Joint IAPR International Workshops on
Structural and Syntactic Pattern Recognition (SSPR 2012)
and Statistical Techniques in Pattern Recognition (SPR 2012)
Miyajima-Itsukushima, Hiroshima, 7th-9th November, 2012.

Paper Submission

The maximum length is 9 pages in LNCS style. The preferred way to typeset your paper is to use LaTeX; the use of MS Word is strongly discouraged.

  • Abstract Deadline
  • 10th July 2012 JST 23:59 (JST=UTC(GMT)+9).

  • Submission Deadline
  • 13th July 2012 JST 23:59 (JST=UTC(GMT)+9).

  • We do not accept any submission by e-mail. Please submit papers using submission link described above.
    The final camera-ready manuscripts should be at most 9 pages in LNCS style. We do not prepare any over-page charge system. Even if the paper is accepted by reviewers, the final manuscript whichviolates this regulation will not be included in the proceedings.

    Visa to Japan

    For Visa addministration by JTB office, 2,000JPY is added to your registration fee. Visa addministration will start after your payment will be confermed.

    Guid to Japan Visa.

    Submission Policy

    The review process is single blind as to fit with ICPR. We appreciate that because of the proximity of the ICPR deadline, authors will have a limited time to undertake the additional work to develop new papers for submission SSPR. We are happy to consider papers that report work that is partially overlapped with an ICPR submission provided that:
    a) The SSPR papers contain at least 50% of additional material that is substantially different from the ICPR (or previously submitted) paper. This might include a) additional theory, proofs etc, b) additional experimentation or detailed comparison, c) deeper analysis. It does not include ephemeral or insubstantial material, such as additional literature review, discussion or bibliography.
    b) The authors declare the existence of a related ICPR paper ID and title in the online submission system, and briefly summarize the differences in the comments box on submission.
    If we detect substantially similar work that does not follow these guidelines, we will automatically reject it.

    Important Notice

    Each accepted paper must be registered by one of the authors before submission of the final manuscript.
    - Please note that at least one of the authors must register for the workshop paying regular registration fees (not student fee) before submitting the camera-ready copy of his/her manuscript(s). Papers submitted without registration will not be included in the conference program or in the proceedings. Please note that this fee will not be refunded even if the registration is cancelled.
    - According to IAPR's policy, should an author have more than one paper accepted, only one registration is required for publication although other authors are encouraged to register and participate in the conference.
    The organizers of S+SSPR2012 wish to obtain your prior understanding that we will not be held liable for any damages incurred by participants (such as participating fees, transportation expenses, lodging expenses) as a result of a partial revision or cancellation of all or any of the content of the meeting that occurs due to reasons beyond our control, such as act of providence, outbreak of an infectious disease, or suspension of services by the venue and transportation networks.

    SSPR Topics

    • Structural Matching and Syntactic Method
    • Probabilistic and Stochastic Structural Models
    • Graphical Models and Graph-Based Models
    • Spectral Methods for Graph Based Representations
    • Kernel Methods for Structured Data
    • Structural Learning in Spatial or Spatio-Temporal Signals
    • SSPR Methods in Text, Document, Shape Image, Video and Multimedia Signal Analysis
    • Intelligent Sensing Systems
    • Novel Applications

    SPR Topics

    • Multiple Classifiers and Large Margin Classifiers
    • Density Estimation and Model Selection
    • Ensemble Methods, Bayesian Methods and Kernel Methods
    • Independent Component Analysis and Compressed Representation
    • Unsupervised and Semi-Supervised Learning
    • Linear and Non-linear Manifold Learning
    • Gaussian Processes
    • Dimensionality Reduction
    • Cluster Analysis
    • Data Visualization
    • Hybrid Methods
    • Comparative Studies
    • SPR Methods in Text, Document, Shape Image, Video and Multimedia Signal Analysis
    • Novel Applications

    Invited Lecture

    George Nagy,


    The accuracy of automated classification (labeling) of single patterns, especially printed, hand-printed, or handwritten characters, leveled off some time ago. Further gains in accuracy depend on classifying unordered sets or ordered sequences of patterns. Linguistic context, already widely used, relies on 1-D lexical and syntactic constraints in plain text. Style-constrained classification exploits the shape-similarity of sets of same-source (isogenous) characters of either the same or different classes. 2-D structural and relational constraints are necessary for understanding tables and forms. Applications of pattern recognition that do not exceed the limits of human sensory and cognitive systems can benefit from green interaction whereby operator corrections are incorporated into the classifier.


