Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/588782
Title: Detecting Salient Objects via Color and Texture Compactness Hypotheses
Authors: Ping Hu;Weiqiang Wang;Chi Zhang;Ke Lu
subject: saliency detection|compactness|Salient object
Year: 2016
Publisher: IEEE
Abstract: In recent years, the object-level saliency detection has attracted much research attention, due to its usefulness in many high-level tasks. Existing methods are mostly based on the contrast hypothesis, which regards the regions with high contrast in a certain context as salient objects. Although the contrast hypothesis is effective in many scenarios, it cannot handle some difficult cases. As a remedy to address the weakness of contrast hypothesis, we propose a novel compactness hypothesis, which assumes salient regions are more compact than background from the perspectives of both color layout and texture layout. Based on the compactness hypotheses, we implement an effective object-level saliency detection method. In the proposed method, we first construct a weak saliency map based on the compact hypotheses, then collect samples from the weak saliency map to train a dedicated classifier. This classifier is applied on each individual pixel of the input image to produce a confidence score. Finally, the confidence scores are used to form a saliency map. This process is carried out at different scales, and the corresponding results are integrated into the formation of the final saliency map. The proposed approach is evaluated on eight benchmark data sets, where it delivers the competitive performance compared with the state-of-the-art methods.
URI: http://localhost/handle/Hannan/168153
http://localhost/handle/Hannan/588782
ISSN: 1057-7149
1941-0042
volume: 25
issue: 10
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7523421.pdf7.39 MBAdobe PDFThumbnail
Preview File
Title: Detecting Salient Objects via Color and Texture Compactness Hypotheses
Authors: Ping Hu;Weiqiang Wang;Chi Zhang;Ke Lu
subject: saliency detection|compactness|Salient object
Year: 2016
Publisher: IEEE
Abstract: In recent years, the object-level saliency detection has attracted much research attention, due to its usefulness in many high-level tasks. Existing methods are mostly based on the contrast hypothesis, which regards the regions with high contrast in a certain context as salient objects. Although the contrast hypothesis is effective in many scenarios, it cannot handle some difficult cases. As a remedy to address the weakness of contrast hypothesis, we propose a novel compactness hypothesis, which assumes salient regions are more compact than background from the perspectives of both color layout and texture layout. Based on the compactness hypotheses, we implement an effective object-level saliency detection method. In the proposed method, we first construct a weak saliency map based on the compact hypotheses, then collect samples from the weak saliency map to train a dedicated classifier. This classifier is applied on each individual pixel of the input image to produce a confidence score. Finally, the confidence scores are used to form a saliency map. This process is carried out at different scales, and the corresponding results are integrated into the formation of the final saliency map. The proposed approach is evaluated on eight benchmark data sets, where it delivers the competitive performance compared with the state-of-the-art methods.
URI: http://localhost/handle/Hannan/168153
http://localhost/handle/Hannan/588782
ISSN: 1057-7149
1941-0042
volume: 25
issue: 10
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7523421.pdf7.39 MBAdobe PDFThumbnail
Preview File
Title: Detecting Salient Objects via Color and Texture Compactness Hypotheses
Authors: Ping Hu;Weiqiang Wang;Chi Zhang;Ke Lu
subject: saliency detection|compactness|Salient object
Year: 2016
Publisher: IEEE
Abstract: In recent years, the object-level saliency detection has attracted much research attention, due to its usefulness in many high-level tasks. Existing methods are mostly based on the contrast hypothesis, which regards the regions with high contrast in a certain context as salient objects. Although the contrast hypothesis is effective in many scenarios, it cannot handle some difficult cases. As a remedy to address the weakness of contrast hypothesis, we propose a novel compactness hypothesis, which assumes salient regions are more compact than background from the perspectives of both color layout and texture layout. Based on the compactness hypotheses, we implement an effective object-level saliency detection method. In the proposed method, we first construct a weak saliency map based on the compact hypotheses, then collect samples from the weak saliency map to train a dedicated classifier. This classifier is applied on each individual pixel of the input image to produce a confidence score. Finally, the confidence scores are used to form a saliency map. This process is carried out at different scales, and the corresponding results are integrated into the formation of the final saliency map. The proposed approach is evaluated on eight benchmark data sets, where it delivers the competitive performance compared with the state-of-the-art methods.
URI: http://localhost/handle/Hannan/168153
http://localhost/handle/Hannan/588782
ISSN: 1057-7149
1941-0042
volume: 25
issue: 10
Appears in Collections:2016

Files in This Item:
File Description SizeFormat 
7523421.pdf7.39 MBAdobe PDFThumbnail
Preview File