Building Up Low-Level Centroids for Groups of Perceptually Similar Images
نویسندگان
چکیده
Image retrieval by using content analysis is known as a difficult task. It is hard to work out common features and metrics that match all perceptually similar images well and distinguish non-similar ones. In our previous studies [8] and [7] mixed-metrics were proposed in order to combine color and texture metrics for image retrieval task. It was shown that it is always possible to mark out the best mixed-metrics for every group of similar images. Thus, usage of appropriate mixed-metrics for a given query improves retrieval effectiveness. To get the proper mixed-metrics a particular query-image should be classified to one of the predefined groups of perceptually similar images. In this study possible solutions for classification task are discussed, experimental results for one of the solution are
منابع مشابه
eID: a system for exploration of image databases
The goal of this paper is to describe an exploration system for large image databases in order to help the user understand the database as a whole, discover hidden relationships, and formulate insights with minimum effort. While the proposed system works with any type of low-level feature representation of images, we describe our system using color information. The system is built in three stag...
متن کاملIntegration of Deep Learning Algorithms and Bilateral Filters with the Purpose of Building Extraction from Mono Optical Aerial Imagery
The problem of extracting the building from mono optical aerial imagery with high spatial resolution is always considered as an important challenge to prepare the maps. The goal of the current research is to take advantage of the semantic segmentation of mono optical aerial imagery to extract the building which is realized based on the combination of deep convolutional neural networks (DCNN) an...
متن کاملA Perceptually Motivated Technique to Query-by-Example Using Color Cardinality
In this paper we present a method for retrieval of color images via query-by-example which takes into consideration human perception regarding the number of colors present in images being compared.. First, we perform HSV-space segmentation to extract regions of perceptually relevant color, to build a low-level color representation. This segmented result is then used to build image indices by ta...
متن کاملDetermining the extent of building destruction after an earthquake using satellite imagery and fuzzy logic (Case study of Sarpol-e-Zahab region)
Background and objective: Earthquake is one of the most destructive natural disasters. Earthquakes occur in urban areas, destroying buildings and injuring people living in them. Urban center buildings are among the features that are exposed to many hazards during an earthquake. One of the first measures taken after an earthquake is relief. Locating damaged buildings can speed up relief efforts....
متن کاملAnalysis of speaker clustering strategies for HMM-based speech synthesis
This paper describes a method for speaker clustering, with the application of building average voice models for speakeradaptive HMM-based speech synthesis that are a good basis for adapting to specific target speakers. Our main hypothesis is that using perceptually similar speakers to build the average voice model will be better than use unselected speakers, even if the amount of data available...
متن کامل