Region-based Measures for Evaluation of Color Image Segmentation (original) (raw)

Salient Object Detection Using Segmentation process

2016

The saliency estimation plays a significant role in a variety of applications including image segmentation, adaptive compression, region based image retrieval, multimedia etc. Saliency becomes useful under such a case as low score is attached to the background. In our proposed work salient feature based segmentation will be based on the contrast, gradient, illumination, structure, histograms and feature extraction. The saliency features will be extracted by applying Histogram Of Gradient (HOG) and Difference Of Gaussian (DOG) detector. The main objective of this work is to detect the salient region of the object in the image with well defined boundaries and to segment the Region Of interest (ROI) using modified Fuzzy-C Means (FCM) and expectation maximization clustering method. Here region to region mapping is used instead of pixel to pixel mapping. This approach provides 97.66% accuracy and it is efficient than the previous existing methods. The extended work includes implementing ...

Comparative Evaluation of Mixed Algorithms for Color Image Segmentation

In the present paper we are introducing a new method of salient object detection with very good results relative to other already known segmentation methods. We address through our research the problem of image segmentation evaluation by an efficient comparison of four complex al-gorithms. In order to compare our method with other ap-proaches, we built an evaluation framework that helped us with our experiments. The experimental results offer a com-plete basis for parallel analysis with respect to the precision of our algorithm, rather than the individual efficiency.

Detecting Salient Image Objects Using Color Histogram Clustering for Region Granularity

Journal of Imaging, 2021

Salient object detection represents a novel preprocessing stage of many practical image applications in the discipline of computer vision. Saliency detection is generally a complex process to copycat the human vision system in the processing of color images. It is a convoluted process because of the existence of countless properties inherent in color images that can hamper performance. Due to diversified color image properties, a method that is appropriate for one category of images may not necessarily be suitable for others. The selection of image abstraction is a decisive preprocessing step in saliency computation and region-based image abstraction has become popular because of its computational efficiency and robustness. However, the performances of the existing region-based salient object detection methods are extremely hooked on the selection of an optimal region granularity. The incorrect selection of region granularity is potentially prone to under- or over-segmentation of co...