Natal-RN - Brazil | Oct 30th - Nov 1st, 2017

XIII Workshop de Visão Computacional (WVC 2017)

This will be the 13th edition of the WVC. Researchers, graduate and undergraduate students who are working in Computer Vision are invited to submit technical papers about novel research contributions or applications.
In 2017, WVC will take place at the Federal University of Rio Grande do Norte (UFRN), Natal, Rio Grande do Norte, Brazil.
Important dates:
  • Paper Subscription deadline: July 23rd (extended, firm deadline)
  • Notification of Acceptance: September 11th
  • Camera Ready Deadline: September 25th
  • Venue: October 30th - November 1st (Natal-RN)

Call for Papers - WVC 2017

XIII Workshop de Visão Computacional(WVC 2017)


This will be the 13th edition of the WVC. Researchers, graduate and undergraduate students who are working in Computer Vision are invited to submit technical papers about novel research contributions or applications.
In 2017, WVC will take place at the Federal University of Rio Grande do Norte (UFRN), Natal, Rio Grande do Norte, Brazil.
Important dates:
  • Paper Subscription deadline: July 23rd (extended, firm deadline)
  • Notification of Acceptance: September 11th
  • Camera Ready Deadline: September 25th
  • Venue: October 30th - November 1st (Natal-RN)
Topics of interest include (but are not limited to):
  • Images and Video Coding
  • Image/video analysis
  • Image/video filtering and restoration
  • Image/video registration
  • Image/video segmentation
  • Motion Detection and Tracking
  • Shape representation and matching
  • Surface Reconstruction and Representation
  • Projective Geometry and Computer Vision
  • Texture and Color in Computer Vision
  • Feature extraction
  • Feature Matching, Inference and Recognition
  • Pattern Recognition in Computer Vision
  • Cognitive models applied to Computer Vision Systems
  • Architectural models for Computer Vision
  • Design methods for systems of Vision
  • Case studies and Computer Vision systems analysis
  • Real-time Computer Vision
  • Facial and Hand Gesture Recognition
  • Biomedical imaging and visualization
  • Biometrics
  • Visual Inspection and Robotics
  • Visual Document processing and analysis
  • Content-based image retrieval (CBIR)
If you have any question and need further information, please feel free to contact us on the workshop email: wvc2017@natalnet.br.

Sincerely, The Chairs of WVC 2017:
Bruno Marques Ferreira da Silva (UFRN)
Bruno Motta de Carvalho (UFRN)
Marcelo Andrade da Costa Vieira (USP)
Rafael Beserra Gomes (UFRN)

Registration

The registration system for the WVC 2017 is now open! Authors can register to te event following the instruction on the Registration Website. Information about payments via "Nota de Empenho" is available at the bottom of the Registration Website.

  • An early full registration of at least one author is required for each paper publication
  • An early full registration covers up to two papers
  • An extra fee of R$ 200,00 covers up to two additional papers (until 06/10/2017)
  • All papers (both oral/poster) written in English will be published in IEEE. Further instructions will be send to the authors regarding IEEE publication.
In the table below, you can find the event registration fees:
Type Early Registration (Until 06/10/2017) After (06/10/2017)
Professional R$ 500,00 R$ 700,00
SBC Professional R$ 425,00 R$ 595,00
Graduate Student R$ 250,00 R$ 350,00
SBC Graduate Student R$ 210,00 R$ 295,00
Undergrad. Student R$ 60,00 R$ 84,00 R$ 60,00
SBC Undergrad. Student R$ 50,00 R$ 70,00 R$ 50,00

Paper Submission

Instructions for authors

  • The manuscript must be submitted electronically, as a PDF file.
  • The conference accepts articles written in English or Portuguese, but the manuscript title and abstract must be written in English. Only articles written in English will be published in IEEE-CPS.
  • The abstract should contain no more than 150 words, and the manuscript total length should not exceed 6 pages.
  • The manuscripts should be formatted using the IEEE templates, which are blind-submission review-formatted templates ( link for the templates ).

Submission

Authors can now submit papers to WVC 2017 using JEMS.

