DICTA-2019 – Full Program

 

Day 0 – Sunday, 1 December

17:00 - 18:00

Registration

17:00 - 19:00

Welcome Reception

Day 1 – Monday, 2 December

08:15 - 08:45

Registration

08:45 - 09:00

Conference Opening

09:00 - 10:00

Keynote 1: Prof Kyros Kutulakos

10:00 - 10:30

Morning Tea

10:30 - 12:00

Oral Session 1: Classification

Chair: (TBC)

12:00 - 13:00

Lunch

13:00 - 15:30

Poster Session 1

15:00 - 15:30

Afternoon Tea

15:30 - 17:00

Oral Session 2: 3D Vision

Chair: (TBC)

Day 2 – Tuesday, 3 December

08:15 - 09:00

Registration

09:00 - 10:00

Keynote 2: Prof Mubarak Shah

10:00 - 10:30

Morning Tea

10:30 - 12:00

Oral Session 3: Detection and Localization

Chair: (TBC)

12:00 - 13:00

Lunch

13:00 - 15:00

Poster Session 2

14:30 - 15:00

Afternoon Tea

15:00 - 16:30

Oral Session 4: Medical Image Analysis

Chair: (TBC)

16:30 - 17:30 

APRS AGM

18:40 - 22:00 

Conference Dinner

Day 3 – Wednesday, 4 December

08:15 - 09:00

Registration

09:00 - 10:00

Keynote 3: Dr Ivan Laptev

Towards Embodied Action Understanding

10:00 - 10:30

Morning Tea

10:30 - 12:00

Oral Session 5: Computer Vision Applications I

Chair: (TBC)

12:00 - 13:00

Lunch

13:00 – 14:00

Keynote 4: Prof Ian Reid

14:00 - 14:30

Oral Session 6 – Image and Text

Chair: (TBC)

14:30 - 15:00

Afternoon Tea

15:00 - 16:30

Oral Session 7 - Remote Sensing

Chair: (TBC)

16:30 - 16:45

Closing

Workshops – Thursday, 5 December

08:15 - 09:00

Registration

09:00 - 12:00

Adversarial Attacks on Deep Learning (Details TBC)

12:00 - 13:00

Lunch

13:00 – 16:00

Natural Language Processing - (Details TBC)

 

 

Oral Session 1: Classification

Chair: (TBC)

1.       

Object Graph Networks for Spatial Language Grounding.

Phil Hawkins (Queensland University of Technology, Australia); Frederic Maire (Queensland University of Technology, Australia); Simon Denman (Queensland University of Technology, Australia); and Mahsa Baktashmotlagh (University of Queensland, Australia)

2.       

Part-Based Feature Aggregation Method for Dynamic Scene Recognition.

Xiaoming Peng (University of Wollongong, Australia); and Abdesselam Bouzerdoum (University of Wollongong, Australia)

3.       

Generalized Zero-Shot Learning with Domain Classification in a Joint Semantic and Visual Space.

Rafael Felix (The University of Adelaide); Ben Harwood (Monash University); Michele Sasdelli (The University of Adelaide); Gustavo Carneiro (University of Adelaide)

4.       

Tree Log Identity Matching Using Convolutional Correlation Networks.

Mikko Vihlman (Aalto University); Jakke Kulovesi (Aalto University); Arto Visala (Aalto University)

5.       

A Classification Methodology based on Subspace Graphs Learning.

Riccardo La Grassa (University of Insubria, Italy); Ignazio Gallo (University of Insubria, Italy); Alessandro Calefati (University of Insubria, Italy); and Dimitri Ognibene (University of Essex, United Kingdom)

6.       

Faster R-CNN Based Deep Learning for Seagrass Detection from Underwater Digital Images.

Md Moniruzzaman (Edith Cowan University); Syed Islam (Edith Cowan University); Paul Lavery (Edith Cowan University); Mohammed Bennamoun (University of Western Australia)

 

Oral Session 2: 3D Vision

Chair: (TBC)

1.       

Fast Point Cloud Registration using Semantic Segmentation.

