Erdem Yörük

Shape-based hand recognition

The problem of person recognition and verification based on their hand images has been addressed. The system is based on the images of the right hands of the subjects, captured by a flatbed scanner in an unconstrained pose at 45 dpi. In a preprocessing stage of the algorithm, the silhouettes of hand images are registered to a fixed pose, which involves both rotation and translation of the hand and, separately, of the individual fingers. Two feature sets have been comparatively assessed, Hausdorff distance of the hand contours and independent component features of the hand silhouette images. Both the classification and the verification performances are found to be very satisfactory as it was shown that, at least for groups of about five hundred subjects, hand-based recognition is a viable secure access control scheme.

Hand biometrics

The potential of hand shape and hand texture-based biometry is investigated and algorithms are developed. Feature extraction stage is preceded by meticulous registration of the deformable shape of the hand. Alternative features addressing hand shape and hand texture are compared. Independent component analysis features prove to be the best performing in the identification and verification tasks. It is shown that hand biometric devices can be built that perform reliably for a population of at least 1000. 00.

Comparative analysis of global hand appearance-based person recognition

We provide a survey of hand biometric techniques in the literature and incorporate several novel results of hand-based per- sonal identification and verification. We compare several feature sets in the shape-only and shape-plus-texture categories, empha- sizing the relevance of a proper hand normalization scheme in the success of any biometric scheme. The preference of the left and right hands or of ambidextrous access control is explored. Since the business case of a biometric device partly hinges on the longevity of its features and the generalization ability of its database, we have tested our scheme with time-lapse data as well as with subjects that were unseen during the training stage. Our experiments were con- ducted on a hand database that is an order of magnitude larger than any existing one in the literature.

A Comprehensive Statistical Model for Cell Signaling

Protein signaling networks play a central role in transcriptional regulation and the etiology of many diseases. Statistical methods, particularly Bayesian networks, have been widely used to model cell signaling, mostly for model organisms and with focus on uncovering connectivity rather than inferring aberrations. Extensions to mammalian systems have not yielded compelling results, due likely to greatly increased complexity and limited proteomic measurements in vivo. In this study, we propose a comprehensive statistical model that is anchored to a predefined core topology, has a limited complexity due to parameter sharing and uses micorarray data of mRNA transcripts as the only observable components of signaling. Specifically, we account for cell heterogeneity and a multilevel process, representing signaling as a Bayesian network at the cell level, modeling measurements as ensemble averages at the tissue level, and incorporating patient-to-patient differences at the population level. Motivated by the goal of identifying individual protein abnormalities as potential therapeutical targets, we applied our method to the RAS-RAF network using a breast cancer study with 118 patients. We demonstrated rigorous statistical inference, established reproducibility through simulations and the ability to recover receptor status from available microarray data.

A physical model for DT-MRI based connectivity map computation

In this study we address the problem of extracting a robust connectivity metric for brain white matter. We defined the connectivity problem as an energy minimization task, by associating the DT-field to a physical system composed of nodes and springs, with their constants defined as a function of local structure. Using a variational approach we formulated a fast and stable map evolution, which utilizes an anisotropic kernel smoothing scheme equivalent to a diffusion PDE. The proposed method provides connectivity maps that correlate with normal anatomy on real patient data.

Person authentication based on hand shape

A system has been developed for person identification based on hand images. The images of the left hand of the subjects are captured by a flatbed scanner in an unconstrained pose. The silhouettes of hands are registered to a fixed pose, which involves both rotation and translation of the hand and, separately, of the individual fingers. Independent component features of the hand silhouette images are used for recognition. The classification performance is found to be very satisfactory and it is shown that, at least for groups of one hundred subjects, hand-based recognition becomes a viable and secure access control scheme.

