Supervised texture segmentation using 2D LSTM networks

Byeon, Wonmin; Breuel, Thomas M.

doi:10.1109/icip.2014.7025887

Cited by 9 publications

(8 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The projected centroid ( * +,-, 4 +,-) may belong to ℝ 5 , however, in the used datasets we only have color and disparity values for integer positions. To access these features from the projected centroid, the color and disparity values are obtained by rounding the coordinates to ensure integer indexing belonging to 5 . Notice that the normalized unrounded values of the position and disparity are used for clustering and clustering weights adaptation.…”

Section: B 4d Lf Pixels Labelingmentioning

confidence: 99%

See 1 more Smart Citation

ALFO: Adaptive Light Field Over-Segmentation

Hamad¹,

Conti

Nunes

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Automatic image over-segmentation into superpixels has attracted increasing attention from researchers to apply it as a pre-processing step for several computer vision applications. In 4D Light Field (LF) imaging, image over-segmentation aims at achieving not only superpixel compactness and accuracy but also cross-view consistency. Due to the high dimensionality of 4D LF images, depth information can be estimated and exploited during the over-segmentation along with spatial and visual appearance features. However, balancing between several hybrid features to generate robust superpixels for different 4D LF images is challenging and not adequately solved in existing solutions. In this paper, an automatic, adaptive, and view-consistent LF over-segmentation method based on normalized LF cues and K-means clustering is proposed. Initially, disparity maps for all LF views are estimated entirely to improve superpixel accuracy and consistency. Afterwards, by using K-means clustering, a 4D LF image is iteratively divided into regular superpixels that adhere to object boundaries and ensure cross-view consistency. Our proposed method can automatically adjust the clustering weights of the various features that characterize each superpixel based on the image content. Quantitative and qualitative results on several 4D LF datasets demonstrate outperforming performance of the proposed method in terms of superpixel accuracy, shape regularity and view consistency when using adaptive clustering weights, compared to the state-of-the-art 4D LF over-segmentation methods.INDEX TERMS Automatic segmentation, adaptive light field over-segmentation, superpixels.

show abstract

Section: B 4d Lf Pixels Labelingmentioning

confidence: 99%

“…Available image segmentation algorithms in the literature require different levels of supervision to suit different types of applications. These algorithms can be classified into supervised [5], semisupervised [6], and unsupervised (automatic) [7], [8], based on the need for pre-trained labels or human interactions.…”

Section: Introductionmentioning

confidence: 99%

ALFO: Adaptive Light Field Over-Segmentation

Hamad¹,

Conti

Nunes

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…A few works are reported that use LSTM based layers for image segmentation and related tasks. Byeon and Breuel (2014) improvements, brain tumor segmentation is still a challenging task.…”

Section: Literature Surveymentioning

confidence: 99%

Deep learning model integrating features and novel classifiers fusion for brain tumor segmentation

Iqbal

Khan

Saba

et al. 2019

Microscopy Res & Technique

View full text Add to dashboard Cite

Automatic and precise segmentation and classification of tumor area in medical images is still a challenging task in medical research. Most of the conventional neural network based models usefully connected or convolutional neural networks to perform segmentation and classification. In this research, we present deep learning models using long short term memory (LSTM) and convolutional neural networks (ConvNet) for accurate brain tumor delineation from benchmark medical images. The two different models, that is, ConvNet and LSTM networks are trained using the same data set and combined to form an ensemble to improve the results. We used publicly available MICCAI BRATS 2015 brain cancer data set consisting of MRI images of four modalities T1, T2, T1c, and FLAIR. To enhance the quality of input images, multiple combinations of preprocessing methods such as noise removal, histogram equalization, and edge enhancement are formulated and best performer combination is applied. To cope with the class imbalance problem, class weighting is used in proposed models. The trained models are tested on validation data set taken from the same image set and results obtained from each model are reported. The individual score (accuracy) of ConvNet is found 75% whereas for LSTM based network produced 80% and ensemble fusion produced 82.29% accuracy.

show abstract

“…However, even though many applications related to textures in computer vision involving deep learning deal with texture classification [ 54 , 55 , 56 , 57 , 58 , 59 , 60 , 61 , 62 ] and texture synthesis [ 63 , 64 , 65 ], only a few papers present deep learning techniques applied to texture segmentation. In [ 66 ], a two-dimensional long short-term memory (LSTM) network was proposed to classify each pixel of an image according to a predefined class, where the spatial recurrent behavior of the network made it possible to consider neighborhood contributions to the final decision. A convolutional neural network was used in [ 62 ] to segment image patches found by a region proposal algorithm through their classification.…”

Section: Introductionmentioning

confidence: 99%

A Class-Independent Texture-Separation Method Based on a Pixel-Wise Binary Classification

Soares

Côco

Ciarelli

et al. 2020

Sensors

View full text Add to dashboard Cite

Texture segmentation is a challenging problem in computer vision due to the subjective nature of textures, the variability in which they occur in images, their dependence on scale and illumination variation, and the lack of a precise definition in the literature. This paper proposes a method to segment textures through a binary pixel-wise classification, thereby without the need for a predefined number of textures classes. Using a convolutional neural network, with an encoder–decoder architecture, each pixel is classified as being inside an internal texture region or in a border between two different textures. The network is trained using the Prague Texture Segmentation Datagenerator and Benchmark and tested using the same dataset, besides the Brodatz textures dataset, and the Describable Texture Dataset. The method is also evaluated on the separation of regions in images from different applications, namely remote sensing images and H&E-stained tissue images. It is shown that the method has a good performance on different test sets, can precisely identify borders between texture regions and does not suffer from over-segmentation.

show abstract

Supervised texture segmentation using 2D LSTM networks

Cited by 9 publications

References 25 publications

ALFO: Adaptive Light Field Over-Segmentation

ALFO: Adaptive Light Field Over-Segmentation

Deep learning model integrating features and novel classifiers fusion for brain tumor segmentation

A Class-Independent Texture-Separation Method Based on a Pixel-Wise Binary Classification

Contact Info

Product

Resources

About