Giang Truong (Edith Cowan University); Syed Zulqarnain Gilani (The University of Western Australia); Syed Islam (Edith Cowan University); David Suter (Edith Cowan University)

2.       

Single View 3D Point Cloud Reconstruction using Novel View Synthesis and Self Supervised Depth Estimation.

Adrian Johnston (University of Adelaide); Gustavo Carneiro (University of Adelaide)

3.       

Perspective-consistent multifocus multiview 3D reconstruction of small objects.

Hengjia Li (Australian National University); Chuong Nguyen (CSIRO Data61)

4.       

High-Throughput Plant Height Estimation from RGB Images Acquired with Aerial Platforms: a 3D Point Cloud based Approach.

Xun Li (CSIRO, Australia); Geoff Bull (CSIRO, Australia); Robert Coe (CSIRO, Australia); Sakda Eamkulworapong (CSIRO, Australia); Jamie Scarrow (CSIRO, Australia); Michael Salim (CSIRO, Australia); Michael Schaefer (CSIRO, Australia); and Xavier Sirault (CSIRO, Australia)

5.       

AB-PointNet for 3D Point Cloud Recognition.

Junya Komori (Meijo university); Kazuhiro Hotta (Meijo University)

6.       

An Automated Method for Individual Wire Extraction from Power Line Corridor using LiDAR Data.

Nosheen Munir (Griffith University); Mohammad Awrangjeb (Griffith University, Australia); Bela Stantic (Griffith University)

 

Oral Session 3: Detection and Localization

Chair: (TBC)

1.       

Insect-inspired Small Moving Target Enhancement in Infrared Videos.

Muhammad Uzair (University of South Australia); Russell Brinkworth (University of South Australia); Anthony Finn (University of South Australia)

2.       

Visual Localization Under Appearance Change: A Filtering Approach.

Dzung Anh Doan (The University of Adelaide, Australia); Yasir Latif (The University of Adelaide, Australia); Tat-Jun Chin (University of Adelaide, Australia); Yu Liu (The University of Adelaide, Australia); Shin-Fang Ch’ng (The University of Adelaide, Australia); Thanh-Toan Do (The University of Liverpool, UK); Ian Reid (The University of Adelaide, Australia )

3.       

Automatic Nipple Detection Method for Digital Skin Images with Psoriasis Lesions.

Yasmeen M George (University of Melbourne); Mohammad Aldeen (Department of Electrical and Electronic Engineering, University of Melbourne, Australia); Rahil Garnavi (IBM Research Australia)

4.       

OGaze: Gaze Prediction in Egocentric Videos for Attentional Object Selection.

Mohammad Al-Naser (German Research Centre for Artificial Intelligence (DFKI)); Shoaib Ahmed Siddiqui (DFKI); Hiroki Ohashi (Hitachi Ltd); Sheraz Ahmed (DFKI); Nakamura KATSUYUKI (Hitachi); Sato Takuto (Hitachi); Andreas Dengel (DFKI GmbH)

5.       

Deep-Learning From Mistakes: Automating Cloud Class Refinement for Sky Image Segmentation.

S3.5. Gemma Dianne (University of Queensland, Australia); Arnold Wiliem (University of Queensland, Australia); and Brian C. Lovell (University of Queensland, Australia)

6.       

Enhanced micro target detection through local motion feedback in biologically inspired algorithms.

Aaron Melville-Smith (University of South Australia); Anthony Finn (University of South Australia); Russell Brinkworth (University of South Australia)

 

Oral Session 4: Medical Image Analysis

Chair: (TBC)

1.       

To What Extent Does Downsampling, Compression, and Data Scarcity Impact Renal Image Analysis?

Can Peng (the University of Queensland); Kun Zhao (University of Queensland); Arnold Wiliem (the University of Queensland); Teng Zhang (The University of Queensland); Peter Hobson (Sullivan Nicolaides Pathology); Anthony Jennings (Sullivan Nicolaides Pathology); Brian C Lovell (University of Queensland)

2.       

SRM superpixel merging framework for precise segmentation of cervical nucleus.

Ratna Saha (Flinders University); Mariusz Bajger (Flinders University); Gobert Lee (Flinders University)

3.       

