We propose an image segmentation method based on combining unsupervised clustering in the color space with region growing in the image space. No ‘a priori’ knowledge is required about the number of regions in the image. The algorithm is useful for marker extraction or complete segmentation of multidimensional, and in particular color, images. The running time depends mostly upon the speed of th...

Color is an important attribute for image matching and retrieval We present a new method for color matching based on a clustering algorithm in the D color space We de ne a new color feature to characterize the color information and a distance measure to compute the color similarity of images We have implemented this technique and tested it for a database of about images The test results show th...

In this paper, we propose a user-assisted video segmentation algorithm based on color information to alleviate oversegmentation problems. We perform intra-frame segmentation by image simplification, region labeling, and color clustering. In this paper, we also present a discrete three dimensional diffusion model for easy implementation. The statistical property of each labeled region is used to...

In this paper, we focus on the problem of unsupervised clustering which allows automatic setting of optimal clusters number. We present a generalization of the competitive agglomeration clustering algorithm firstly introduced in [1]. This generalization is inspired by the regularization theory and suggests a new schema for using various cluster validity criteria continuously proposed in the lit...

This paper presents a flower classification and identification system that takes a flower image as input and identifies it to be belonging to a particular category present in the database. It begins by performing pre-processing operations on the input image. A set of digital images are segmented using k-means clustering algorithm from which texture and color features are extracted. Texture feat...

In the present paper we propose and evaluate a framework for detection and classification of plant leaf/stem diseases using image processing and neural network technique. The images of plant leaves affected by four types of diseases namely early blight, late blight, powdery-mildew and septoria has been considered for study and evaluation of feasibility of the proposed method. The color transfor...

In this paper, we propose a novel approach for dominant color region detection using dominant sets clustering and apply it to soccer video shot classification. Compared with the widely used histogram based dominant color extraction methods which require appropriate thresholds and sufficient training samples, the proposed method can automatically extract dominant color region without any thresho...

In this paper, a denoising approach, which exploits patchredundancy for removing Gaussian noise from RGB color images is described. Both geometrical and photometrical similarity of image patches have to be considered for learning the parameters of this Patch-based Locally Optimal Weiner(PLOW) filer. K-means clustering,with LARK(Locally Adaptive Regression Kernel) features, is used to identify t...

Image database sizes have increased enormously in the recent years due to the development of the technology which has developed the need for Content Based Image Retrieval (CBIR) system. In this study a CBIR system that allows searching and retrieves images from the databases is developed using the fuzzy c-means algorithm and K-means clustering, the system uses the low level features like color,...

Nowadays in agriculture the labour work is very important. This paper is proposed to reduce the labour work in fruit picking by using the image clustering algorithm in a machine vision system. For plucking fruits such as citrus, apple, jujube, etc., so many different classification techniques were proposed. This paper focus on the automatic detection of the pomegranate fruits in an orchard. The...