Topic
Content-based image retrieval
About: Content-based image retrieval is a research topic. Over the lifetime, 6916 publications have been published within this topic receiving 150696 citations. The topic is also known as: CBIR.
Papers published on a yearly basis
Papers
More filters
01 May 2015
TL;DR: The results using receiver operating characteristic (ROC) curve proved that the proposed architecture is highly contributed to computer-aided diagnosis of skin lesions.
Abstract: To retrieve images of similar diseases that lead to similar diagnosis.To provide improved diagnosis of diseases in medical applications.To guide the physician by predicting the disease of large number of dermatological cases. This method presents extraction of effective color and shape features for the analysis of dermatology images. We employ three phases of operation in order to perform efficient retrieval of images of skin lesions. Our proposed algorithm used color and shape feature vectors and the features are normalized using Min-Max normalization. Particle swarm optimization (PSO) technique for multi-class classification is used to converge the search space more efficiently. The results using receiver operating characteristic (ROC) curve proved that the proposed architecture is highly contributed to computer-aided diagnosis of skin lesions. Experiments on a set of 1450 images yielded a specificity of 98.22% and a sensitivity of 94%. Our empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other works. We present explicit combinations of feature vectors corresponding to healthy and lesion skin.
38 citations
24 Oct 2011
TL;DR: The proposed scheme transfers each image to a quantized color code using the regulations of the properties in compliance with HSV model and succeeds in transferring the image retrieval problem to quantizedcolor code comparison, so the computational complexity is decreased obviously.
Abstract: We propose an efficient image retrieval scheme to retrieve images. We extract the color pixel features by the HSV color space. The proposed scheme transfers each image to a quantized color code using the regulations of the properties in compliance with HSV model. Subsequently, using the quantized color code to compare the images of database. We succeed in transferring the image retrieval problem to quantized color code comparison. Thus the computational complexity is decreased obviously. Our results illustrate it has merits both of the content based image retrieval system and a text based image retrieval system.
38 citations
TL;DR: A new adaptive classification and cluster-merging method to find multiple regions and their arbitrary shapes of a complex image query and achieves the same high retrieval quality regardless of the shapes of query regions since the measures used in the method are invariant under linear transformations.
38 citations
TL;DR: The experiment results show that the proposed retrieval method is more efficient than the traditional CBIR method based on the single visual feature and other methods combining color and texture.
Abstract: Content based image retrieval (CBIR) has been one of the most important research areas in computer science for the last decade. A retrieval method which combines color and texture feature is proposed in this paper. According to the characteristic of the image texture, we can represent the information of texture by Dual-Tree Complex Wavelet (DT-CWT) transform and rotated wavelet filter (RWF). We choose the color histogram in RGB and HSV color space as the color feature. The experiment results show that this method is more efficient than the traditional CBIR method based on the single visual feature and other methods combining color and texture.
37 citations
27 Jun 2004
TL;DR: An entropy-based active learning scheme with support vector machines (SVMs) is proposed for relevance feedback in content-based image retrieval and an entropy- based criterion for good request selection is proposed.
Abstract: An entropy-based active learning scheme with support vector machines (SVMs) is proposed for relevance feedback in content-based image retrieval. The main issue in active learning for image retrieval is how to choose images for the user to label in the next interaction. According to information theory, we proposed an entropy-based criterion for good request selection. To apply the criterion with SVMs, probabilistic outputs are required. Since standard SVMs do not provide such outputs, two techniques are used to produce probabilities. One is to train the parameters of an additional sigmoid function. The other is to use the notion of version space. Experimental results on a database of 10,000 general-purpose images demonstrate the effectiveness of the proposed active learning scheme.
37 citations