From Chest X-rays to Radiology Reports: A Multimodal Machine Learning Approach.

Sonit Singh (Macquarie University); Sarvnaz Karimi (DATA61, CSIRO); Kevin Ho-Shon (Macquarie University); Len Hamey (Computing Department, Macquarie University, NSW 2109)

4.       

Constructing synthetic chorio-retinal patches using generative adversarial networks.

Jason Kugelman (Queensland University of Technology); David Alonso-Caneiro (Queensland University of Technology); Scott Read (Queensland University of Technology); Stephen Vincent (Queensland University of Technology); Fred Chen (Lions Eye Institute); Michael Collins (Queensland University of Technology)

5.       

Radiography Contrast Enhancement: Smoothed LHE Filter a Practical Solution for Digital X-rays with Mach band.

Prasoon Ambalathankandy (Hokkaido University, Japan); Yafei Ou (Hokkaido University, Japan); Jyotsna Kochiyil (Independent Radiologist, United States); Shinya Takamaeda (Hokkaido University, Japan); Masato Motomura (Tokyo Institute of Technology, Japan); Tetsuya Asai (Hokkaido University, Japan); and Masayuki Ikebe (Hokkaido University, Japan)

6.       

Assessment and Elimination of Inflammatory Cell: A Machine Learning Approach in Digital Cytology.

Jing Ke (Shanghai Jiao Tong University, China); Junwei Deng (University of Michigan, United States); Yizhou Lu (Shanghai Jiao Tong University, China); Dadong Wang (Data61, CSIRO, Australia); Yang Song (University of New South Wales, Australia); and Huijuan Zhang (Shanghai Jiao Tong University, China)

 

Oral Session 5: Computer Vision Applications I

Chair: (TBC)

1.       

Modelling and Flame Segmentation for Real-Time Monitoring of Rotary Kilns.

John Ridley (Curtin University); Duc Son Pham (Curtin University); Mihai Lazarescu (Curtin University)

2.       

Multi-pooling attention learning for melanoma recognition.

Ruolin Liang (South China University of Technology, China); Qiuxia Wu (South China University of Technology, China); and Xiaowei Yang (South China University of Technology, China)

3.       

Mine-like Object Sensing in Sonar Imagery with a Compact Deep Learning Architecture for Scarce Data.

Son Lam Phung (University of Wollongong, Australia); Thi Nhat Anh Nguyen (University of Wollongong, Australia); Hoang Thanh Le (University of Wollongong, Australia); Philip Chapple (Defence Science Technology Group, Australia); Christian Ritz (University of Wollongong, Australia); Abdesselam Bouzerdoum (University of Wollongong, Australia); and Le Chung Tran (University of Wollongong, Australia)

4.       

Using style-transfer to understand material classification for robotic sorting of recycled beverage containers.

Mark D. McDonnell (University of South Australia); Bahar Moezzi (University of South Australia); Russell Brinkworth (University of South Australia)

5.       

EncapNet-3D and U-EncapNet for Cell Segmentation.

Takumi Sato (Meijo University); Kazuhiro Hotta (Meijo University)

6.       

Explaining Machine Learning based Classifications of in-vivo Gastral Images.

Avleen Malhi (Aalto University); Timotheus Kampik (Umeå University); Husanbir Singh Pannu (Thapar University); Manik Madhikermi (Aalto University); Kary Främling (Aalto University)

 

Oral Session 6 – Image and Text (or Computer Vision Applications II)

Chair: (TBC)

1.       

Historical Document Text Binarization using Atrous Convolution and Multi-scale Feature Decoder.

Hanif Rasyidi (Australian National University); Salman Khan (Australian National University (ANU))

2.       

Picture What you Read.

Ignazio Gallo (University of Insubria, Italy); Shah Nawaz (University of Insubria, Italy); Alessandro Calefati (University of Insubria, Italy); Riccardo La Grassa (University of Insubria, Italy); and Nicola Landro (University of Insubria, Italy)

 

Oral Session 7 - Remote Sensing

Chair: (TBC)

1.       

