Filters








11 Hits in 2.3 sec

Exploiting Surroundedness for Saliency Detection: A Boolean Map Approach

Jianming Zhang, Stan Sclaroff
2016 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Exploiting surroundedness for saliency detection: a boolean map approach This work was made openly accessible by BU Faculty. Please share how this access benefits you. Your story matters.  ...  Abstract A novel Boolean Map based Saliency (BMS) model is proposed. An image is characterized by a set of binary images, which are generated by randomly thresholding the image's color channels.  ...  In this paper, we explore the surroundedness cue for saliency detection.  ... 
doi:10.1109/tpami.2015.2473844 pmid:26336114 fatcat:ra253jx625cuddlr4z7oakhjjm

Saliency Detection: A Boolean Map Approach

Jianming Zhang, Stan Sclaroff
2013 2013 IEEE International Conference on Computer Vision  
A novel Boolean Map based Saliency (BMS) model is proposed. An image is characterized by a set of binary images, which are generated by randomly thresholding the image's color channels.  ...  Based on a Gestalt principle of figure-ground segregation, BMS computes saliency maps by analyzing the topological structure of Boolean maps. BMS is simple to implement and efficient to run.  ...  In this paper, we explore the surroundedness cue for saliency detection.  ... 
doi:10.1109/iccv.2013.26 dblp:conf/iccv/ZhangS13 fatcat:ibjml6c6ovfjrm6qgypmi63z4y

Multi-Scale Cascade Network for Salient Object Detection

Xin Li, Fan Yang, Hong Cheng, Junyu Chen, Yuxiao Guo, Leiting Chen
2017 Proceedings of the 2017 ACM on Multimedia Conference - MM '17  
the saliency prior knowledge obtained from coarser stages and thus lead to better detection accuracy.  ...  Our network consists of several stages (sub-networks) for handling saliency detection across different scales.  ...  [37] explore the surroundedness cue for salient object detection through Boolean Maps computed by using image intensities.  ... 
doi:10.1145/3123266.3123290 dblp:conf/mm/LiYCCGC17 fatcat:ssbtm2omszeythyqkjed5p6ajq

Detecting Salient Image Objects Using Color Histogram Clustering for Region Granularity

Seena Joseph, Oludayo O. Olugbara
2021 Journal of Imaging  
Saliency detection is generally a complex process to copycat the human vision system in the processing of color images.  ...  However, the performances of the existing region-based salient object detection methods are extremely hooked on the selection of an optimal region granularity.  ...  Graph-Based Saliency Detection The bottom-up saliency detection methods based on graph structure have recently gained attention for object detection.  ... 
doi:10.3390/jimaging7090187 pmid:34564113 fatcat:zvr3qmmz2zbe5fleb6lzbcu5pq

Hierarchical Contour Closure-Based Holistic Salient Object Detection

Qing Liu, Xiaopeng Hong, Beiji Zou, Jie Chen, Zailiang Chen, Guoying Zhao
2017 IEEE Transactions on Image Processing  
Such fine-grained contrast based salient object detection methods are stuck with saliency attenuation of the salient object and saliency overestimation of the background when the image is complicated.  ...  To better compute the saliency for complicated images, we propose a hierarchical contour closure based holistic salient object detection method, in which two saliency cues, i.e., closure completeness and  ...  [34] proposed a convexity context based saliency model while Zhang et al. [35] explored the surroundedness cue and presented a Boolean map based saliency model.  ... 
doi:10.1109/tip.2017.2703081 pmid:28500000 fatcat:rxkjth3jqraqjcatmrzizzm6pe

Automatic Salient Object Detection for Panoramic Images Using Region Growing and Fixation Prediction Model [article]

Chunbiao Zhu, Kan Huang, Ge Li
2018 arXiv   pre-print
Finally, a refinement step based on geodesic distance is utilized for post-processing to derive the final saliency map.  ...  Almost all previous works on saliency detection have been dedicated to conventional images, however, with the outbreak of panoramic images due to the rapid development of VR or AR technology, it is becoming  ...  [17] proposed a model that combines multiscale low-level features to create a saliency map. Harel et al.  ... 
arXiv:1710.04071v6 fatcat:askeucd3vrhfdart3hyptwcloy

A Neurally Inspired Model of Figure Ground Organization with Local and Global Cues

Sudarshan Ramenahalli
2020 AI  
Model performance is evaluated based on figure-ground classification accuracy (FGCA) at every border location using the BSDS 300 figure-ground dataset.  ...  A biologically motivated, feed forward computational model of FGO incorporating convexity, surroundedness, parallelism as global cues and spectral anisotropy (SA), T-junctions as local cues is presented  ...  [63] propose a feed-forward model with Grouping and Border Ownership cells to study proto-object based saliency. Though the proposed model is inspired by this work, the goal of Russell et al.  ... 
doi:10.3390/ai1040028 fatcat:gpvzxkbl45csldptce7ynqgoou

A model of figure ground organization incorporating local and global cues [article]

Sudarshan Ramenahalli
2020 arXiv   pre-print
We evaluate model performance based on figure-ground classification accuracy (FGCA) at every border location using the BSDS 300 figure-ground dataset.  ...  We present a biologically motivated, feed forward computational model of FGO incorporating convexity, surroundedness, parallelism as global cues and Spectral Anisotropy (SA), T-junctions as local cues.  ...  [66] propose a feed-forward model with Grouping and Border Ownership cells to study proto-object based saliency. Though our model is inspired by this work, the goal of Russell et al.  ... 
arXiv:2003.06731v1 fatcat:photm6hmfvg5rcvl5kejyv3e5a

Prediction of Natural Image Saliency for Synthetic Images [article]

Ewa Rudak, Filip Rynkiewicz, Marcin Daszuta, Łukasz Struglewski
2021
This work shows that carefully chosen and integrated features, including a deep learning based one, can be used for saliency prediction. The integration is obtained by using Multiple Kernel Learning.  ...  Numerous saliency models are being developed with the use of neural networks and are capable of combining various features and predicting the saliency values with great results.  ...  The use of different scales means that multiscale feature extraction is possible.  ... 
doi:10.34658/9788366741102.11 fatcat:wur6cu4wanewffz26ss4kulwhm

How well can we predict where people look in images? [article]

Matthias Kümmerer, Universitaet Tuebingen, Bethge, Matthias (Prof. Dr.)
2020
metric-specific saliency maps that account for how the metric interprets the saliency maps.  ...  Here, we show that the underlying cause for the disagreement between saliency metrics is actually that they interpret saliency maps in highly different ways.  ...  Zhang J, Sclaroff S (2015) Exploiting surroundedness for saliency detection: A Boolean map approach. IEEE Trans Pattern Anal Mach Intell, in press. 37.  ... 
doi:10.15496/publikation-45488 fatcat:kz3xyoqy2zbxfeyrlgt7skqefi

TEWI 2021 [article]

Piotr Lipiński, Piotr Napieralski, Adam Wojciechowski
2021
The use of different scales means that multiscale feature extraction is possible.  ...  It is able to correctly detect conspicuous regions such as faces, text and animals and is rated as one of the best in the MIT saliency benchmark.  ...  The construction of information granules is based on certain criteria, such as spatial neighbourhood (e.g. superpixels), similarity or functionality.  ... 
doi:10.34658/9788366741102 fatcat:yyyfe62vwvcvpntxliidkoavri