Color Segmentation using LVQ-Learning Vector Quantization

This thesis aims to present a color segmentation approach for traffic sign recognition based on LVQ neural networks. The RGB images were converted into HSV color space, and segmented using LVQ depending on the hue and saturation values of each pixel in the HSV color space. LVQ neural network was used to segment red, blue and yellow colors on the road and traffic signs to detect and recognize them. LVQ was effectively applied to 536 sampled images taken from different countries in different conditions with 89% accuracy and the execution time of each image among 31 images was calculated in between 0.726sec to 0.844sec. The method was tested in different environmental conditions and LVQ showed its capacity to reasonably segment color despite remarkable illumination differences. The results showed high robustness.

A dislocation based theory for the deformation hardening behavior of DP steels : Impact of martensite content and ferrite grain size

A dislocation model, accurately describing the uniaxial plastic stress-strain behavior of dual phase (DP) steels, is proposed and the impact of martensite content and ferrite grain size in four commercially produced DP steels is analyzed. It is assumed that the plastic deformation process is localized to the ferrite. This is taken into account by introducing a non-homogeneity parameter, f(e), that specifies the volume fraction of ferrite taking active part in the plastic deformation process. It is found that the larger the martensite content the smaller the initial volume fraction of active ferrite which yields a higher initial deformation hardening rate. This explains the high energy absorbing capacity of DP steels with high volume fractions of martensite. Further, the effect of ferrite grain size strengthening in DP steels is important. The flow stress grain size sensitivity for DP steels is observed to be 7 times larger than that for single phase ferrite.