Does K-Means reasonably divides the data into k groups is an important question that arises when one works on Image Segmentation? Which color space one should choose and how to ascertain that the k we determine is valid? The purpose of this study was to explore the answers to aforementioned questions. We perform K-Means on a number of 2-cluster, 3cluster and k-cluster color images (k>3) in RGB ...

This paper describes a color texture-based image segmentation system. The color texture information is obtained via modeling with the Multispectral Simultaneous Auto Regressive (MSAR) random field model. The general color content characterized by ratios of sample color means is also used. The image is segmented into regions of uniform color texture using an unsupervised histogram clustering app...

After performing a thorough comparison of different quantization schemes in the RGB;HSV; Y UV; and CIEL u v color spaces, we propose to use color features obtained by hierarchical color clustering based on a pruned octree data structure to achieve efficient and robust image retrieval. With the proposed method, multiple color features, including the dominant color, the number of distinctive colo...

AbstructThis paper presents a color image segmentation method which divides color space into clusters. Competitive learning is used as a tool for clustering color space based on the least sum of squares criterion. We show that competitive learning converges to approximate the optimum solution based on this criterion theoretically and experimentally. We applied this method to various color scene...

An automatic color-based image recognition approach is presented in this article. A set of digital images will be clustered in several classes on the color similarity basis. The images are featured using LAB color space. Then, the obtained color-based feature vectors are clustered using a novel automatic unsupervised classification algorithm based on validation indexes. Some experiments, perfor...

For the distribution characteristics in a slice of pathological cell image, the system transforms them into the characteristic vectores by quantization and clustering in HSV color model, it promotes the concerned isolated pixel color description into the color feature ralative to its neighborhood’s color histogram and color moments. By choosing appropriate neighborhood window size, it uses colo...

In this paper, an invisible hybrid color image hiding scheme based on spread vector quantization (VQ) neural network with penalized fuzzy c-means (PFCM) clustering technology (named SPFNN) is proposed. The goal is to offer safe exchange of a color stego-image in the internet. In the proposed scheme, the secret color image is first compressed by a spread-unsupervised neural network with PFCM bas...

This paper introduces a hybrid approach that is based on color information that utilizes background subtraction technique, a mask and K-Mean clustering algorithm. This hybrid approach efficiently removes artifacts caused by lightening changes such as highlight, reflection, and shadows of moving objects from segmentation. We first create a mask by assigning values to R, G and B channels utilizin...

This paper presents an efficient spatial indexing technique for content-based image retrieval. Spatial index is generated based upon a fast and robust clustering technique, which can recognize color clusters of any shape. It also exploits entropy measure to decide whether quantization is needed before clustering. Based on experimentation, the performance of the new indexing technique has been f...

The mean-shift clustering is an efficient technique for color image segmentation by dividing an image into homogeneous regions. The main drawback of mean-shift clustering is to use a fixed scale, which directly determines to use a fixed homogeneity. Since each region could have different homogeneity, using a fixed scale has a problem to segment well. To resolve this problem, we incorporate mult...