Policies

  • WVC 2017 reviewing is double blind, in that authors do not know the names of the area chair/reviewers of their papers, and area chairs/reviewers do not know the names of the authors.
  • Avoid providing information that may identify the authors in the acknowledgments (e.g., co-workers and grant IDs).
  • Avoid providing links to websites that identify the authors. Violation of any of these guidelines will lead to rejection without review.
  • By submitting a manuscript to WVC 2017, the authors guarantee that it has not been previously published (or accepted for publication) in substantially similar form.
  • It is the authors' responsibility to ensure that all authors on their paper have registered their conflicts into JEMS website. Conflicts are needed to resolve assignments to both reviewers and area chairs.

Keynote Speakers

John Tsotsos

John Tsotsos is Distinguished Research Professor of Vision Science at York University. He received his doctorate in Computer Science from the University of Toronto. After a postdoctoral fellowship in Cardiology at Toronto General Hospital, he joined the University of Toronto on faculty in Computer Science and in Medicine. In 1980 he founded the highly respected Computer Vision Group at the University of Toronto, which he led for 20 years. He was recruited to move to York University in 2000 as Director of the Centre for Vision Research. He has been a Canadian Heart Foundation Research Scholar (1981-83), a Fellow of the Canadian Institute for Advanced Research (1985-95) and Canada Research Chair in Computational Vision (2003-2017). He has received many awards and honours including several best paper awards, the 2006 Canadian Image Processing and Pattern Recognition Society Award for Research Excellence and Service, the 1st President’s Research Excellence Award by York University on the occasion of the University’s 50th anniversary in 2009, the 2011 Geoffrey J. Burton Memorial Lectureship from the United Kingdom's Applied Vision Association for significant contribution to vision science. He was elected as Fellow of the Royal Society of Canada in 2010 and was awarded its 2015 Sir John William Dawson Medal for sustained excellence in multidisciplinary research, the first computer scientist to be so honoured. Over 125 trainees have passed through his lab. His current research focuses on a comprehensive theory of visual attention in humans. A practical outlet for this theory forms a second focus, embodying elements of the theory into the vision systems of mobile robots.

Presentation Info

Title: Attention is More Important for AI than you Think.
Abstract
Although attentive capabilities have been effectively employed in AI and cognitive systems for decades, there is little agreement on how to characterize their scope or power, let alone their rationale. The dominant view is that attention is necessary to deal with the capacity limits of processing whether in the brain or in machines, but is this all there is? Here, it is claimed that an additional role is perhaps more important. Attention is what enables the functional generalization of brain processes by dynamically tuning computations for the task of the moment, making them not only more selective to task-relevant elements but also less sensitive to interference. The challenge is how to include such processes into machine vision and AI systems and some of our steps in these directions will be briefly presented.

Cosimo Distante

Cosimo Distante received the degree in Computer Science in 1997 at the University of Bari and PhD in Engineering in 2001 at University of Salento. In 1998 he has been visiting researcher at the Computer Science Department of the University of Massachusetts at Amherst MA (USA) where has worked in the context of Perceptual Robotics and Artificial Neural Networks systems. He served as a teaching Assistant of the Artificial Intelligence Class of the University of Massachusetts. In 2001 he joined the Italian National Research Council CNR leading the signal and image processing laboratory. In 2009 he joined the National Institute of Optics. Since 2003 Dr. Distante is contract professor on “Image Processing” and “Pattern Recognition” in computer engineering at the University of Salento Italy. In 2011, Dr. Distante has been awarded with the national innovation Prize working capital PNI-Cube with the project Taggalo. In 2012 he has been awarded from the Senate President and Minister of Education University and Research of the Republic of Italy with the “Prize of the Prizes” for Innovation. Currently he is with the Institute of Applied Sciences and Intelligent systems ISASI “ScienceAPP” of the CNR. He chaired VAAM (Video analytics for Audience Measurement workshop), ACIVS 2016 (Int. Conf. on advanced concepts for intelligent vision systems) and IEEE AVSS 2017 (Int. Conf. on Advanced Video and Signal Based surveillance). His main research interests are in the field of computer vision and pattern recognition applied to: audience measurements, security and surveillance, robotics, medical imaging and manufacturing.

