SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture LIbraries

By James Ze Wang, Jia Li, Gio Wiederhold. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000

2,557 citations recorded by the source corpus.

We present here SIMPLIcity (semantics-sensitive integrated matching for picture libraries), an image retrieval system, which uses semantics classification methods, a wavelet-based approach for feature extraction, and integrated region matching based upon image segmentation. An image is represented by a set of regions, roughly corresponding to objects, which are characterized by color, texture, shape, and location. The system classifies images into semantic categories. Potentially, the categorization enhances retrieval by permitting semantically-adaptive searching methods and narrowing down the searching range in a database. A measure for the overall similarity between images is developed using a region-matching scheme that integrates properties of all the regions in the images. The application of SIMPLIcity to several databases has demonstrated that our system performs significantly better and faster than existing ones. The system is fairly robust to image alterations.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2a41681900f295a3098592c1040b35b6e3767c96

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Content-based image retrieval: approaches and trends of the new age (2005, positive): “In the case of image retrieval, some of the ways of getting around this problem have been to reduce dependence on reliable segmentation [12], to involve every generated segment of an image in the matching process to obtain soft similarity measures [104], or to characterize spatial arrangement of col”
Concept-Based Video Retrieval (2009, background): “Research in content-based retrieval has resulted in a wide variety of image and video search systems [17, 32, 34, 61, 67, 72, 114, 143, 180, 197, 207, 214, 258, 266].”
Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “With an increased popularity of region-based image retrieval [Carson et al. 2002; Wang et al. 2001; Ko and Byun 2002], attempts have been made to incorporate the region factor into RF.”
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (2021, methodology): “We fixed the issue by replacing these common images in CASIAv1 with the same amount of images randomly sampled from Corel [42], which is the data source of CASIAv1.”
Image Categorization by Learning and Reasoning with Regions (2004, methodology): “But, in general, semantically accurate image segmentation by a computer program is still an ambitious long-term goal for computer vision researchers (see Shi and Malik, 2000; Wang et al., 2001a; Zhu and Yuille, 1996).”
Features for image retrieval: an experimental comparison (2008, methodology): “Other systems following this approach include SIMBA [21], CIRES [22], SIMPLIcity [23], IRMA [24], and our own system FIRE [25, 26].”
Content-based visual search learned from social media (2012, background): “As shown previously in content-based image search [117, 127], image annotation [41, 80], and video concept detection [128, 137], fusing multiple visual features is beneficial.”
Studying Aesthetics in Photographic Images Using a Computational Approach (2006, methodology): “Today, several efficient region-based image retrieval engines are in use [13, 6, 21, 18].”
Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval (2006, methodology): “In the system, images are represented by three main features: color [23], [17], [14], [9], [16], texture [14], [24], [13], [15], [4], [30], and shape [9], [16].”
Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach (2003, background): “Readers are referred to that article and some additional references [2], [17], [18], [25], [23], [4], [11], [26] for more information.”
Semantic manifold learning for image retrieval (2005, background): “A key ingredient of designing successful Content-Based Image Retrieval (CBIR) systems [4, 16, 31] is how to effectively transform users’ interactions into information that could help the underlying retrieval engines to better organize their image data.”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “1: Comparing pixels of two regions (images are taken from Corel-database [4]).”
Segmentation and histogram generation using the HSV color space for image retrieval (2002, background): “The histogram retains a uniform color transition that enables us to do a window-based smoothing during retrieval.”
CLUE: cluster-based retrieval of images by unsupervised learning (2005, methodology): “Digital Object Identifier 10.1109/TIP.2005.849770”
Social Network Data Analytics (2011, methodology): “Similarly, the RankClus algorithm[107] is only designed to deal with bi-type network, where the network’s vertex set have two types of vertices.”
The Quadratic-Chi Histogram Distance Family (2010, neutral): “[26].”