4,482 Hits in 7.5 sec

A Feature Fusion Approach for Hand Tools Classification

Mostafa Ibrahim, Alaa Ahmed
2017 International Journal of Advanced Computer Science and Applications  
The fused moment-Fourier feature vector is invariant to image scaling, rotation, and translation.  ...  The fused feature vector for a reference object is used for training feed-forward neural network classifier.  ...  The fused feature vector is invariant to object scaling, rotation and translation. A feed-forward neural network has been used as objects classifier.  ... 
doi:10.14569/ijacsa.2017.081013 fatcat:qkzxbhfksfdftlk3ksunw7qlsi


Bahgat F.
2001 International Conference on Aerospace Sciences and Aviation Technology  
This type of neural networks is commonly used as pattern classifiers, with complex moment invariant feature vector as input.  ...  The method combines complex moments with the complex neural-network. The network uses the complex moments as a feature vector that are invariant to translation, scale and rotation.  ...  defined by equation ( 9 ) is invariant to object rotation, translation, contrast and scale change [6] .  ... 
doi:10.21608/asat.2001.31145 fatcat:ygzktqvchjekxne24pz4t4rzcq

Plant leaf identification using moment invariants & General Regression Neural Network

Zalikha Zulkifli, Puteh Saad, Itaza Afiani Mohtar
2011 2011 11th International Conference on Hybrid Intelligent Systems (HIS)  
Then, the resulting set of features representing the leaf images are classified using General Regression Neural Network (GRNN) for recognition purposes.  ...  based on images of leaf is a very challenging task in the field of pattern recognition and computer vision.  ...  ACKNOWLEDGEMENTS All praises and gratitude to Allah s.w.t, who has guided and blessed me in finishing my project successfully.  ... 
doi:10.1109/his.2011.6122144 dblp:conf/his/ZulkifliSM11 fatcat:es2p5omh7ncbvdyojh63tnqspu

Persian Printed Numerals Classification Using Extended Moment Invariants

Hamid Reza Boveiri
2010 Zenodo  
Third is a well-known neural network and forth is a kind of fuzzy neural network that is based on utilizing hyperbox fuzzy sets.  ...  In representation stage, for the first time in Persian optical character recognition, extended moment invariants has been utilized as characters image descriptor.  ...  These moments are nonlinear and invariant under translation, rotation, scaling, and image reversal. Li [23] developed Hu's invariants and listed 52 extended moment invariants.  ... 
doi:10.5281/zenodo.1082016 fatcat:6vu6rkehmvhzpj2ukdqs42uqzi

A Multi-Layered Competitive Net for Pattern Recognition Invariant to Coordinate Transformations

Takeshi Nishida, Shuichi Kurogi
2000 The Brain & Neural Networks  
A multi.1ayered competitive neural network is presented for learning to achieve pattem recognition in a manner invariant to linear and/or nonlinear coordinate transformations such as projection,shift,rotation  ...  ,magnification and so on.The transformed input pattems stored in the network are multiplied by the Jacobian of the transformation,an aspect shown to be essential for the transformation invariance.The network  ...  .G.(1992): Translationrotationand scale invariant pat− tem recognition by highorder neural networks and moment classifiers,IEEE Trans.Neural Networks,Vol.3,No.2,pp。  ... 
doi:10.3902/jnns.7.106 fatcat:cnkdjarmi5gydewcjdwyx2xqne

Invariant pattern recognition: A review

Jeffrey Wood
1996 Pattern Recognition  
Invariance Pattern classification Group theory Integral transforms Fourier transforms Moment invariants Neural networks Weight sharing Higher order networks  ...  In this document we review and compare some of the classical and modem techniques for solving the problem of invariant pattern recognition.  ...  Acknowledgement--I would like to thank my supervisor, John Shawe-Taylor, for supporting me in this work and for reading through and advising me upon this document.  ... 
doi:10.1016/0031-3203(95)00069-0 fatcat:givjeyjknfdyzkmqlgzv34xhca


2000 International journal of pattern recognition and artificial intelligence  
This calls for augmenting the original Neuro-Fuzzy model with a modified moment-based RST invariant feature extractor.  ...  The capability of Kasuba's Simplified Fuzzy ARTMAP (SFAM) to behave as a Pattern Recognizer/Classifier of images both noisy and noise free has been investigated in this paper.  ...  For 2D images, moments have been used to achieve Rotation (R), Scaling (S), and Translation (T ) invariants.  ... 
doi:10.1142/s0218001400000684 fatcat:gywidy3msvd5taeiwx7iwtf3te

Feature extraction methods for character recognition-A survey

Øivind Due Trier, Anil K. Jain, Torfinn Taxt
1996 Pattern Recognition  
The feature extraction methods are discussed in terms of invariance properties, reconstructability and expected distortions and variability of the characters.  ...  Selection of a feature extraction method is probably the single most important factor in achieving high recognition performance in character recognition systems.  ...  This work was supported by a NATO collaborative research grant (CRG 930289) and The Research Council of Norway.  ... 
doi:10.1016/0031-3203(95)00118-2 fatcat:ilpomr6kufel7fdspwjyin5azi