Robust Image Watermarking Framework Powered by Convolutional Encoder-Decoder Network.

Thien Huynh-The (Kumoh National Institute of Technology, South Korea); Cam-Hao Hua (Kyung Hee University, South Korea); Tu Nguyen (Nazarbayev University, Kazakhstan); and Dong-Seong Kim (Kumoh National Institute of Technology, South Korea)

2.       

Runway detection and localization in aerial images using deep learning.

Javeria Akbar (National University of Sciences and Technology, Pakistan); Muhammad Shahzad (National University of Sciences and Technology, Pakistan); Muhammad Imran Malik (National University of Sciences and Technology, Pakistan); Adnan Ul-Hasan (Deep Learning Laboratory, National Center of Artificial Intelligence, Pakistan); and Faisal Shafait (National University of Sciences and Technology, Pakistan)

3.       

Abundance-guided Superpixels and Recurrent Neural Network for Hyperspectral Image Classification.

Fahim Alam (Griffith University, Australia); Jun Zhou (Griffith University, Australia); Alan Liew (Griffith University, Australia)

4.       

Temporal 3D fully connected network for water-hazard detection.

Juntao Li (Australian National University, Australia); Chuong Nguyen (CSIRO, Australia); and Shaodi You (CSIRO, Australia)

5.       

Improved Detection for WAMI using Background Contextual Information.

Elena M Vella (The University of Melbourne); Anee Azim (Lockheed Martin); Han Gaetjens (Lockheed Martin); Boris Repasky (Lockheed Martin); Timothy Payne (Lockheed Martin)

6.       

Change Detection Over the State of Queensland Using High Resolution Planet Satellite Mosaics.

Connor McLaughlin (Queensland University of Technology, Australia); Holly Hutson (Queensland University of Technology, Australia); Lance De Vine (Queensland University of Technology, Australia); Alan Woodley (Queensland University of Technology, Australia); Shlomo Geva (Queensland University of Technology, Australia); Timothy Chappell (Queensland University of Technology, Australia); Wayne Kelly (Queensland University of Technology, Australia); Wageeh Boles (Queensland University of Technology Australia); and Dimitri Perrin (Queensland University of Technology, Australia)

 


 

Poster Session 1

P1.1.     Image Alignment Using Norm Conserved GAT Correlation
Toru Wakahara (Hosei University, Japan); Yukihiko Yamashita (Tokyo Institute of Technology, Japan)

P1.2.     Wave scale, speed and direction from airborne video of maritime scene
Kent Rosser (Defence Science and Technology Group, Australia); and Javaan Chahl (University of South Australia, Australia)

P1.3.     Indian Sign Language Gesture Recognition using Image Processing and Deep Learning
Neel Kamal Bhagat (IISc, Bangalore, India); Vishnusai Yoganand (RV College of Engineering, India); and Rathna G N (IISc, Bangalore, India)

P1.4.     Reading Meter Numbers in the Wild
Alessandro Calefati (University of Insubria, Italy); Ignazio Gallo (University of Insubria, Italy); Shah Nawaz (University of Insubria, Italy)

P1.5.     Automated Building Footprint and 3D Building Model Generation from Lidar Point Cloud Data
Fayez Tarsha Kurdi (Griffith University, Australia); Mohammad Awrangjeb (Griffith University, Australia, Australia); Alan Liew (Griffith University, Australia)

P1.6.     Deep Latent Space Learning for Cross-modal Mapping of Audio and Visual Signals
Shah Nawaz (University of Insubria, Italy); Muhammad Kamran Janjua (National University of Sciences and Technology, Pakistan); Ignazio Gallo (University of Insubria, Italy); Arif Mahmood (Information Technology University, Pakistan); Alessandro Calefati (University of Insubria, Italya)

P1.7.     Using Image Processing to Automatically Measure Pearl Oyster Size for Selective Breeding
Adrian Lapico (James Cook University, Australia); Mangalam Sankupellay (James Cook University, Australia); Louis Cianciullo (James Cook University, Australia); Trina Myers (James Cook University, Australia); Dmitry Konovalov (James Cook University, Australia); Dean Jerry (James Cook University, Australia); Preston Toole (James Cook University, Australia); David Jones (James Cook University, Australia); and Kyall Zenger (James Cook University, Australia)

