Inhibition-augmented trainable COSFIRE filters for keypoint detection and object recognition

The shape and meaning of an object can radically change with the addition of one or more contour parts. For instance, a T-junction can become a crossover. We extend the COSFIRE trainable filter approach which uses a positive prototype pattern for configuration by adding a set of negative prototype patterns. The configured filter responds to patterns that are similar to the positive prototype but not to any of the negative prototypes. The configuration of such a filter comprises selecting given channels of a bank of Gabor filters that provide excitatory or inhibitory input and determining certain blur and shift parameters. We compute the response of such a filter as the excitatory input minus a fraction of the maximum of inhibitory inputs. We use three applications to demonstrate the effectiveness of inhibition: the exclusive detection of vascular bifurcations (i.e., without crossovers) in retinal fundus images (DRIVE data set), the recognition of architectural and electrical symbols (GREC’11 data set) and the recognition of handwritten digits (MNIST data set).

[1]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[2]  Edmund T. Rolls,et al.  The relative advantages of sparse versus distributed encoding for associative neuronal networks in the brain , 1990 .

[3]  D. Hubel.  Eye, brain, and vision , 1988 .

[4]  George Azzopardi,et al.  Ventral-stream-like shape representation: from pixel intensity values to trainable object-selective COSFIRE models , 2014, Front. Comput. Neurosci..

[5]  N. Chapman,et al.  Peripheral vascular disease is associated with abnormal arteriolar diameter relationships at bifurcations in the human retina. , 2002, Clinical science.

[6]  Yun Zhang,et al.  A novel biologically inspired local feature descriptor , 2014, Biological Cybernetics.

[7]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[8]  Chi-Wing Fu,et al.  Online chemical symbol recognition for handwritten chemical expression recognition , 2013, 2013 IEEE/ACIS 12th International Conference on Computer and Information Science (ICIS).

[9]  Eli Brenner,et al.  Structure learning and the Occam's razor principle: a new view of human function acquisition , 2014, Front. Comput. Neurosci..

[10]  Paul Beaudet,et al.  Rotationally invariant image operators , 1978 .

[11]  George Azzopardi,et al.  Detection of Retinal Vascular Bifurcations by Trainable V4-Like Filters , 2011, CAIP.

[12]  Max A. Viergever,et al.  Ridge-based vessel segmentation in color images of the retina , 2004, IEEE Transactions on Medical Imaging.

[13]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[14]  T. Poggio,et al.  Hierarchical models of object recognition in cortex , 1999, Nature Neuroscience.

[15]  George Azzopardi,et al.  A CORF computational model of a simple cell that relies on LGN input outperforms the Gabor function model , 2012, Biological Cybernetics.

[16]  David G. Lowe,et al.  Object recognition from local scale-invariant features , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[17]  I. Deary,et al.  Retinal image analysis: Concepts, applications and potential , 2006, Progress in Retinal and Eye Research.

[18]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[19]  Sanja Fidler,et al.  Hierarchical Statistical Learning of Generic Parts of Object Structure , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[20]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[21]  Yannis Avrithis,et al.  VIRaL: Visual Image Retrieval and Localization , 2010, Multimedia Tools and Applications.

[22]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[23]  George Azzopardi,et al.  A Push-Pull CORF Model of a Simple Cell with Antiphase Inhibition Improves SNR and Contour Detection , 2014, PloS one.

[24]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[25]  D. Hubel,et al.  Receptive fields and functional architecture of monkey striate cortex , 1968, The Journal of physiology.

[26]  Su Yang.  Spectra of shape contexts: An application to symbol recognition , 2014, Pattern Recognit..

[27]  Charles E Connor,et al.  Underlying principles of visual shape selectivity in posterior inferotemporal cortex , 2004, Nature Neuroscience.

[28]  Nicolai Petkov,et al.  Computational models of visual neurons specialised in the detection of periodic and aperiodic oriented visual stimuli: bar and grating cells , 1997, Biological Cybernetics.

[29]  Carlos Guedes,et al.  Optical music recognition: state-of-the-art and open issues , 2012, International Journal of Multimedia Information Retrieval.

[30]  Antonio Torralba,et al.  Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope , 2001, International Journal of Computer Vision.

[31]  Yannis Avrithis,et al.  Visual Image Retrieval and Localization , 2009 .

[32]  Cordelia Schmid,et al.  Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study , 2006, 2006 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'06).

[33]  Ernest Valveny,et al.  A general framework for the evaluation of symbol recognition methods , 2007, International Journal of Document Analysis and Recognition (IJDAR).

[34]  Mriganka Sur,et al.  Response-dependent dynamics of cell-specific inhibition in cortical networks in vivo , 2014, Nature Communications.

[35]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[36]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[38]  M. Tso,et al.  Pathophysiology of hypertensive retinopathy. , 1982, Ophthalmology.

[39]  M. Sonka,et al.  Retinal Imaging and Image Analysis. , 2010, IEEE transactions on medical imaging.

[40]  Chenyu Shi,et al.  Recognition of Architectural and Electrical Symbols by COSFIRE Filters with Inhibition , 2015, CAIP.

[41]  George Azzopardi,et al.  Unsupervised delineation of the vessel tree in retinal fundus images , 2016 .

[42]  George Azzopardi,et al.  A Shape Descriptor Based on Trainable COSFIRE Filters for the Recognition of Handwritten Digits , 2013, CAIP.

[43]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  George Azzopardi,et al.  Trainable COSFIRE filters for vessel delineation with application to retinal images , 2015, Medical Image Anal..

[45]  C. Gilbert,et al.  Generation of end-inhibition in the visual cortex via interlaminar connections , 1986, Nature.

[46]  Richard Zanibbi,et al.  Recognizing Mathematical Expressions Using Tree Transformation , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[47]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

[48]  Nicolai Petkov,et al.  Modifications of center-surround, spot detection and dot-pattern selective operators , 2005 .

[49]  Cordelia Schmid,et al.  Indexing Based on Scale Invariant Interest Points , 2001, ICCV.

[50]  Ernest Valveny,et al.  Report on the Symbol Recognition and Spotting Contest , 2011, GREC.

[51]  Kotagiri Ramamohanarao,et al.  Automatic Detection of Vascular Bifurcations and Crossovers from Color Retinal Fundus Images , 2007, 2007 Third International IEEE Conference on Signal-Image Technologies and Internet-Based System.

[52]  Max A. Viergever,et al.  General intensity transformations and differential invariants , 1994, Journal of Mathematical Imaging and Vision.

[53]  George Azzopardi,et al.  Multiscale Blood Vessel Delineation Using B-COSFIRE Filters , 2015, CAIP.

[54]  George Azzopardi,et al.  Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[55]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[56]  Nicolai Petkov,et al.  Nonlinear operator for oriented texture , 1999, IEEE Trans. Image Process..

[57]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[58]  Chenyu Shi,et al.  Automatic Differentiation of u- and n-serrated Patterns in Direct Immunofluorescence Images , 2015, CAIP.

[59]  Cordelia Schmid,et al.  A sparse texture representation using local affine regions , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[60]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[61]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[62]  Chia-Ling Tsai,et al.  Model-based method for improving the accuracy and repeatability of estimating vascular bifurcations and crossovers from retinal fundus images , 2004, IEEE Transactions on Information Technology in Biomedicine.