Unsupervised Segmentation of Color-Texture Regions in Images and Video
By Yining Deng, Bangalore S. Manjunath. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001
1,563 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition
View Paper: https://www.semanticscholar.org/paper/7ff4bc32bbdeb84c403a0535b244d468b352ce06
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
- Luc Van Gool
- Dacheng Tao
- Xiaogang Wang
- Trevor Darrell
- Ming-Hsuan Yang
- Jitendra Malik
- Li Fei-Fei
- Andrew Zisserman
Citations in the corpus
- Segmentation of Natural Images by Texture and Boundary Compression (2010, neutral): “The proposed region-merging method has been widely used by other image segmentation algorithms (Haralick and Shapiro 1985; Tremeau and Borel 1997; Deng and Manjunath 2001).”
- Semantic object classes in video: A high-definition ground truth database (2009, methodology): “In the context of video based object analysis, many advanced techniques have been proposed for object segmentation (Marcotegui et al., 1999; Deng and Manjunath, 2001; Patras et al., 2003; Wang et al., 2005; Agarwala et al., 2004).”
- A Formal Study of Shot Boundary Detection (2007, methodology): “Various approaches, such as JSEG [ 66 ], Mean Shift [67], and graph partition model [53], [54], [68], have been proposed.”
- Image retrieval: Ideas, influences, and trends of the new age (2008, methodology): “An unsupervised approach for segmentation of images containing homogeneous color/texture regions has been proposed in [Deng and Manjunath 2001].”
- Recognition of Multiple-Food Images by Detecting Candidate Regions (2012, methodology): “The proposed method detects candidate regions with several methods including Felzenszwalb’s deformable part model (DPM) [1], a circle detector and the JSEG region segmentation [6].”
- Seeded region growing: an extensive and comparative study (2005, methodology): “However, automatic semantic image segmentation is an ill-defined problem because semantic objects do not usually correspond to homogeneous regions in color or texture (Deng and Manjunath, 2001).”
- Concept-Based Video Retrieval (2009, background): “Shape: Alternatively, a key frame can be segmented by grouping pixels in the image based on a homogeneity criterion on color, texture, or both [32] [54] [89], or by connecting edge lines [65].”
- A survey of content-based image retrieval with high-level semantics (2007, background): “Similarity between two images is defined based on region features.”
- Segmentation using superpixels: A bipartite graph partitioning approach (2012, methodology): “We compare the average scores of SAS and the ten benchmark algorithms, Ncut [26], Mean Shift [4], FH [10], JSEG [6], Multi-scale Ncut (MNcut) [5], Normalized Tree Partitioning (NTP) [28], Saliency Driven Total Variation (SDTV) [9], Texture and Boundary Encoding-based Segmentation (TBES) [21], Ultram”
- A Review on Image Feature Extraction and Representation Techniques (2013, methodology): “Figure 4 illustrates the regions obtained by these three methods, where (a) shows the original image, (b) gives the image segmented by a regular grid, (c) provides the image segmented by the JSEG [25], and (d) outlines the salient regions detected by the Difference of Gaussian (DoG) [26] detector .”
- Wavelet-based multiscale texture segmentation: Application to stromal compartment characterization on virtual slides (2010, methodology): “Based texture segmentation methods (such as JSEG criterion (Deng and Manjunath, 2001) or active region based segmentation (Lecellier et al., 2006)) were not able to provide good results of segmentation.”
- Unsupervised extraction of visual attention objects in color images (2006, methodology): “Our work incorporates visual attention with seeded object/ region growing [2], [ 10 ] to extract the attention object.”
- A methodological approach to the classification of dermoscopy images (2007, methodology): “The method is based on the JSEG algorithm [19] and included three main phases: preprocessing , segmentation, and postprocessing.”