P1.8.     Real-Time Human Gaze Estimation
Thomas J Rowntree (The University of Adelaide, Australia); Carmine Pontecorvo (Defence Science and Technology Group, Australia); Ian Reid (University of Adelaide, Australia)

P1.9.     Deep Learning for Autonomous Driving
Jordan M King (University of Western Australia, Australia); Nicholas Burleigh (University of Western Australia, Australia); Thomas Braunl (University of Western Australia, Australia)

P1.10. LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
Taha Emara (Ain Shams University, Egypt); Hossam Abdelmunim (Ain Shams University, Egypt); Hazem Abbas (Ain Shams University, Egypt)

P1.11. Feature Engineering meets Deep Learning: A Case Study on Table Detection in Documents
Muhammad Ali Shahzad (Deutsches Forschungszentrum fur Kunstliche Intelligenz, Germany); Rabeya Noor (National University of Sciences and Technology, Pakistan); Sheraz Ahmad (Deutsches Forschungszentrum fur Kunstliche Intelligenz, Germany); Ajmal Mian (The University of Western Australia, Australi)a; and Faisal Shafait (National University of Sciences and Technology, Pakistan)

P1.12. Facial gender classification- Analysis using convolutional neural networks
Brian Lee (The University of Western Australia, Australia); Syed Zulqarnain Gilani (The University of Western Australia, Australia); Ghulam Mubashar Hassan (The University of Western Australia, Australia); Ajmal Mian (University of Western Australia)

P1.13. STCEC: A Remote Sensing Dataset for Identifying Spatial Temporal Change in Homogeneous and Heterogeneous Environments
Thaer F. Ali (Queensland University of Technology, Australia); and Alan Woodley (Queensland University of Technology, Australia)

P1.14. Semantic Segmentation under Severe Imaging Conditions
Hoda Imam (Ain Shams University, Egypt);
Bassem A. Abdullah (Ain Shams University, Egypt); and Hossam E. Abd El Munim (Ain Shams University, Egypt)

P1.15. Incorporating the Barzilai-Borwein Adaptive Step Size into Sugradient Methods for Deep Network Training
Antonio Robles-Kelly (Deakin University, Australia); Asef Nazari (Deakin University, Australia)

P1.16. Ensemble of Training Models for Road and Building Segmentation.
Ryosuke Kamiya (Meijo University, Japan); Kyoya Sawada (Meijo University, Japan); and Kazuhiro Hotta (Meijo University, Japan)

P1.17. Efficient Block Pruning based on kernel and feature stabilization.
Sheng Xu (Beihang University, China); Hanlin Chen (Beihang University, China); Kexin Liu (Beihang University, China); Jinhu Lyu (Beihang University, China); and Baochang Zhang (Beihang University, China)

P1.18. Bi-SAN-CAP: Bi-Directional Self-Attention for Image Captioning.
Md Zakir Hossain (Murdoch University); Ferdous Sohel (Murdoch University, Australia); Mohd Fairuz Shiratuddin (Murdoch University, Australia); Hamid Laga (Murdoch university, Australia); Mohammed Bennamoun (University of Western Australia, Australia)

P1.19. Scalable video classification using bag of visual words on Spark.
Nguyen Anh Tu (Nazarbayev University, Kazakhstan); Thien Huynh-The (Kumoh National Institute of Technology, South Korea); and Young-Koo Lee (Kyung Hee University, South Korea)

P1.20. Class Activation Map generation by Multiple Level Class Grouping and Orthogonal Constraint.
Kaixu Huang, University of Electronic Science and Technology of China, China; Fanman Meng, University of Electronic Science and Technology of China, China; Hongliang Li, University of Electronic Science and Technology of China, China; Shuai Chen, University of Electronic Science and Technology of China, China; Qingbo Wu, University of Electronic Science and Technology of China, China; and King N. Ngan, University of Electronic Science and Technology of China, China )