An Improved Interacting Multiple Model Algorithm for Target Tracking Based on ANFIS

Zengqiang Ma, Yacong Zheng, Sha Zhong, Xingxing Zou, Yachao Li
2014 International Journal of Signal Processing, Image Processing and Pattern Recognition  
The paper presents a novel object recognition system using multiple invariant moments as the main feature of the object, and the detected feature is trained by BP neural network so that the classification  ...  Finally, we implemented the proposed approach by visual air plane recognition, the experimental results demonstrates the robustness and efficiency of the presented approach.  ...  Acknowledgements This project was sponsored in part by The National NaturalScience Foundation of Chinese NO.61302159.  ... 
doi:10.14257/ijsip.2014.7.5.29 fatcat:euexajrn65bbzgk3htagsrglky

Translation, rotation, and scale-invariant object recognition

L.A. Torres-Mendez, J.C. Ruiz-Suarez, L.E. Sucar, G. Gomez
2000 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
A method for object recognition, invariant under translation, rotation, and scaling, is addressed.  ...  Recognition was tested with 17 different sizes and 14 rotations. The results are encouraging, since we achieved 98% correct recognition.  ...  Madaline structures for translation-invariant recognition [1] , the self-organized neocognitron [5] , and high-order neural networks [7] , [18] , [19] , are examples of IOR neural-based methods.  ... 
doi:10.1109/5326.827484 fatcat:wnphggcouvfvlczwxmqtowjmzq

Modular Adaptive System Based on a Multi-Stage Neural Structure for Recognition of 2D Objects of Discontinuous Production

I. Topalova
2005 International Journal of Advanced Robotic Systems  
The translation, scale and partial rotation invariant contour object description is transformed in a DCT spectrum space.  ...  The NNs are structured in three stages -filtering and full rotation invariance; partial recognition; general classification.  ...  The second approach uses higher-order neural networks to produce invariance.  ... 
doi:10.5772/5804 fatcat:5krfc3tcdnhsljxfhgdyltb75q

A Review of Visual Descriptors and Classification Techniques Used in Leaf Species Identification

K. K. Thyagharajan, I. Kiruba Raji
2018 Archives of Computational Methods in Engineering  
As computers cannot comprehend images, they are required to be converted into features by individually analysing image shapes, colours, textures and moments.  ...  that affect them, the pattern of leaf growth, and so on.  ...  Zernike moments [121] Moment features on leaf shape Pros: translation, Scale, rotation and skew invariant.  ... 
doi:10.1007/s11831-018-9266-3 fatcat:xa4zxzfhjbgnhkv4h2xu5axhqy

Krawtchouk moment feature extraction for neural Arabic handwritten words recognition

A. El Affar, K. Ferdous, H. El Fadili, H. Qjidaa
2009 2009 International Conference on Multimedia Computing and Systems  
It produces excellent and encouraging result by reducing the computational burden of the recognition system and presenting a high recognition rate with good generalization ability.  ...  The second step (recognition) is achieved by using multilayer feedforward neural network (MFNN) as a classifier with the stochastic back propagation as a learning algorithm.  ...  The new set of moments can be formed by replacing the regular geometric moments the new set of moments is rotation, scale and translation invariant.  ... 
doi:10.1109/mmcs.2009.5256656 fatcat:coofjn6eirc4peie4rivlrbh3m

Scene Classification by Fuzzy Local Moments

H. D. Cheng, Rutvik Desai
1998 International journal of pattern recognition and artificial intelligence  
The classi cation capability and robustness of the technique is demonstrated by experiments on scaled, rotated and noisy gray-level images of uppercase and lowercase characters and digits of English alphabet  ...  The technique does not require translation, scaling or rotation of the image. Furthermore, it is suitable for parallel implementation which is an advantage for real-time applications.  ...  INTRODUCTION The issue of pattern/object classi cation and recognition invariant to translation, rotation and scaling is very important for pattern recognition, image processing and computer vision 18  ... 
doi:10.1142/s0218001498000506 fatcat:bx27oarrordmpbxogdahjvbsny

Vehicle Recognition based on Pseudo invariant Linear Moment Features and ELM

Shao Yong-lin, Luo Yi-ping
2016 International Journal of Computer Applications  
In view of the problem of slow speed and low accuracy of the vehicle recognition in advanced driver assistance systems, a vehicle recognition method based on pseudo invariant linear moment features and  ...  The validity of the model is verified through experiments, compared with other algorithms, the recognition accuracy of pseudo invariant linear moment features and ELM vehicle recognition method is higher  ...  Compared with the traditional artificial neural network, the PCNN have the advantages of rotation invariant, scale invariant, translation invariant and gray intensity invariant, which be found that it  ... 
doi:10.5120/ijca2016909171 fatcat:gswh5hdpcra7nhjp5rzuwoltwm
« Previous Showing results 1 — 15 out of 4,482 results