    Kenichi Kanatani,

    Optimization Techniques for Geometric Estimation:
      Beyond Minimization

    We overview techniques for optimal geometric estimation from noisy observations for computer vision applications. We first describe estimation techniques based on minimization of given cost functions: least squares, maximum likelihood, which includes reprojection error minimization as a special case, and Sampson error minimization. We then formulate estimation techniques not based on minimization of any cost function: iterative reweight, renormalization, and hyper-renormalization. Showing numerical examples, we conclude that hyper-renormalization is robust to noise and currently is the best method.

    Ales Leonardis,

    Hierarchical Compositional Representations of Object Structure

    Visual categorisation has been an area of intensive research in the vision community for several decades. Ultimately, the goal is to efficiently detect and recognize an increasing number of object classes. The problem entangles three highly interconnected issues: the internal object representation, which should compactly capture the visual variability of objects and generalize well over each class; a means for learning the representation from a set of input images with as little supervision as possible; and an effective inference algorithm that robustly matches the object representation against the image and scales favorably with the number of objects. In this talk I will present our approach which combines a learned compositional hierarchy, representing (2D) shapes of multiple object classes, and a coarse-to-fine matching scheme that exploits a taxonomy of objects to perform efficient object detection. Our framework for learning a hierarchical compositional shape vocabulary for representing multiple object classes takes simple contour fragments and learns their frequent spatial configurations. These are recursively combined into increasingly more complex and class-specific shape compositions, each exerting a high degree of shape variability. At the top-level of the vocabulary, the compositions represent the whole shapes of the objects. The vocabulary is learned layer after layer, by gradually increasing the size of the window of analysis and reducing the spatial resolution at which the shape configurations are learned. The lower layers are learned jointly on images of all classes, whereas the higher layers of the vocabulary are learned incrementally, by presenting the algorithm with one object class after another. However, in order for recognition systems to scale to a larger number of object categories, and achieve running times logarithmic in the number of classes, building visual class taxonomies becomes necessary. We propose an approach for speeding up recognition times of multi-class part-based object representations. The main idea is to construct a taxonomy of constellation models cascaded from coarse-to-fine resolution and use it in recognition with an efficient search strategy. The structure and the depth of the taxonomy is built automatically in a way that minimizes the number of expected computations during recognition by optimizing the cost-to-power ratio. The combination of the learned taxonomy with the compositional hierarchy of object shape achieves efficiency both with respect to the representation of the structure of objects and in terms of the number of modeled object classes. The experimental results show that the learned multi-class object representation achieves a detection performance comparable to the current state-of-the-art flat approaches with both faster inference and shorter training times.

    Conjunction with:

    A satellite event of the 21st International Conference on Pattern Recognition. ICPR 2012.

    Call for Paper

    Technical Committee 1 and Technical Committee 2 of International Assocition for Pattern Recognition (IAPR) jointly with Special Interest Group of Pattern Recognition and Media Understanding of the Institute Electronics, Information and Cmmunication Engineers of Japan (SIG-PRMU, IEICE) organize S+SSPR 2012. The workshop will be jointly hosted Hiroshima University, Hokkaido University, Tohoku University.


    • Co-organizers:
    • Atsushi Imiya (IMIT, Chiba University, Japan)
    • Mineichi Kudo (Hokkaido University, Japan)
    • Georgy L. Gimel'farb (University of Auckland, New Zealand)
    • Keiji Yamada (NEC Corporation, Japan)

    • Co-Program Chairs
    • Arjan Kuijper (Fraunhofer IGD & TU Darmstadt, Germany)
    • Edwin Hancock (University of York, UK)
    • Shinichiro Omachi (Tohoku University, Japan)
    • Terry Windeatt (University of Surrey, UK)

    • Local Organizers
    • Tomoya Sakai (Nagasaki University, Japan)
    • Yukihiko Yamashita (Tokyo Institute of Technology, Japan)
    • Ken-ichi Maeda (Toshiba, Japan)
    • Takio Kurita (Hiroshima University, Japan)
    • Toru Tamaki (Hiroshima University, Japan)
    • Heitoh Zen (IMIT, Chiba University, Japan)
    • Kazuhiko Kawamoto (IMIT, Chiba University, Japan)
    • Yoshihiko Mochizuki (Waseda University, Japan)


    PDF in LNCS style 9 pages. Final camera-ready due of the accepted papers is 28th August (GMT 12:00). If the final paper would not be uploaded until 28th August (GMT 12:00), the paper would not be contained in the final workshop proceedings volume from Springer-Verlag.

    Important Dates

      Submission deadline 6th July, 2012
      Author notification 24th August, 2012
      Camera-ready 28th August, 2012
      Workshop 7-9th November, 2012