23,207 Hits in 3.3 sec

Features extraction based on the Discrete Hartley Transform for closed contour

Pere Martí-Puig, Ramon Reig-Bolaño, Jaume Danes
2015 AI Communications  
very efficiently by the fast Discrete Hartley Transform (DHT) algorithm.  ...  In this paper the authors propose a new closed contour descriptor that could be seen as a Feature Extractor of closed contours based on the Discrete Hartley Transform (DHT), its main characteristic is  ...  Acknowledgements This work was partially supported by the Spanish Government project "3D Otolith shape analysis (AFORO 3D)" with reference: CTM2010-19701 and from the University of Vic (UVIC) under the  ... 
doi:10.3233/aic-140620 fatcat:p7cxisswgrapra7j5wq75gchcu

Translating the Architectural Complexity of the Colon or Polyp into a Sinusoid Wave for Classification via the Fast Fourier Transform [article]

David H. Nguyen
2018 arXiv   pre-print
This sinusoid wave can then undergo the Fast Fourier Transform to obtain a spectrum of frequencies that represents the sinusoid wave.  ...  Plotting these values [y variable] against the angle of each radial line from the horizontal axis [x variable] results in a sinusoid wave consisting of discrete points.  ...  Nichols passed away in 2017 because of colon cancer, but left behind 30+ years of students inspired to do STEM research.  ... 
arXiv:1801.06752v1 fatcat:q2dvd6fe2reglavr67p5zptos4

Patchy Image Structure Classification Using Multi-Orientation Region Transform [article]

Xiaohan Yu, Yang Zhao, Yongsheng Gao, Shengwu Xiong, Xiaohui Yuan
2019 arXiv   pre-print
structure classification.  ...  MORT is performed over multiple orientation regions at multiple scales to effectively integrate patchy features, and thus enables a better description of the shape in a coarse-to-fine manner.  ...  contour (or the number of contour points when the contour is sampled in discrete form), and t is the scale index (t = 0, 1, . . . , Q where Q = log 2 N ).  ... 
arXiv:1912.00622v1 fatcat:lab7dv5u7bhlddju5mqsz4i4uu

Patchy Image Structure Classification Using Multi-Orientation Region Transform

Xiaohan Yu, Yang Zhao, Yongsheng Gao, Shengwu Xiong, Xiaohui Yuan
structure classification.  ...  MORT is performed over multiple orientation regions at multiple scales to effectively integrate patchy features, and thus enables a better description of the shape in a coarse-to-fine manner.  ...  contour (or the number of contour points when the contour is sampled in discrete form), and t is the scale index (t = 0, 1, . . . , Q where Q = log 2 N ).  ... 
doi:10.1609/aaai.v34i07.6968 fatcat:scaqxta6zjah7ogvs7bp3caqhy

Wavelet-based feature extraction technique for fruit shape classification

Slamet Riyadi, Asnor Juraiza Ishak, Mohd Marzuki Mustafa, Aini Hussain
2008 2008 5th International Symposium on Mechatronics and Its Applications  
Abnormality in papaya fruit shape represents a defective fruit and is used as one of the main criteria to determine suitability of the fruit to be exported.  ...  The extracted features, when used in the classification task using linear discriminant analysis (LDA), afford accuracy of more than 98%.  ...  ACKNOWLEDGMENT The authors would like to acknowledge the Ministry of Science, Technology and Innovation Malaysia (Project No. 03-01-02-SF0178) for the support of this research.  ... 
doi:10.1109/isma.2008.4648858 fatcat:d6uitw7hefhabft57kyqyjniju

InShaDe: Invariant Shape Descriptors for Visual Analysis of Histology 2D Cellular and Nuclear Shapes

Marco Agus, Khaled Al-Thelaya, Corrado Cali, Marina M. Boido, Yin Yang, Giovanni Pintore, Enrico Gobbetti, Jens Schneider
2020 Eurographics Workshop on Visual Computing for Biomedicine  
The framework is based on a novel shape descriptor of closed contours relying on a geodesically uniform resampling of discrete curves to allow for discrete differential-geometry-based computation of unsigned  ...  The capabilities of the proposed framework are demonstrated in the context of visual analysis and unsupervised classification of histology images.  ...  Contour Smoothing The discrete nature of binary segmentation masks may lead to pixelation artifacts in the extracted contour.  ... 
doi:10.2312/vcbm.20201173 dblp:conf/vcbm/AgusACBYPGS20 fatcat:l2s7zbn7rrh2fjrcxfbo4iq5qq

Bag of contour fragments for robust shape classification

Xinggang Wang, Bin Feng, Xiang Bai, Wenyu Liu, Longin Jan Latecki
2014 Pattern Recognition  
In this paper, we focus on mid-level modeling of shape representation. We develop a new shape representation called Bag of Contour Fragments (BCF) inspired by classical Bag of Words (BoW) model.  ...  In BCF, a shape is decomposed into contour fragments each of which is then individually described using a shape descriptor, e.g., the Shape Context descriptor, and encoded into a shape code.  ...  Ho Simon Wang for assisting to improve the language of this paper.  ... 
doi:10.1016/j.patcog.2013.12.008 fatcat:szpyu3xzgba6vivl3ywsc3xko4

Comprehensive Performance Evaluation of Various Feature Extraction Methods for OCR Purposes [chapter]