Presentation Info

Title: Face analysis in the wild and on the move in several domains.
Abstract
Face analysis has been investigated for over 50 years, especially biometric recognition in the forensics and security sectors. However, it is still a hot topic of scientific research due to the requirements of extracting facial traits in highly challenging conditions such as variations in: illuminations, poses, aging, occlusions, expressions, resolution etc. Beside the face recognition topic and the latest demanding of extracting “biometrics on the move” for critical infrastructure surveillance, face analysis is of paramount importance to estimate social interaction and social behaviour in other contexts. I will show the activity carried out at CNR at border control for biometric on the move extraction, as well as in the health and retail sectors. In fact, in the health sector, social interaction can be measured by face analysis for human robot and human machine interactions in order to understand and measure human social skills. In the retail space, face analysis allows to understand engagement of shoppers with the product space by analysing soft biometrics and expressions in highly challenging conditions.

Workshop Program

Time/Date Monday, Oct. 30 Tuesday, Oct. 31 Wednesday, Nov. 1
8:00 - 9:30 Checkin and on-site
registration
Minicourse Minicourse
9:30 - 10:30 Opening Cerimony
10:00 - 10:30 Coffee Break
10:30 - 12:00 Keynote Speaker 1 Oral Session 3 Keynote Speaker 2
12:00 - 14:00 Lunch
14:00 - 15:30 Oral Session 1 Oral Session 4 Oral Session 6
15:30 - 16:00 Coffee Break
16:00 - 17:15 Poster Session 1 Poster Session 2 Conference Meeting,
Awards Ceremony and
Closing Ceremony
17:15 - 18:00 Oral Session 2 Oral Session 5
19:00 - 22:00 Conference Dinner

Mini Course

Title: CUDA Programming
Professor: Prof. Dr. Ricardo Farias
Minicourse Contents (Portuguese):
Com um grande poder de processamento paralelo, as placas gráficas, que possuem GPUs (Graphics Processing Unit), como as placas da NVidia, tornaram-se de imenso interesse para acelerar aplicações em áreas diversas como processamento de imagens, equações diferenciais, CFD, entre outras. Neste mini-curso estudamos tanto os detalhes mais importantes da arquitetura das GPUs, como algumas técnicas necessárias para sua programação eficiente. Mostraremos algumas aplicações básicas de processamento de imagens como estudo de caso.

