SHAPE RECOGNITION USING A FIXED-SIZE VLSI ARCHITECTURE

1995 ◽  
Vol 09 (01) ◽  
pp. 1-21 ◽  
Author(s):  
H.D. CHENG ◽  
X. CHENG
Keyword(s):  
Pattern Recognition ◽  
Real Time ◽  
Time Complexity ◽  
Shape Recognition ◽  
Computing Time ◽  
Vlsi Architecture ◽  
Recognition Algorithm ◽  
Fixed Size ◽  
Attribute Grammar ◽  
Real Time Applications

Shape recognition is an important research area in pattern recognition. It also has wide practical applications in many fields. An attribute grammar approach to shape recognition combines both the advantages of syntactic and statistical methods and makes shape recognition more accurate and efficient. However, the time complexity of a sequential shape recognition algorithm using attribute grammar is O(n3) where n is the length of an input string. When the problem size is very large it needs much more computing time, therefore a high speed parallel shape recognition is necessary to meet the demands of some real-time applications. This paper presents a parallel shape recognition algorithm and also discusses the algorithm partition problem as well as its implementation on a fixed-size VLSI architecture. The proposed algorithm has time complexity O(n3/k2) if using k×k processing elements. When k=n, its time complexity is O(n). The experiment has been conducted to verify the performance of the proposed algorithm. The correctness of the algorithm partition and the behavior of the proposed VLSI architecture have also been proved through the experiment. The results indicate that the proposed algorithm and the VLSI architecture could be very useful to imaging processing, pattern recognition and related areas, especially for real-time applications.

Space-Varying Templates for Real-Time Applications of Cellular Nonlinear Networks to Pattern Recognition in Nuclear Fusion

2013 ◽  
Vol 41 (9) ◽  
pp. 2516-2526
Author(s):  
Simone Palazzo ◽  
Andrea Murari ◽  
Paolo Arena ◽  
Didier Mazon ◽  
Jet-Efda Contributors
Keyword(s):  
Pattern Recognition ◽  
Real Time ◽  
Nuclear Fusion ◽  
Nonlinear Networks ◽  
Real Time Applications

Image Enhancement Techniques Using Particle Swarm Optimization Technique

2015 ◽  
pp. 327-347 ◽  
Author(s):  
V. Santhi ◽  
B. K. Tripathy
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Particle Swarm Optimization ◽  
Real Time ◽  
Quality Enhancement ◽  
Swarm Optimization ◽  
Image Processing Techniques ◽  
Real Time Applications ◽  
High Level ◽  
Processing Techniques

The image quality enhancement process is considered as one of the basic requirement for high-level image processing techniques that demand good quality in images. High-level image processing techniques include feature extraction, morphological processing, pattern recognition, automation engineering, and many more. Many classical enhancement methods are available for enhancing the quality of images and they can be carried out either in spatial domain or in frequency domain. But in real time applications, the quality enhancement process carried out by classical approaches may not serve the purpose. It is required to combine the concept of computational intelligence with the classical approaches to meet the requirements of real-time applications. In recent days, Particle Swarm Optimization (PSO) technique is considered one of the new approaches in optimization techniques and it is used extensively in image processing and pattern recognition applications. In this chapter, image enhancement is considered an optimization problem, and different methods to solve it through PSO are discussed in detail.

3D Shape Recognition Based on 1D Signal Processing for Real-Time Applications

2020 ◽  
Vol 30 (3) ◽  
pp. 315-327
Author(s):  
K. Baibai ◽  
K. Hachami ◽  
M. Emharraf ◽  
B. Bellach
Keyword(s):  
Signal Processing ◽  
Real Time ◽  
Shape Recognition ◽  
3D Shape ◽  
Real Time Applications

Image Enhancement Techniques Using Particle Swarm Optimization Technique

2015 ◽  
pp. 860-878
Author(s):  
V. Santhi ◽  
B. K. Tripathy
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Particle Swarm Optimization ◽  
Real Time ◽  
Quality Enhancement ◽  
Swarm Optimization ◽  
Image Processing Techniques ◽  
Real Time Applications ◽  
High Level ◽  
Processing Techniques

The image quality enhancement process is considered as one of the basic requirement for high-level image processing techniques that demand good quality in images. High-level image processing techniques include feature extraction, morphological processing, pattern recognition, automation engineering, and many more. Many classical enhancement methods are available for enhancing the quality of images and they can be carried out either in spatial domain or in frequency domain. But in real time applications, the quality enhancement process carried out by classical approaches may not serve the purpose. It is required to combine the concept of computational intelligence with the classical approaches to meet the requirements of real-time applications. In recent days, Particle Swarm Optimization (PSO) technique is considered one of the new approaches in optimization techniques and it is used extensively in image processing and pattern recognition applications. In this chapter, image enhancement is considered an optimization problem, and different methods to solve it through PSO are discussed in detail.

A Fixed Size Storage O(n3) Time Complexity Learning Algorithm for Fully Recurrent Continually Running Networks

1992 ◽  
Vol 4 (2) ◽  
pp. 243-248 ◽  
Author(s):  
Jürgen Schmidhuber
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Learning Algorithm ◽  
Fixed Size ◽  
Time Step ◽  
The Real ◽  
On Line ◽  
On Line Learning

The real-time recurrent learning (RTRL) algorithm (Robinson and Fallside 1987; Williams and Zipser 1989) requires O(n4) computations per time step, where n is the number of noninput units. I describe a method suited for on-line learning that computes exactly the same gradient and requires fixed-size storage of the same order but has an average time complexity per time step of O(n3).

Research on Real-Time NURBS Interpolator with Quintic Curve Acceleration/Deceleration Algorithm

2011 ◽  
Vol 101-102 ◽  
pp. 884-888
Author(s):  
Xian Kui Liu ◽  
Yu Mei Yang ◽  
Zu Xing Han
Keyword(s):  
Real Time ◽  
Time Complexity ◽  
Dynamic Properties ◽  
Computing Time ◽  
Cnc Machine ◽  
Nurbs Interpolator ◽  
Interpolation Algorithms ◽  
Simple Implementation

We put up a new fast and steady parameter interpolator on the basis of the present various interpolation algorithms. This proposed algorithm has little rate of speed errors than other algorithms and can save much computing time because of its avoiding derivation operations. Quintic curve acceleration/deceleration algorithm (QCAD) is deduced which can improve the flexibility of the CNC machine. By means of the QCAD planning, the demand velocity is maintained high at large of the time and can be smoothly accelerated/decelerated when needed. Therefore, the parameter interpolator with QCAD can meet the CNC dynamic properties to improve the machine quality. In the end, this NURBS interpolator is validated by matlab, which proves this proposed algorithm not only has the advantages of good flexibility and simple implementation procedure, but also has lower time complexity.

Sign in / Sign up

Export Citation Format

Share Document