Dawid Sas, Khalid Saeed
2015 Lecture Notes in Computer Science  
Optical Character Recognition (OCR) is a very extensive branch of pattern recognition.  ...  The existence of super effective software designed for omnifont text recognition, capable of handling multiple languages, creates an impression that all problems in this field have already been solved.  ...  Acknowledgment The research was supported by the Rector of Bialystok University of Technology in Bialystok, grant number S/WI/1/2013.  ... 
doi:10.1007/978-3-319-24369-6_34 fatcat:ojhhesbkxbhatmrkshj5th3iou

Multiscale Contour Steered Region Integral and Its Application for Cultivar Classification

Xiaohan Yu, Yongsheng Gao, Shengwu Xiong, Xiaohui Yuan
2019 IEEE Access  
The experimental results demonstrate the superiority of the proposed method over the state-of-the-art methods in similar shape classification and the possibility of cultivar recognition via leaf pattern  ...  A component distance map (CDM) is developed to robustly characterize the flexible interior connection structure, shape of the exterior contour, and their inter-relationship in a shape image.  ...  DISCRETE MReT In this section, we present the algorithm of computing discrete Multiscale Region Transform.  ... 
doi:10.1109/access.2019.2918263 fatcat:46clap2375eevj36bt2iffgwju

Efficient Fourier shape descriptor for industrial defect images using wavelets

Iivari Kunttu
2005 Optical Engineering: The Journal of SPIE  
A novel approach to contour-based shape description using wavelet transform combined with Fourier transform is presented.  ...  The use of image retrieval and classification has several applications in industrial imaging systems, which typically use large image archives.  ...  In this figure, the classification rate Fig. 1 Example contours of each 14-paper defect class in the testing database.  ... 
doi:10.1117/1.1993687 fatcat:he5xq3jrzre2xakr7te6gm35pi

Cosine Contours: a Multipurpose Representation for Melodies

Bas Cornelissen, Willem Zuidema, John Ashley Burgoyne
2021 Zenodo  
Melodic contour is central to our ability to perceive and produce music. We propose to represent melodic contours as a combination of cosine functions, using the discrete cosine transform.  ...  The motivation for this approach is twofold: (1) it approximates a maximally informative contour representation (capturing most of the variation in as few dimensions as possible), but (2) it is nevertheless  ...  These basis functions correspond to the most popular version of the discrete cosine transform, DCT-II, for which fast implementations are widely available; others would have been possible [36] .  ... 
doi:10.5281/zenodo.5624530 fatcat:4nefzhjtn5bqdoolu4nu5hjs5u

A Novel Framework for Detection of Cervical Cancer

V. Pushpalatha
2018 Asian Journal of Engineering and Applied Technology  
This framework comprises of five phases, (i) Dual tree discrete wavelet transform to pre-process the image (ii) Curvelet transform and contour transform to enhance the image (iii) K-means for segmentation  ...  (iv) features computation using Gray level co-occurrence matrix (v) classification using adaptive Support vector machine.  ...  Thus, automated approach has to be developed that performs the disclosure of unusual cells fast, accurate, and easy. II.  ... 
doi:10.51983/ajeat-2018.7.2.1016 fatcat:5hp7pwl37bdlxanzxp5bga4twq

The Analysis of Shape Features for the Purpose of Exercise Types Classification Using Silhouette Sequences

Katarzyna Gościewska, Dariusz Frejlichowski
2020 Applied Sciences  
Each action sequence is represented using a vector with shape features and Discrete Fourier Transform.  ...  This paper presents the idea of using simple shape features for action recognition based on binary silhouettes. Shape features are analysed as they change over time within an action sequence.  ...  However, current implementations of the Discrete Fourier Transform can handle arbitrary size transforms, e.g., Fast Fourier Transform algorithm available in the FFTW library [35] .  ... 
doi:10.3390/app10196728 fatcat:wb7xdrtpnnfzzdziaqjsxdig5u

Robust line extraction based on repeated segment directions on image contours

Andres Solis Montero, Amiya Nayak, Milos Stojmenovic, Nejib Zaguia
2009 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications  
Contours of each connected component are divided into short segments, which are classified by their orientation into nine discrete categories.  ...  This algorithm uses a compilation of different image processing steps such as normalization, Gaussian smooth, thresholding, and Laplace edge detection to extract edge contours from colour input images.  ...  Contours are a sequence of consecutive boundary pixels that describe outer edges and forms for any shape and object.  ... 
doi:10.1109/cisda.2009.5356556 dblp:conf/cisda/MonteroNSZ09 fatcat:2jthmwq3u5fftloengmdhpk6la

Otolith shape feature extraction oriented to automatic classification with open distributed data

J. Piera, V. Parisi-Baradad, E. García-Ladona, A. Lombarte, L. Recasens, J. Cabestany
2005 Marine and Freshwater Research  
shape features for automatic classification.  ...  The present study reviewed some of the critical pre-processing steps required for otolith shape characterisation for automatic classification with heterogeneous distributed data.  ...  We would like to thank Antoni Cruz for his contribution in acquiring some of the otolith images processed, and Albert Martí for developing some of the required function routines.  ... 
doi:10.1071/mf04163 fatcat:eacetb5ryjgtfifxmfsvr4wkh4
« Previous Showing results 1 — 15 out of 23,207 results