyvale, CA Other locations: US, China, India, Taiwan

Fast R-CNN. Author: Ross Girshick Speaker: Charlie Liu Date: Oct, 13 th. Girshick, R. (2015). Fast R-CNN. arxiv preprint arxiv:

Fast R-CNN Object detection with Caffe

Pedestrian Detection using R-CNN

Lecture 2: The SVM classifier

Learning to Process Natural Language in Big Data Environment

Introduction to Machine Learning CMU-10701

Face Recognition: Some Challenges in Forensics. Anil K. Jain, Brendan Klare, and Unsang Park

Multi-Column Deep Neural Network for Traffic Sign Classification

Applications of Deep Learning to the GEOINT mission. June 2015

Convolutional Feature Maps

Stochastic Pooling for Regularization of Deep Convolutional Neural Networks

Novelty Detection in image recognition using IRF Neural Networks properties

Transfer Learning for Latin and Chinese Characters with Deep Neural Networks

The Delicate Art of Flower Classification

Face Recognition For Remote Database Backup System

InstaNet: Object Classification Applied to Instagram Image Streams

NAVIGATING SCIENTIFIC LITERATURE A HOLISTIC PERSPECTIVE. Venu Govindaraju

Applying Deep Learning to Car Data Logging (CDL) and Driver Assessor (DA) October 22-Oct-15

Towards Reversible De-Identification in Video Sequences Using 3D Avatars and Steganography

Application of Face Recognition to Person Matching in Trains

Learning Detectors from Large Datasets for Object Retrieval in Video Surveillance

Deformable Part Models with CNN Features

VEHICLE LOCALISATION AND CLASSIFICATION IN URBAN CCTV STREAMS

EdVidParse: Detecting People and Content in Educational Videos

Machine Learning Logistic Regression

Recognizing Cats and Dogs with Shape and Appearance based Models. Group Member: Chu Wang, Landu Jiang

Methods and Applications for Distance Based ANN Training

The Applications of Deep Learning on Traffic Identification

3D Object Recognition using Convolutional Neural Networks with Transfer Learning between Input Channels

Module 5. Deep Convnets for Local Recognition Joost van de Weijer 4 April 2016

Big Data in the Mathematical Sciences

Parallel & Distributed Optimization. Based on Mark Schmidt s slides

More Data Mining with Weka

Feature Selection vs. Extraction

SIGNAL INTERPRETATION

LOCAL SURFACE PATCH BASED TIME ATTENDANCE SYSTEM USING FACE.

Analecta Vol. 8, No. 2 ISSN

Chapter 6. The stacking ensemble approach

Detection. Perspective. Network Anomaly. Bhattacharyya. Jugal. A Machine Learning »C) Dhruba Kumar. Kumar KaKta. CRC Press J Taylor & Francis Croup

Sense Making in an IOT World: Sensor Data Analysis with Deep Learning

Digital Identity & Authentication Directions Biometric Applications Who is doing what? Academia, Industry, Government

Interactive person re-identification in TV series

Automatic 3D Reconstruction via Object Detection and 3D Transformable Model Matching CS 269 Class Project Report

A Content based Spam Filtering Using Optical Back Propagation Technique

Recurrent Neural Networks

Recognition of Facial Expression Using AAM and Optimal Neural Networks

Feature Subset Selection in Spam Detection

Real time vehicle detection and tracking on multiple lanes

arxiv: v2 [cs.cv] 19 Jun 2015

CAP 6412 Advanced Computer Vision

Recognition. Sanja Fidler CSC420: Intro to Image Understanding 1 / 28

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

Experiments in Web Page Classification for Semantic Web

Local features and matching. Image classification & object localization

Keywords Input Images, Damage face images, Face recognition system, etc...

International Journal of Advanced Information in Arts, Science & Management Vol.2, No.2, December 2014

Semantic Recognition: Object Detection and Scene Segmentation

Introduction to Data Mining

Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?

Taking Inverse Graphics Seriously

FRAUD DETECTION IN ELECTRIC POWER DISTRIBUTION NETWORKS USING AN ANN-BASED KNOWLEDGE-DISCOVERY PROCESS

FPGA Implementation of Human Behavior Analysis Using Facial Image

Efficient Attendance Management: A Face Recognition Approach

arxiv: v2 [cs.cv] 30 Jan 2015

Two-Stream Convolutional Networks for Action Recognition in Videos

Data Mining Algorithms Part 1. Dejan Sarka

Data Mining Practical Machine Learning Tools and Techniques

Supervised Learning (Big Data Analytics)

Facebook Friend Suggestion Eytan Daniyalzade and Tim Lipus

Industrial Challenges for Content-Based Image Retrieval

Deep learning applications and challenges in big data analytics

Dr. Asher Vaturi The Max Stern Yezreel Valley College

CNN Based Object Detection in Large Video Images. WangTao, IQIYI ltd

Keypoint Density-based Region Proposal for Fine-Grained Object Detection and Classification using Regions with Convolutional Neural Network Features

Image Analysis CHAPTER ANALYSIS PROCEDURES

Simplified Machine Learning for CUDA. Umar

III. SEGMENTATION. A. Origin Segmentation

Administrivia. Traditional Recognition Approach. Overview. CMPSCI 370: Intro. to Computer Vision Deep learning

Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승

Speed Performance Improvement of Vehicle Blob Tracking System

Machine Learning Introduction

Performance Metrics. number of mistakes total number of observations. err = p.1/1

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

A Study on SURF Algorithm and Real-Time Tracking Objects Using Optical Flow

Application of Data Mining based Malicious Code Detection Techniques for Detecting new Spyware

Selecting Receptive Fields in Deep Networks

Advanced analytics at your hands

Transcription:

1 Tattoo Detection for Soft Biometric De-Identification Based on Convolutional NeuralNetworks Tomislav Hrkać, Karla Brkić, Zoran Kalafatić Faculty of Electrical Engineering and Computing University of Zagreb, Croatia

Introduction Motivation o Omnipresence of surveillance cameras serios privacy risk for law abiding individuals o Aggravated by the development of various techniques for: video retrieval person re-identification o Juridical regulation for the protection of personal data o For video sequences: removing personally identifying features of recorded individuals in reversible fashion maintaining information on the action and its context 2

Introduction De-identification o removal of personally identifying features from data o Biometric features: fingerprints, iris, face,... o Soft biometric / non-biometric features: tattoos, birthmarks hairstyle clothing,... 3

Introduction De-identification o Proposed / comercially used approaches: face blurring soft and non-biometric features mostly ignored o Possible approaches to soft / non-biometric de-identification: de-identification of whole persons localization and de-identification of individual soft and nonbiometric identifiers 4

Related work o De-identification most work concerned with de-identifing biometric features, especially the face (e.g. Gross et al. 2009.) little to no work devoted to soft and non-biometric de-identification o Tattoo recognition studied in the context of forensic applications (Jain et al. 2008, 2013...) cropped images; content based image retrieval detection in the wild (Heflin et al. 2012) o Deep learning applied to wide variety of problems with competitive results convolutional neural networks can learn good features on their own (Krizhevsky et al. 2014, LeCun et al. 2015,...) 5

Proposed method Tattoos o Great variability of designs, skin color, lighting conditions, may resemble many different real objects... o Difficult to devise good hand-crafted features o Convolutional neural networks (CNNs) able to learn good features for many classification tasks 6

Proposed method Patch labeling using convolutional neural network (CNN) o CNNs: convolutional layers in charge of learning good features local receptive fields shared weights pooling layers reduce the feature space dimensionality fully connected layers perform the classification task contain majority of learned weights 7

8 Proposed method The proposed network architecture o inspired by VGGNet (Simonyan and Zisserman 2014)

Dataset o No readily available tattoo dataset we developed our own subset of ImageNet containing tattoos tattoos precisely annotated manually (890 images) 9

Dataset o Positive and negative samples: 22700 image patches generated by randomly sampling image patches (N*N) from the annotated images (2 classes: tattoo & background) 10

Training the network o Patches dataset (11359 P + 11341 N = 22700 total): training data: 2/3 of the dataset (7573 P + 7560 N = 15134 total) validation data: 1/6 of the dataset (1893 P + 1890 N = 7573 total) test data: 1/6 of the dataset (1893 P + 1890 N = 7573 total) patches extracted from the same image end: up in the same subset o Network trained on the training dataset optimizing mean sqared error loss stochastic gradient descent with momentum mini-batch: 32 samples learning rate 0.1 max 40 epochs; early stopping 11

Evaluation o Network trained and evaluated for different patch sizes: 8*8, 12*12, 16*16, 24*24, 32*32, 48*48 larger patches presumably provide more information about context smaller patches faster to train and test o Results (using test dataset) Patch size 8*8 12*12 16*16 24*24 32*32 48*48 # FN 152 229 187 213 248 290 FN (%) 8.03 % 12.10 % 9.88 % 11.25 % 13.10 % 15.32 % # FP 593 418 444 436 337 408 FP (%) 31.37 % 22.12 % 23.49 % 23.07 % 17.83 % 21.59 % Acc (%) 80.31 % 82.90 % 83.32 % 82.83 % 83.54 % 81.55 % 12

Tattoo detection - examples o Preliminary experiments in a sliding window setting original images labeled tattoo patches 13

Some observations o Larger patch sizes (up to 32*32) better accuracy less false positives more false negatives (!?) o Encurraging results on complete images relatively simple examples most tattoo patches correctly detected some misclassifications more difficult examples (more bg with textured objects) - #FP rises o Possible improvements to elliminate false positives combine with person detector (most FP are in the background) merge detections into blobs; disregard unconnected detections 14

Conclusions and outlook o Some conclusions: We addressed the challenging problem of tattoo detection for soft biometric de-identification Instead of hand-crafting the features, we applied deep learning Deep CNN trained using a dataset of positive and negative patches generated from a subset of annotated ImageNet tattoo images Using CNN to classify small image patches can be a reliable way to detect candidate tattoo regions Patch size should be kept up to 32*32 Further experiments needed o Possible improvements: Combining the tattoo detector with person detector Merging detections into blobs 15

16 Discussion o Thank you for your attention! o Questions?