Prof. Dr. Ricardo Farias

Ricardo Farias, is bachelor's at Bacharelado em Fisica from Universidade Federal Fluminense (1984), master's at Computer Science from Universidade Federal do Rio de Janeiro (1996) and doctorate at Applied Mathematics And Statistics from State University Of New York At Stony Brook (2001). Has experience in Computer Science, acting on the following subjects: volume rendering, scientific visualization, visualization, volume visualization and high performance computing.
Session/Time Pattern recognition and applications
Oral Session 1
Monday 14:00-15:30
A computer vision system for soybean diseases recognition using UAVs: preliminary results
Human Epithelial type 2 (HEp-2) cell classification by using a Multiresolution Texture Descriptor
Comparison between traditional texture methods and deep learning descriptors for detection of nitrogen deficiency in maize crops
HEp-2 cell image classification based on Convolutional Neural Networks
Combining Deep Learning and Multi-Class Discriminant Analysis for Granite Tiles Classification
Session/Time Feature extraction, descriptors and shape analysis
Oral Session 2
Monday 17:15-18:00
Automated Feature Extraction from Breast Masses using Multiscale Fractal Dimension
A novel method for shape analysis based on statistics of Euclidean distances
Session/Time Image segmentation and texture analysis
Oral Session 3
Tuesday 10:30-12:00
A comparison between two approaches to segment overlapped chromosomes in microscopy images
Multi-class Segmentation of Satellite Images by Color Mixture and Neural Network
Exploring fuzzy numbers for image texture analysis
Segmentation of the prostate gland in images using prior knowledge and level set method
A novel method for fingerprint image segmentation based on Adaptative Gabor filters
Fully Convolutional Neural Network for Occular Iris Semantic Segmentation
Session/Time Image/video analysis
Oral Session 4
Tuesday 14:00-15:30
Automatic Vehicle Count in Multiple Climatic and Illumination Conditions
Aerial image analysis for estimation of ground traversal difficulty in robot navigation
A Replacement Based Video De-interlacing Technique by Feathering Effect Detection and Artifact Agglomeration Index
Image Colorization with Neural Networks
A Study of Swimmers Detection in Beach Images
Session/Time SLAM, Visual Odometry and Motion Estimation
Oral Session 5
Tuesday 17:15-18:00
Backward Motion for Estimation Enhancement in Sparse Visual Odometry
Tracking Spatially Distributed Features in KLT Algorithms for RGB-D Visual Odometry
Accuracy Analysis of Augmented Reality Markers for Visual Mapping and Localization
Session/Time Biometrics
Oral Session 6
Wednesday 14:00-15:30
Optimizing a Homomorphic Filter for Illumination Compensation In Face Recognition Using Population-based Algorithms
CNNFusion-Gender: fusion facial parts methodology for gender classification in the wild
Precise eye localization using the new multiscale high-boost Weber local filter
Biometric Recognition based on Fingerprint: A Comparative Study
Analysis of Wavelet Families for Face Recognition
Biometric iris classification when the eyes pupil reacts to light

List of accepted papers for poster session 1:

01. Facial Recognition in Digital Images using Local Binary Pattern Methods
02. Análise Comparativa da janela LBP para segmentação de Fissuras Pulmonares
03. Biometria Facial para Controle de Acesso Usando Medidas de Textura LBP e Redes Neurais ELM
04. Taking the Most of Existing Image Descriptors: A Hybrid Approach
05. Facial Biometrics Using SIFT/SURF in Comparison with Eigenfaces
06. A Novel Approach for Fingerprint Singularities Detection
07. Automatic segmentation of the human bone vascular network
08. Normalization Methods Analysis Applied to Face Recognition
09. Binarization Algorithms Applied to Chromosomes Image Segmentation
10. Classification of E-commerce-related Images Using Hierarchical Classification with Deep Neural Networks
11. Face Recognition Based on a Multi-Scale Local Mapped Pattern Method
12. Color Texture Classification by using Opponent Color and Local Mapped Pattern
13. A Comparative Analysis of the Evolution of the IBM Watson's Visual Recognition API on Android
14. Methods of detecting and reconstructing partial occlusions in face images: Systematic Literature Review
15. Edge Detection Based on Receptive Field

List of accepted papers for poster session 2:

16. A Multi-level Thresholding Method Based on Improved Group Search Optimization and Otsu
17. A New Approach to Ripplet Transform-Based Texture Descriptor for Breast Lesions Classification
18. Stereo vision methods: from development to the evaluation of disparity maps
19. Defoliation Level Estimation using Convolutional Neural Networks and Data Augmentation
20. A Restricted Boltzmann Machine-Based Approach for Robust Dimensionality Reduction
21. Waveletfaces and Linear Regression Classification for Face Recognition
22. A Method for Automatic Correction of Multiple-Choice Tests
23. Definition of Management Zones through Image Processing for Precision Agriculture
24. Improving the definition of markers for the transformed watershed combining h-maxima transform and convex-hull
25. A Comparison of Texture and Shape Descriptors for Iris Location based on a Sliding Window Approach
26. Remote sensing for pasture areas monitoring through spectral image analysis
27. Saccharomyces cerevisiae yeast counting through image processing
28. Classification of the maturation period of table tomatoes using color images and neural networks
29. Improved Non Local Means algorithm using DCT-based K-means clustering
30. Leukocyte Segmentation and Classification using Computational Vision

General Information

  • Your badge is personal and not transferable. Please use your badge to access all activities of the workshop;
  • Please turn off your mobile phones or switch them to silent/vibrate mode during all scientific activities;
  • All certificates will be sent via e-mail after the conference;
  • The WVC proceedings will be published online soon after the workshop. Only papers presented during the workshop will be published in the final version of the proceedings;
  • The ticket for the Conference Dinner must be purchased at the event’s office;
  • If you need a registration receipt please refer to the event’s office.

