Global Blur Assessment and Blurred Region Detection in Natural Images

Abstract

In this paper we present a global no-reference blur metric based on a local approach of blur detection in natural macro-like images. The purpose is to study the possibility of global assessment based on thedetection of blurred regions over an analyzed image. In our case, it represents the first step for a plant recognition system. Blur detection works on small non-overlapping blocks using wavelet decomposition and edge classification. At the block level the number of edges is less than on global images. A set of rules is obtained by a supervised decision tree algorithm trained on a manually labeled blurred/un-blurred image blocks which leads to a qualitative decision of the blurriness/sharpness of the regions. Experimental results show how the qualitative decision may be transformed in a global assessment.

Authors and Affiliations

Loreta ŞUTA, Mircea VAIDA

Keywords

Related Articles

Accelerated Ageing Tests of Aluminum Electrolytic Capacitors for Evaluating Lifetime Prediction Models

During the course of the presented work accelerated ageing tests at constant temperature for aluminum electrolytic capacitors were carried out. The obtained results from practical tests are compared with projections of t...

Acoustic Echo Cancellation Using Wavelet Transform And Adaptive Filters

The paper proposes a new method for acoustic echo cancellation(AEC), in order to improve the performances of the normalized least-mean-square (NLMS) and non-parametric variable- step -size-NLMS (NPVSS-NLMS) algorithms. T...

Simplification Of A Link Performance Prediction Method Based On Mutual Information

In this paper, we propose a method to predict the block error rate performance of the wireless links in OFDM communication systems. Our approach relies on a performance prediction methodology that uses the mean mutual in...

On Using DNA Distances And Consensus In Repeats Detection

Sequence repeats are the simplest form of regularity and analyzing repeats can lead to first clues to evidencing new biological phenomena. Many of the methods for detecting repeated sequences are part of the digital sign...

A Derived Robust Statistics Approach For Adaptive Volterra Filters Applied In Nonlinear Acoustic Echo Cancellation Scenarios

The paper proposes a novel updating concept for adaptive Volterra kernels that relies on a robust statistics approach. The optimization of a certain cost function leads to the update equations for the linear and quadrati...

Download PDF file
  • EP ID EP161173
  • DOI -
  • Views 116
  • Downloads 0

How To Cite

Loreta ŞUTA, Mircea VAIDA (2012). Global Blur Assessment and Blurred Region Detection in Natural Images. Acta Technica Napocensis- Electronica-Telecomunicatii (Electronics and Telecommunications), 53(2), 30-35. https://europub.co.uk/articles/-A-161173