Back-propagation algorithm for relevance feedback in image retrieval
نویسندگان
چکیده
Content-based image retrieval (CBIR) usually relies on pre-attentive similarities. Results are often coarse because of the gap between the pre-attentive level and the semantic level of the user’s request. The aim of relevance feedback is to refine results by taking user’s expertise into account. This paper presents a new feedback architecture for CBIR. Images are compared through a weighted dissimilarity function which can be represented as a “network of dissimilarities”. The weights are updated via an error backpropagation algorithm using the user’s annotations of the successive set of result images. It allows an iterative refinement of the search through a simple interactive process (the user has just to specify if images are relevant or not). A quality assessment realized with three databases containing about 10,000 images shows the performance improvement after feedback.
منابع مشابه
Document Image Retrieval Based on Keyword Spotting Using Relevance Feedback
Keyword Spotting is a well-known method in document image retrieval. In this method, Search in document images is based on query word image. In this Paper, an approach for document image retrieval based on keyword spotting has been proposed. In proposed method, a framework using relevance feedback is presented. Relevance feedback, an interactive and efficient method is used in this paper to imp...
متن کاملبازیابی تعاملی تصاویر طبیعت با بهره گیری از یادگیری چند نمونه ای
Content-based image retrieval (CBIR) has received considerable research interest in the recent years. The basic problem in CBIR is the semantic gap between the high-level image semantics and the low-level image features. Region-based image retrieval and learning from user interaction through relevance feedback are two main approaches to solving this problem. Recently, the research in integra...
متن کاملArtificial Neural Network based Relevance Feedback for Intermediate Feature Based Image Retrieval
-In this paper, a new method for intermediate features based image retrieval is proposed. Image database is constructed with low level texture features obtained from Gray Level Co-Occurrence Matrix (GLCM). Semantic level queries from the user mapped to the low level features at retrieval time to retrieve the required images. Artificial Neural Network (ANN) is used in the next steps after receiv...
متن کاملAlgorithms of High-Level Semantic-Based Image Retrieval
IPSM is an integrated probabilistic image semantic description multi-level model. This model includes input layer, feature layer, semantic layer, synthetical probability layer, probability propagation layer, and semantic mapping layer. Based on the model and characterizing of the image high-level semantic content according to Bayesian theory, SHM (semantic high-level retrieval algorithm) and SR...
متن کاملManifold-Ranking-Based Keyword Propagation for Image Retrieval
In this paper, a novel keyword propagation method is proposed for image retrieval based on a recently developed manifold-ranking algorithm. In contrast to existing methods which train a binary classifier for each keyword, our keyword model is constructed in a straightforward manner by exploring the relationship among all images in the feature space in the learning stage. In relevance feedback, ...
متن کامل