Context-aware hybrid classification system for fine-grained retail product recognition

We present a context-aware hybrid classification system for the problem of fine-grained product class recognition in computer vision. Recently, retail product recognition has become an interesting computer vision research topic. We focus on the classification of products on shelves in a store. This is a very challenging classification problem because many product classes are visually similar in terms of shape, color, texture, and metric size. In shelves, same or similar products are more likely to appear adjacent to each other and displayed in certain arrangements rather than at random. The arrangement of the products on the shelves has a spatial continuity both in brand and metric size. By using this context information, the co-occurrence of the products and the adjacency relations between the products can be statistically modeled. The proposed hybrid approach improves the accuracy of context-free image classifiers such as Support Vector Machines (SVMs), by combining them with a probabilistic graphical model such as Hidden Markov Models (HMMs) or Conditional Random Fields (CRFs). The fundamental goal of this paper is using contextual relationships in retail shelves to improve the classification accuracy by executing a context-aware approach.

DT-MRI Connectivity and/or Tractography?: Two New Algorithms

Abstract Diffusion Tensor MRI (DTI) is a special MR imaging technique where the second order symmetric diffusion tensors that are correlated with the underlying fi-brous structure (eg. the nerves in brain), are computed based on DiffusionWeighted MR Images (DWI). DTI is the only in vivo imaging technique that provides information about the network of nerves in brain. The computed tensors describe the local diffusion pattern of water molecules via a 3D Gaussian distribution in space. The most common analysis and visualization technique is tractography, which is a numerical integration of the principal diffusion direction (PDD) that attempts to reconstruct fibers as streamlines. Despite its simplicity and ease of interpretation, tractography algorithms suffer from several drawbacks mainly due to ignoring the information in the underlying spatial distribution but using the PDD only. An alternative to tractography is connectivity which aims at computing probabilistic connectivity maps based on the above mentioned 3D Gaussian distribution as described by the DTI data. However, the computational cost is high and the resulting maps are usually hard to visualize and interpret. This chapter discusses these two approaches and introduces two new tractography techniques, namely the Lattice-of-Springs (LoS) method that exploits the connectivity approach and the Split & Merge Tractography (SMT) that attempts to combine the advantages of tractography and connectivity.

Retail product recognition with a graphical shelf model

Recently, retail product recognition has become an interesting computer vision research topic. The classification of products on shelves is a very challenging classification problem because many product classes are visually similar in terms of shape, color, texture, and metric size. In shelves, same or similar products are more likely to appear adjacent to each other and displayed in certain arrangements rather than at random. The arrangement of the products on the shelves has a spatial continuity both in brand and metric size. By using this context information, the co-occurrence of the products and the adjacency relations between the products can be statistically modeled. In this work, we present a context-aware hybrid classification system for the problem of fine-grained product class recognition. The proposed hybrid approach improves the accuracy of the context-free image classifiers, by combining them with a probabilistic graphical model based on Hidden Markov Models. The fundamental goal of this paper is to use contextual relationships in retail shelves to improve accuracy of the product classifier.

An efficient Hough transform for multi-instance object recognition and pose estimation

Generalized Hough transform, when applied to object detection, recognition and pose estimation, can be susceptible to spurious voting depending on the Hough space to be used and hypotheses to be voted. This often necessitates additional computational steps like non-maxima suppression and geometric consistency checks, which can be costly and prevent voting based methods from being precise and scalable for large numbers of target classes and crowded scenes. In this paper, we propose an efficient and refined Hough transform for simultaneous detection, recognition and exact pose estimation, which can efficiently accommodate up to multiple tens of co-visible query instances and multiple thousands of visually similar classes. Specifically, we match SURF features from a given query image to a database of model features with known poses, and in contrast to existing techniques, for each matched pair, we analytically compute a concise set of 6 degrees-of-freedom pose hypotheses, for which the geometric relationship of the correspondence remains invariant. We also introduce an indirect but equivalent representation for those correspondence-specific poses, termed as feature aligning affine transformations, which results in a Hough voting scheme as cheap and refined as line drawing in raster grids. Owing to minimized voting redundancy, we can obtain a very sparse and stable Hough image, which can be readily used to read off instances and poses without dedicated steps of non-maxima suppression and geometric verification. Experimented on an extensive Grocery Products dataset, our method significantly outperforms the sate-of-the-art with near real time overall cost.