Trainable COSFIRE Filters for Keypoint Detection and Pattern Recognition

Background: Keypoint detection is important for many computer vision applications. Existing methods suffer from insufficient selectivity regarding the shape properties of features and are vulnerable to contrast variations and to the presence of noise or texture. Methods: We propose a trainable filter which we call Combination Of Shifted FIlter REsponses (COSFIRE) and use for keypoint detection and pattern recognition. It is automatically configured to be selective for a local contour pattern specified by an example. The configuration comprises selecting given channels of a bank of Gabor filters and determining certain blur and shift parameters. A COSFIRE filter response is computed as the weighted geometric mean of the blurred and shifted responses of the selected Gabor filters. It shares similar properties with some shape-selective neurons in visual cortex, which provided inspiration for this work. Results: We demonstrate the effectiveness of the proposed filters in three applications: the detection of retinal vascular bifurcations (DRIVE dataset: 98.50 percent recall, 96.09 percent precision), the recognition of handwritten digits (MNIST dataset: 99.48 percent correct classification), and the detection and recognition of traffic signs in complex scenes (100 percent recall and precision). Conclusions: The proposed COSFIRE filters are conceptually simple and easy to implement. They are versatile keypoint detectors and are highly effective in practical computer vision applications.

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

[2]  C D Murray,et al.  The Physiological Principle of Minimum Work: I. The Vascular System and the Cost of Blood Volume. , 1926, Proceedings of the National Academy of Sciences of the United States of America.

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

[4]  Luc Van Gool,et al.  Moment invariants for recognition under changing viewpoint and illumination , 2004, Comput. Vis. Image Underst..

[5]  Nicolai Petkov,et al.  The Role of Non-CRF Inhibition in Contour Detection , 2003, WSCG.

[6]  H. Damasio,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence: Special Issue on Perceptual Organization in Computer Vision , 1998 .

[7]  Nicolai Petkov,et al.  Suppression of contour perception by band-limited noise and its relation to nonclassical receptive field inhibition , 2003, Biological cybernetics.

[8]  T F Sherman,et al.  On connecting large vessels to small. The meaning of Murray's law , 1981, The Journal of general physiology.

[9]  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.

[10]  Nikolay Petkov,et al.  Biologically motivated computationally intensive approaches to image pattern recognition , 1995, Future Gener. Comput. Syst..

[11]  Edward H. Adelson,et al.  The Design and Use of Steerable Filters , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

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

[13]  M Zamir,et al.  Arterial bifurcations in the human retina , 1979, The Journal of general physiology.

[14]  Marc'Aurelio Ranzato,et al.  Efficient Learning of Sparse Representations with an Energy-Based Model , 2006, NIPS.

[15]  Thomas Villmann,et al.  Generalized relevance learning vector quantization , 2002, Neural Networks.

[16]  Tony Lindeberg,et al.  Feature Detection with Automatic Scale Selection , 1998, International Journal of Computer Vision.

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

[18]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  T. Poggio,et al.  A model of V4 shape selectivity and invariance. , 2007, Journal of neurophysiology.

[20]  C. D. Murray.  THE PHYSIOLOGICAL PRINCIPLE OF MINIMUM WORK APPLIED TO THE ANGLE OF BRANCHING OF ARTERIES , 1926, The Journal of general physiology.

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

[22]  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.

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

[24]  C. Gross,et al.  Visuotopic organization and extent of V3 and V4 of the macaque , 1988, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[25]  Sanja Fidler,et al.  Towards Scalable Representations of Object Categories: Learning a Hierarchy of Parts , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

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

[27]  F. Kingdom,et al.  Multiplication in curvature processing. , 2009, Journal of vision.

[28]  C. Connor,et al.  Responses to contour features in macaque area V4. , 1999, Journal of neurophysiology.

[29]  Nicolai Petkov,et al.  Distance sets for shape filters and shape recognition , 2003, IEEE Trans. Image Process..

[30]  M. Kolesnik,et al.  Unsupervised shape learning in a neuromorphic hierarchy , 2008, Pattern Recognition and Image Analysis.

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

[32]  C. Connor,et al.  Shape representation in area V4: position-specific tuning for boundary conformation. , 2001, Journal of neurophysiology.

[33]  Cordelia Schmid,et al.  Local Grayvalue Invariants for Image Retrieval , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  Nicolai Petkov,et al.  Contour and boundary detection improved by surround suppression of texture edges , 2004, Image Vis. Comput..

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

[36]  R. Sukthankar,et al.  PCA-SIFT: a more distinctive representation for local image descriptors , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

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

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

[39]  Marcel F. Jonkman,et al.  Learning effective color features for content based image retrieval in dermatology , 2011, Pattern Recognit..

[40]  Ali Borji,et al.  Invariance analysis of modified C2 features: case study—handwritten digit recognition , 2009, Machine Vision and Applications.

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

[42]  Adam Baumberg,et al.  Reliable feature matching across widely separated views , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[43]  J. Hegdé,et al.  A comparative study of shape representation in macaque visual areas v2 and v4. , 2007, Cerebral cortex.

[44]  Gustavo Carneiro,et al.  Multi-scale phase-based local features , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

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

[46]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[47]  Thomas Martinetz,et al.  The Support Feature Machine for Classifying with the Least Number of Features , 2010, ICANN.

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

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

[50]  Fariborz Mahmoudi,et al.  Robust Handwritten Character Recognition with Features Inspired by Visual Ventral Stream , 2008, Neural Processing Letters.

[51]  C. Connor,et al.  Population coding of shape in area V4 , 2002, Nature Neuroscience.

[52]  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.

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

[54]  Nicolai Petkov,et al.  Contour detection based on nonclassical receptive field inhibition , 2003, IEEE Trans. Image Process..

[55]  Thomas Serre,et al.  A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex , 2005 .