Semantic image segmentation using low-level features and contextual cues

Zhou, Chongbo; Liu, Chuancai

doi:10.1016/j.compeleceng.2013.04.017

Cited by 11 publications

(14 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The extracted features of an image are then mapped onto the corresponding representative bins, and finally, pixels in the same cluster constitute a region. These methods determine the number of clusters beforehand, or empirically by testing several values [33]. However, the consistency within and across different clusters cannot be guaranteed.…”

Section: Ontologymentioning

confidence: 99%

“…These techniques are the Layered object models [1], Contextual cues [33], [27], SvrSegm [57], HIM [58], DPG model [32], and Graphical model [31]. In MSRC-21, the classification accuracy for each class is measured by its pixel-wise classification accuracy.…”

Section: ) Datasetsmentioning

confidence: 99%

“…Boix et al [27] proposed a CRF model called harmony potential, which allowed multiple class labels to be assigned to a single node. In [33], the histogram representations of the superpixels and co-occurrence relations among object classes were used as local features and contextual cues in the CRF, respectively. However, although different characteristics from several sources can comprise complementary information and be potentially beneficial for enhancing performance, these methods do not take into account the individual importance of each feature.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs

Zand

Doraisamy

Halin

et al. 2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Semantic image segmentation is a fundamental yet challenging problem, which can be viewed as an extension of the conventional object detection with close relation to image segmentation and classification. It aims to partition images into non-overlapping regions that are assigned predefined semantic labels. Most of the existing approaches utilize and integrate low-level local features and high-level contextual cues, which are fed into an inference framework such as, the conditional random field (CRF). However, the lack of meaning in the primitives (i.e., pixels or superpixels) and the cues provides low discriminatory capabilities, since they are rarely object-consistent. Moreover, blind combinations of heterogeneous features and contextual cues exploitation through limited neighborhood relations in the CRFs tend to degrade the labeling performance. This paper proposes an ontology-based semantic image segmentation (OBSIS) approach that jointly models image segmentation and object detection. In particular, a Dirichlet process mixture model transforms the low-level visual space into an intermediate semantic space, which drastically reduces the feature dimensionality. These features are then individually weighed and independently learned within the context, using multiple CRFs. The segmentation of images into object parts is hence reduced to a classification task, where object inference is passed to an ontology model. This model resembles the way by which humans understand the images through the combination of different cues, context models, and rule-based learning of the ontologies. Experimental evaluations using the MSRC-21 and PASCAL VOC'2010 data sets show promising results.

show abstract

Section: Ontologymentioning

confidence: 99%

Section: ) Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Ontology-Based Semantic Image Segmentation Using Mixture Models and Multiple CRFs

Zand

Doraisamy

Halin

et al. 2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…) ( (8) where, 1  and 2  are the parameters that determine the crispness of the fuzzy membership degrees for distance relations and topological relations, respectively; 1  is the cut-off value that divides the distance relations into near and far fuzzy relations; 2  is the cut-off value that determines the surrounded by fuzzy relations. Finally, the concrete directional relations between objects can be determined by maximum membership principle:…”

Section: Fuzzy Spatial Relations Between Objectsmentioning

confidence: 99%

“…Recently, many researchers have attempted to improve the accuracy of image categorization by incorporating contextual information with object's appearance [2,3,4,5,6,7,8]. They have incorporated co-occurrence and spatial arrangement with appearance of local objects.…”

Section: Introductionmentioning

confidence: 99%

Contextual object categorisation with energy‐based model

Ri¹,

DuHo²,

Choe³

et al. 2017

J. eng.

View full text Add to dashboard Cite

：Object categorization is a hot issue of an image mining. Contextual information between objects is one of the important semantic knowledge of an image. However, the previous researches for an object categorization have not made full use of the contextual information, especially the spatial relations between objects. In addition, the object categorization methods, which generally use the probabilistic graphical models to implement the incorporation of contextual information with appearance of objects, are almost inevitable to evaluate the intractable partition function for normalization. In this work, we introduced fully-connected fuzzy spatial relations including directional, distance and topological relations between object regions, so the spatial relational information could be fully utilized. Then, the spatial relations were considered as well as co-occurrence and appearance of objects by using energy-based model, where the energy function was defined as the region-object association potential and the configuration potential of objects. Minimizing the energy function of whole image arrangement, we obtained the optimal label set about the image regions and addressed the evaluation of intractable partition function in conditional random fields. Experimental results show the validity and reliability of this proposed method.

show abstract