Author and Presenter Information

Oral Presenters
  • Each oral presentation will have 10 minutes + 5 minutes for questions;
  • Your presentation can be in Portuguese, but your slides should be written in English;
  • Please refer to the workshop program to check the day and time of your presentation;
  • Please make sure to upload your presentation to the computer in the meeting room on the day of your presentation. The best time is before the first session of the day or during breaks.
Poster Presenters
  • Authors of accepted papers for poster presentations are required to bring a printed (hardcopy) poster for displaying during the Workshop;
  • At least one author should be available at the poster to discuss the work during the scheduled poster session(s);
  • The posters themselves have no predefined formatting, but dimensions may not exceed 90cm (width) x 120cm (height);
  • Due to space limitation, power plugs and tables won't be available at the poster session. Thus, if you plan to show live demos or videos, plan accordingly. Posters presentations are hard-copy (paper/poster) format only;
  • Your presentation can be in Portuguese, but your poster should be written in English;
  • Please hang your poster in the panel with the same number provided by the WVC program;
  • Please refer to the workshop program to check the day and time of your presentation;
  • Posters authors are required (1) to display the poster during the second coffee break of the day of your session 2) attend your Poster Session to answer questions;
  • Remember that during your poster presentation you will have the opportunity to discuss your research with more details. Thus, prepare the best poster you possibly can, aiming at both attracting attention of the readers and having enough material to answer their questions.

Best Work Awards

Best Paper Award

  • A computer vision system for soybean diseases recognition using UAVs preliminary results
    • Everton Castelão Tetila
    • Bruno Bransoli Machado
    • Hemerson Pistori and Gercina Gonçalves
  • Backward Motion for Estimation Enhancement in Sparce Visual Odometry
    • Fabio Pereira
    • Altamiro Susin
    • Joel Luft
    • Arthur Sofiatti
    • Gustavo Ilha
  • Biometric iris classification when the eyes pupil reacts to light
    • Jones Mendonça de Souza
    • Adilson Gonzaga

Best Poster Award

  • A Comparison of Texture and Shape Descriptors for Iris Location based on a Sliding Window Approach
    • Evair Severo
    • David Menotti
  • Improving the definition of markers for the transformed watershed combining h-maxima transform and convex-hull
    • Welton Felipe Gonçalves
    • Rodrigo Júnior Rodrigues
    • João Mari
  • Waveletfaces and Linear Regression Classification for Face Recognition
    • João Antônio Chagas Nunes
    • Fabrício Ferreira
    • Tiago de Carvalho

Venue

Event Location and Hotel Services

In 2017, WVC will take place at the Federal University of Rio Grande do Norte (UFRN), Natal, Rio Grande do Norte, Brazil. official information about the university can be found at its official website. The event will take place at the CCET's Auditorium, check the map for directions.
Natal is a touristic city, we invite you to enjoy the city attractions during the conference. You can find more touristic information at:


Some indicated hotels can be found below, however, there are several other hotels listed on the internet.

Local Map to the Event's Location

Transport

Since the Event will take place in the campus, any bus line that has "Campus" or "UFRN" labeled could be used to reach the conference place. The main bus Line are:

  • Bus 10-29 – Nova Natal/Campus/Via Nova Descoberta/Soledade II - Reunidas
  • Bus 63 – Felipe Camarão/Campus - Conceição
  • Bus 30 – Felipe Camarão/Pirangi - Via Candelária - Conceição
  • Bus 31 – Felipe Camarão/Pirangi - Via Campus

In addition, buses that stop on Via Direta Mall (Shopping Via Direta), could be used to go to the event by using the campus bus Line. The bus 588 - Circular UFRN stops at the crossing of "Av. Passeio das Rosas" with "Rua dos Gerânios".

