Weakly Supervised Foreground Segmentation Based on Superpixel Grouping

Yu, Wei; Hou, Zhiqiang; Peng, Wang; Qin, Xianxiang; Wang, Liguang; Li, Huanyu

doi:10.1109/access.2018.2810210

Cited by 10 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Step 4: Check the convergence of log-likelihood in (23), and terminate the iterations if the convergence criterion is satisfactory.…”

Section: Image Clustering Using a Non-symmetric Gaussian-cauchy Mixtumentioning

confidence: 99%

“…By using an adaptive parameter of superpixel size, Zhu and Zhang [22] proposed a text segmentation method based on SLIC superpixel clustering. In [23], a weakly supervised image clustering method combining the watershed algorithm and mean shift clustering algorithm was proposed to obtain the objects of superpixel images. Ca et al [24] discussed the performance of SLIC followed by different CNNs, and recommended Inception-V3 [25] and Inception-V4 [26] for object detection specifically.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image clustering algorithm using superpixel segmentation and non‐symmetric Gaussian–Cauchy mixture model

Zhu

Wang

et al. 2020

IET image process

View full text Add to dashboard Cite

In this study, an unsupervised clustering algorithm is proposed to label superpixel density images. Firstly, the authors propose a novel superpixel segmentation algorithm driven by a modified fuzzy C-means objective function, Kullback-Leibler (KL) divergence, and an entropy term, which generate superpixels with good boundary adherence and intensity homogeneity. In this model, the logarithm of Gaussian distribution as a new distance metric is used to improve the accuracy of boundary pixel classification, the KL divergence is applied to regularise the fuzzy objective function. Based on this model, the generated superpixel intensity images with a highly distinctive background colour from the colour of the target are obtained. Grouping cues generated by superpixels can affect the performance of image clustering greatly. Next, according to the small amount of clustering data generated by the superpixel intensity images, they construct a non-symmetric mixture model based on a mixture of Gaussian distribution and Cauchy distribution for implementing image clustering. Thus, clustering of colour images is transformed into clustering of these newly generated data. The advantage of this model is its well adaption to different shapes of observed data. Experimental results on publicly available data sets are provided to demonstrate the effectiveness of the proposed algorithm. 12 IET Image Process.

show abstract

“…Step 4: Check the convergence of log-likelihood in (23), and terminate the iterations if the convergence criterion is satisfactory.…”

Section: Image Clustering Using a Non-symmetric Gaussian-cauchy Mixtumentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Image clustering algorithm using superpixel segmentation and non‐symmetric Gaussian–Cauchy mixture model

Zhu

Wang

et al. 2020

IET image process

View full text Add to dashboard Cite

show abstract

“…Image segmentation is fundamental to many computer vision tasks [19]- [22], and many image segmentation methods have be proposed in the past decade. Although their segmentation manners are different, they have the common step of generating object priors, which is the essential step for localizing the object regions [23] from the complicated backgrounds.…”

Section: B Bounding Box Based Segmentationmentioning

confidence: 99%

A New Deep Segmentation Quality Assessment Network for Refining Bounding Box Based Segmentation

Meng

Guo

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Capturing quality cues in blind segmentation quality assessment (SQA) is a challenging task. This paper proposes a new blind SQA method that captures a variety of quality cues using two considerations: one is to consider different types of data, such as segmentation mask and original image patch and the other is to consider different types of data operations, such as the max pooling operation, the average pooling operation, and the convolution operation. An end-to-end segmentation quality assessment network is proposed to capture these different types of quality cues by the above-mentioned two considerations. Then, since the segmentation result by the traditional bounding box-based segmentation method using fixed parameter setting is usually inaccurate, we use the proposed blind SQA network to refine the traditional bounding box-based segmentation results, with the idea of selecting parameters that are adaptive to each image. A two-step refinement method is proposed. The first step generates multiple segmentation results by various parameter settings. The second step, then, uses the segmentation quality assessment to select the best quality segmentation result as the new result. To train and verify the proposed method, a new dataset constructed by using the PASCAL VOC dataset and the bounding box-based segmentation methods, such as Grabcut and improved FCN method, is constructed. The proposed method is finally verified on the constructed dataset and two tasks: the segmentation quality assessment and the bounding box-based segmentation. The experimental results demonstrate the effectiveness of the proposed method. INDEX TERMS Segmentation quality assessment, bounding box based segmentation, grabcut, FCN.

show abstract

“…This work clusters the images based on colour and spatial relationship and the clusters are joined together to form superpixels. In [13], a weakly supervised foreground segmentation technique based on superpixel grouping is proposed. This paper extracts the foreground objects from the complex background based on a predefined bounding box.…”

Section: Review Of Literaturementioning

confidence: 99%

Automated Digital Image Clustering Algorithm Based on Colour Distance and IDBSCAN

Sangeetha*,

Velmani,

Rajakumar

2019

IJITEE

View full text Add to dashboard Cite

Data clustering is inevitable for crucial data analytic based applications. Though data clustering algorithms are capacious in the literature, there is always a room for efficient data clustering algorithms. This is due to the uncontrollable growth of data and its utilization. The data clustering may consider any of the data formats such as text, images, audio, video and so on. Due to the increasing utilization trend of digital images, this work intends to present a data clustering algorithm for digital images, which is based colour distance and Improvised DBSCAN (IDBSCAN) algorithm. The proposed IDBSCAN completely weeds out the annoying process of setting the initial parameters such as 𝜺 and 𝒎𝒊𝒏𝒑𝒕𝒔 by setting them automatically. The performance of the proposed work is analysed in terms of clustering accuracy, precision, recall, Fmeasure and time consumption rates. The proposed work outperforms the existing approaches with reasonable time consumption.

show abstract

Weakly Supervised Foreground Segmentation Based on Superpixel Grouping

Cited by 10 publications

References 23 publications

Image clustering algorithm using superpixel segmentation and non‐symmetric Gaussian–Cauchy mixture model

Image clustering algorithm using superpixel segmentation and non‐symmetric Gaussian–Cauchy mixture model

A New Deep Segmentation Quality Assessment Network for Refining Bounding Box Based Segmentation

Automated Digital Image Clustering Algorithm Based on Colour Distance and IDBSCAN

Contact Info

Product

Resources

About