P1.21. Deep Fusion Net for Coral Classification in Fluorescence and Reflectance Images.
Uzair Nadeem, The University of Western Australia, Australia; Mohammed Bennamoun, The University of Western Australia, Australia; Ferdous Sohel, Murdoch University, Australia; and Roberto Togneri, The University of Western Australia, Australia )

P1.22. Logical Layout Analysis using Deep Learning.
Adnan Ul-Hasan, Deep Learning Lab, Pakistan; Annus Zulfiqar, NUST, Pakistan; and Faisal Shafait, NUST, Pakistan

 

 

Poster Session 2

P2.1.   Data Efficient Classification of Birdcall Through Convolutional Neural Networks Transfer Learning.
Dina Efremova, Funbox Inc., Russian Federation; Mangalam Sankupellay, James Cook University, Australia; and Dmitry Konovalov, James Cook University, Australia

P2.2.    Deep Corrosion Assessment for Electrical Transmission Towers.
Teng Zhang, The University of Queensland, Australia; Liangchen Liu, The University of Queensland, Australia; Arnold Wiliem, The University of Queensland, Australia; Stephen Connor, Powerlink Queensland, Australia; Zelkjo Ilich, Powerlink Queensland, Australia; Eddie Van Der Draai, Powerlink Queensland, Australia; and Brian Lovell, University of Queensland, Australia)

P2.3.    Automatic Weight Estimation of Harvested Fish from Images.
Dmitry Konovalov, James Cook University, Australia; Alzayat Saleh, James Cook University, Australia; Dina Efremova, Funbox Inc, Russian Federation; Jose Domingos, James Cook University, Australia; and Dean Jerry, James Cook University, Australia

P2.4.    Measurement of Traffic Volume by Time Series Images Created from Horizontal Edge Segments.
Kazunori Onoguchi (Hirosaki University, Japan)

P2.5.    Flood Detection in Social Media Images Using Visual Features and Metadata.
Rabiul Islam Jony, Queensland University of Technology, Australia;Alan Woodley, Queensland University of Technology, Australia; and Dimitri Perrin, Queensland University of Technology, Australia

P2.6.    Blind Motion Deblurring for Satellite Image using Convolutional Neural Network.
Hyun-ho Kim, Korea Aerospace Research Institute, Republic of Korea; Doochun Seo, Korea Aerospace Research Institute, Republic of Korea; Jaeheon Jung, Korea Aerospace Research Institute, Republic of Korea; Donghwan Cha, Korea Aerospace Research Institute, Republic of Korea; and Donghan Lee, Korea Aerospace Research Institute, Republic of Korea

P2.7.    Evaluation of the impact of image spatial resolution in designing a context-based fully convolution neural networks for flood mapping.
Chandrama Sarker, Queensland University of Technology, Australia; Luis Mejias, Queensland University of Technology, Australia; Frederic Maire, Queensland University of Technology, Australia; and Alan Woodley, Queensland University of Technology, Australia

P2.8.    Hyperspectral Image Analysis for Writer Identification using Deep Learning.
Ammad Ul Islam, Institute of Space Technology, Pakistan; Muhammad Jaleed Khan, Institute of Space Technology, Pakistan; Khurram Khurshid, Institute of Space Technology, Pakistan; and Faisal Shafait, National University of Sciences and Technology, Pakistan

P2.9.    Automatic generation of lymphoma post-treatment PETs using conditional-GANs.
Gabriel Silva, Instituto Superior de Engenharia de Coimbra, Portugal; Ines Domingues, IPO Porto Research Center (CI-IPOP), Portugal; Hugo Duarte, Portuguese Institute of Oncology of Porto (IPO-Porto), Portugal; and Joao A. M. Santos, Portuguese Institute of Oncology of Porto (IPO-Porto), Portugal

P2.10. Corporate IT-support Help-desk Process Hybrid-Automation Solution with Machine Learning Approach.
Kuruparan Shanmugalingam, Millennium I.T E.S.P (Pvt) Ltd, Sri Lanka; Nisal Chandrasekara, Millennium I.T E.S.P (Pvt) Ltd, Sri Lanka; Calvin Hindle, Millennium I.T E.S.P (Pvt) Ltd, Sri Lanka; Gihan Fernando, Millennium I.T E.S.P (Pvt) Ltd, Sri Lanka; and Chanaka Gunawardhana, Millennium I.T E.S.P (Pvt) Ltd, Sri Lanka

