Global Blur Assessment and Blurred Region Detection in Natural Images
Journal Title: Acta Technica Napocensis- Electronica-Telecomunicatii (Electronics and Telecommunications) - Year 2012, Vol 53, Issue 2
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
- EP ID EP161173
- DOI -
- Views 114
- Downloads 0
Active Balancing Method For Battery Cell Equalization
The emerging need for more power has led to the development of series-parallel connected battery cells. Having a more complex system also brought with it new challenges. One of these is the problem of cell imbalance. Bal...
Advanced Methods And Tools For Online Evaluation Of Multiplexing Services And Encoding Parameters In Digital Video Broadcasting
The paper contains a practical study regarding some aspects of multiplexing and encoding implementation in DVB systems. Starting from the ITU-R DTV model, the main blocks are investigated from theoretical point of view,...
Integration of Network Coding Techniques in Future Internet Architectures
The paper introduces several new methods and experimental results on the integration of Network Coding techniques into the architectures proposed for the future Internet. Also, there are shortly presented some of the mai...
Multimodal Biometric Systems Overview
Biometric systems allow automatic person recognition based on physical or behavioral features which belong to a certain person. Each biometric feature has its limits and no biometric system is perfect so unimodal biometr...
Test Power Optimization with Recordering of Genetic Test Vectors for VLSI Circuits
Power optimization is one of the important challenges in VLSI circuit for testing engineers. Larger power dissipation becomes the reason for overheating and with every increase in 10oC in operating temperature, failure r...