Organization

Local Organizing Committee

  • Bruno Marques Ferreira da Silva (UFRN) – CHAIR
  • Bruno Motta de Carvalho (UFRN) – CO-CHAIR
  • Luiz Marcos Garcia Gonçalves (UFRN) – HONORARY CHAIR
  • Anderson Abner de Santana Souza (UERN)
  • Júlio César Paulino de Melo (UFRN)
  • Justo Emilio Alvarez Jácobo (UFPE)
  • Orivaldo Vieira de Santana Júnior (UFRN)
  • Rafael Beserra Gomes (UFRN)
  • Raissa Tavares Vieira (UFRN)
  • Tiago Pereira do Nascimento (UFPB)

Steering Committee

  • Marcelo Andrade da Costa Vieira (USP) – CHAIR
  • Aparecido Nilceu Marana (UNESP)
  • Evandro Luís Linhari Rodrigues (USP)
  • Hemerson Pistori (UCDB)
  • Marco Antônio Piteri (UNESP)
  • Mauricio Cunha Escarpinati (UFU)
  • Mauricio Marengoni (Mackenzie)

Program Committee

  • Adilson Gonzaga (USP)
  • Ana Claudia Martinez (UFU)
  • André Backes (UFU)
  • Aparecido Nilceu Marana (UNESP)
  • Aristófanes Silva (UFMA)
  • Aylton Pagamisse (UNESP)
  • Bruno Carvalho (UFRN)
  • Carlos Thomaz (FEI)
  • Chidambaram Chidambaram (UDESC)
  • Cristiane Ferreira (UFG)
  • Cristina Vasconcelos (UFF)
  • Daniel Abdala (UFU)
  • Danilo Eler (Unesp)
  • Deborah Fernandes (UFGO)
  • Denis Salvadeo (UNESP)
  • Dibio Leandro Borges (UNB)
  • Emerson Pedrino (UFSCar)
  • Evandro Luis Linhari Rodrigues(USP)
  • Gilson Giraldi (LNCC)
  • Gustavo B. Borba (UTFPR)
  • Helio Pedrini (UNICAMP)
  • Hemerson Pistori (UCDB)
  • Herman Gomes (UFCG)
  • Iális Paula Jr (UFC)
  • Ines Boaventura (USP)
  • Isabel Manssour (PUC-RS)
  • Jacob Scharcanski (UFRGS)
  • Jacques Facon (PUC-PR)
  • Jander Moreira (UFSCar)
  • Silvia Martini Rodrigues (UMC)
  • Thiago Pirola Ribeiro (UFU)
  • Joao Papa (UNESP)
  • José Saito (UFSCar)
  • José Eduardo Castanho (UNESP)
  • José Roberto Nogueira (UNESP)
  • Julio Melo (UFRN)
  • Julio Cesar Nievola (PUC-PR)
  • Jurandy Almeida (UNIFESP)
  • Leandro Neves (UNESP)
  • Leandro Oliveira (UFGO)
  • Leonardo Matos (UFS)
  • Lucas Ferrari de Oliveira (UFPR)
  • Luciano Lulio (USP)
  • Luciano Silva (UFPR)
  • Luiz Marcos Garcia Gonçalves (UFRN)
  • Marcelo Vieira (USP)
  • Marcelo do Nascimento (UFU)
  • Marcio Alexandre Marques (UNESP)
  • Mauricio Cunha Escarpinati (UFU)
  • Mauricio Galo (UNESP)
  • Maurilio Boaventura (UNESP)
  • Maximiliam Luppe (USP)
  • Moacir Ponti (USP)
  • Murillo Homem (UFSCar)
  • Olga Bellon (UFPR)
  • Orivaldo Santana Jr. (UFRN)
  • Paulo Miranda (USP)
  • Paulo Ambrósio (UESC)
  • Rafael Beserra Gomes (UFRN)
  • Raissa Vieira (USP)
  • Ronaldo Costa (UFG)
  • Tiago Nascimento (UFPB)
  • William Schwartz (UFMG)

Sponsors