P2.11. Social network analysis of an acoustic environment: the use of visualised data to characterise natural habitats.
Junling Wang, James Cook University, Australia; Mangalam Sankupellay, James Cook University, Australia; Dmitry Konovalov, James Cook University, Australia; Michael Towsey, Queensland University of Technology, Australia; and Paul Roe, Queensland University of Technology, Australia

P2.12. Improved Image Analysis Methodology for Detecting Changes in Evidence Positioning at Crime Scenes.
Mark Petty, Federation University Australia, Australia;Shyh Wei Teng, Federation University Australia, Australia; and Manzur Murshed, Federation University Australia, Australia

P2.13. Detection of Central Retinal Vein Occlusion Using Guided Salient Features.
Nirupama Rajapaksha, University of Moratuwa, Sri Lanka;Lochandaka Ranathunga, University of Moratuwa, Sri Lanka; and K.M.P.K. Bandara, Teaching Hospital, Ragama, Sri Lanka

P2.14. Haar Pattern Based Binary Feature Descriptor for Retinal Image Registration.
Sajib Saha, Commonwealth Scientific and Industrial Research Organisation, Australia; and Yogesan Kanagasingam, Commonwealth Scientific and Industrial Research Organisation, Australia

P2.15. FFD: Figure and Formula Detection from Document Images.
Junaid Younas, Technical University Kaiserslautern, Germany; Syed Tahseen Raza Rizvi, Technical University Kaiserslautern, Germany; Muhammad Imran Malik, National University of Science Technology, Pakistan;Faisal Shafait, National University of Science Technology, Pakistan; Paul Lukowicz, Technical University Kaiserslautern, Germany; and Sheraz Ahmed, DFKI, Germany

P2.16. Benchmarking Object Detection Networks for Image based Reference Detection in Document Images.
Syed Tahseen Raza Rizvi, German Research Center for Artificial Intelligence, Germany; Adriano Lucieri, German Research Center for Artificial Intelligence, Germany; Andreas Dengel, German Research Center for Artificial Intelligence, Germany; and Sheraz Ahmed, German Research Center for Artificial Intelligence, Germany

P2.17. Registration Based Data Augmentation for Multiple Sclerosis Lesion Segmentation.
Ava Assadi Abolvardi, Macquarie University, Australia; Len Hamey, Macquarie University, Australia; and Kevin Ho-Shon, Macquarie University, Australia

P2.18. Improving Follicular Lymphoma Identification using the class of interest for Transfer Learning.
Upeka Somaratne, Murdoch University, Australia; Kok Wong, Murdoch University, Australia; Jeremy Parry, PathWest Laboratory Medicine WA, Australia; Ferdous Sohel, Murdoch University, Australia; Xuequn Wang, Murdoch University, Australia; and Hamid Laga, Murdoch University, Australia

P2.19. Multimodal brain tumour segmentation using densely connected 3D convolutional neural network.
Mina Ghaffari, Macquarie University, Australia; Arcot Sowmya, University of New South Wales, Australia; Len Hamey, Macquarie University, Australia; and Ruth Oliver, Macquarie University, Australia

P2.20. Rain Streak Removal from Video Sequence Using Spatiotemporal Appearance.
Muhammad Rafiqul Islam, Charles Sturt University, Australia; and Manoranjan Paul, Charles Sturt University, Australia

P2.21. Facial-Expression Recognition from Video Using Enhanced Convolutional LSTM.
Ryo Miyoshi, Chukyo University, Japan; Noriko Nagata, Kwansei Gakuin University, Japan; and Manabu Hashimoto, Chukyo University, Japan

P2.22.     Adult or Child: Recognizing through touch gestures on smartphones.
Osama Rasheed, COMSATS University, Pakistan; Aimal Rextin, COMSATS University, Pakistan; and Mehwish Nasim, Data61 CSIRO, Australia