A neural implementation of the Hough transform and the advantages of explaining away

The Hough transform (HT) is widely used for feature extraction and object detection. However, during the HT individual image elements vote for many possible parameter values. This results in a dense accumulator array and problems identifying the parameter values that correspond to image features. This article proposes a new method for implementing the voting process in the HT. This method employs a competitive neural network algorithm to perform a form of probabilistic inference known as "explaining away". This results in a sparse accumulator array in which the parameter values of image features can be more accurately identified. The proposed method is initially demonstrated using the simple, prototypical, task of straight line detection in synthetic images. In this task it is shown to more accurately identify straight lines, and the parameter of those lines, compared to the standard Hough voting process. The proposed method is further assessed using a version of the implicit shape model (ISM) algorithm applied to car detection in natural images. In this application it is shown to more accurately identify cars, compared to using the standard Hough voting process in the same algorithm, and compared to the original ISM algorithm.

[1]  Bok-Suk Shin,et al.  Accurate and Robust Line Segment Extraction Using Minimum Entropy With Hough Transform , 2015, IEEE Transactions on Image Processing.

[2]  Michael W. Spratling.  Predictive Coding as a Model of Response Properties in Cortical Area V1 , 2010, The Journal of Neuroscience.

[3]  Luc Van Gool,et al.  Scalable multi-class object detection , 2011, CVPR 2011.

[4]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[5]  Bernt Schiele,et al.  Robust Object Detection with Interleaved Categorization and Segmentation , 2008, International Journal of Computer Vision.

[6]  U. Ernst,et al.  Perceptual Inference Predicts Contextual Modulations of Sensory Responses , 2012, The Journal of Neuroscience.

[7]  Michael W. Spratling.  Classification using sparse representations: a biologically plausible approach , 2013, Biological Cybernetics.

[8]  Juergen Gall,et al.  Class-specific Hough forests for object detection , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[9]  Michael W. Spratling,et al.  Unsupervised Learning of Overlapping Image Components Using Divisive Input Modulation , 2009, Comput. Intell. Neurosci..

[10]  Yoshihisa Shinagawa,et al.  Accurate and robust line segment extraction by analyzing distribution around peaks in Hough space , 2003, Comput. Vis. Image Underst..

[11]  Michael W. Spratling.  Predictive coding as a model of biased competition in visual attention , 2008, Vision Research.

[12]  Dan Roth,et al.  Learning a Sparse Representation for Object Detection , 2002, ECCV.

[13]  Michael W. Spratling,et al.  Pre-synaptic lateral inhibition provides a better architecture for self-organizing neural networks. , 1999, Network.

[14]  Michael W. Spratling,et al.  Image Segmentation Using a Sparse Coding Model of Cortical Area V 1 , 2013 .

[15]  David G. Lowe,et al.  Multiclass Object Recognition with Sparse, Localized Features , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  Xiaoping Lou,et al.  Invariant Hough Random Ferns for Object Detection and Tracking , 2014 .

[17]  A. Yuille,et al.  Object perception as Bayesian inference. , 2004, Annual review of psychology.

[18]  Christoph H. Lampert,et al.  Beyond sliding windows: Object localization by efficient subwindow search , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[19]  B. Schiele,et al.  Combined Object Categorization and Segmentation With an Implicit Shape Model , 2004 .

[20]  Luc Van Gool,et al.  Hough Forests for Object Detection, Tracking, and Action Recognition , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  E. R. Davies.  Application of the generalised Hough transform to corner detection , 1988 .

[22]  N. Goodwin,et al.  Learning to Detect Objects in Images via a Sparse, Part-Based Representation , 2004 .

[23]  Michael W. Spratling.  Predictive coding as a model of the V1 saliency map hypothesis , 2012, Neural Networks.

[24]  Björn Stenger,et al.  Demisting the Hough Transform for 3D Shape Recognition and Registration , 2014, International Journal of Computer Vision.

[25]  S. Denéve,et al.  Neural processing as causal inference , 2011, Current Opinion in Neurobiology.

[26]  Guido Gerig,et al.  LINKING IMAGE-SPACE AND ACCUMULATOR-SPACE: A NEW APPROACH FOR OBJECT-RECOGNITION. , 1987 .

[27]  Richard O. Duda,et al.  Use of the Hough transformation to detect lines and curves in pictures , 1972, CACM.

[28]  Haim J. Wolfson,et al.  Articulated object recognition, or: how to generalize the generalized Hough transform , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[29]  P.E. Hart,et al.  How the Hough transform was invented [DSP History] , 2009, IEEE Signal Processing Magazine.

[30]  BarinovaOlga,et al.  On Detection of Multiple Object Instances Using Hough Transforms , 2012 .

[31]  Lining Sun,et al.  A novel Hough transform method for line detection by enhancing accumulator array , 2011, Pattern Recognit. Lett..

[32]  Michael W. Spratling,et al.  Exploring the functional significance of dendritic inhibition in cortical pyramidal cells , 2003, Neurocomputing.

[33]  Dan Roth,et al.  Learning to detect objects in images via a sparse, part-based representation , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[34]  Luc Van Gool,et al.  A Hough transform-based voting framework for action recognition , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[35]  Subhransu Maji,et al.  Object detection using a max-margin Hough transform , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  Michael W. Spratling,et al.  Preintegration Lateral Inhibition Enhances Unsupervised Learning , 2002, Neural Computation.

[37]  Ryuzo Okada,et al.  Discriminative generalized hough transform for object dectection , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[38]  Michael W. Spratling.  Unsupervised Learning of Generative and Discriminative Weights Encoding Elementary Image Components in a Predictive Coding Model of Cortical Function , 2012, Neural Computation.

[39]  Rajesh P. N. Rao,et al.  Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. , 1999 .

[40]  Josef Kittler,et al.  The Adaptive Hough Transform , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[41]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[42]  Michael W. Spratling.  Image Segmentation Using a Sparse Coding Model of Cortical Area V1 , 2013, IEEE Transactions on Image Processing.

[43]  Ashok Samal,et al.  Generalized Hough transform for natural shapes , 1997, Pattern Recognit. Lett..

[44]  Luc Van Gool,et al.  Fast PRISM: Branch and Bound Hough Transform for Object Class Detection , 2011, International Journal of Computer Vision.

[45]  Michael W. Spratling.  A single functional model of drivers and modulators in cortex , 2013, Journal of Computational Neuroscience.

[46]  A. P. Georgopoulos,et al.  Neuronal population coding of movement direction. , 1986, Science.

[47]  Pushmeet Kohli,et al.  On Detection of Multiple Object Instances Using Hough Transforms , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[48]  R W Prager,et al.  Development of low entropy coding in a recurrent network. , 1996, Network.

[49]  Shimon Ullman,et al.  The chains model for detecting parts by their context , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.