Image inpainting based on stacked autoencoders

Shcherbakov, Oleksandr; Batishcheva, Vita

doi:10.1088/1742-6596/536/1/012020

Cited by 12 publications

(11 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…5 At the same time, the generalizing capability of autoencoders has been used to solve the problem of predicting the contents in missing regions of images. 6 This once more indirectly confirms that attributes learned by autoencoders are suitable. The results of such testing, like the capability of a trained system to solve reconstruction problems, can actually be one of the criteria of the efficiency of the attributes discriminated by it.…”

Section: Model For Automatic Attribute Selectionmentioning

confidence: 57%

“…There are various approaches to solving the problem of restoring absent regions on images. [6][7][8] In this paper, we used an iterative algorithm, proposed in Ref. 6, to draw in missing segments of images.…”

Section: Experiments With Image Restoration In Missing Regionsmentioning

confidence: 99%

“…[6][7][8] In this paper, we used an iterative algorithm, proposed in Ref. 6, to draw in missing segments of images. Figures 4-6 show the results of restoring images with an absent region.…”

Section: Experiments With Image Restoration In Missing Regionsmentioning

confidence: 99%

See 2 more Smart Citations

A convolutional autoencoder as a generative model of images for problems of distinguishing attributes and restoring images in missing regions

2015

View full text Add to dashboard Cite

This paper discusses an approach to the description of the structure of models capable of being trained to recognize representations of items of generative models-in particular, the architecture of a convolutional autoencoder is considered in detail. Reliable qualitative results of the operation of a convolutional encoder are also presented that show that it is valid to regard this model as generative because it is possible to implement output and sampling procedures, using as an example the solution of the problem of restoring images in missing regions. URGENCYOne of the most important problems that need to be solved in order to construct the most efficient recognition systems is the problem of selecting the attributes of the object to be classified. In other words, it is necessary to select such a description of an object of interest to us that it retains the most general characteristics for the given class of objects and also eliminates all the superfluous, excess elements. In working with real-world objects, as a rule, the most widely used and at the same time informative input descriptions are various images of the objects themselves. However, an ordinary, pixelbased representation of the images of objects is not the most convenient from the viewpoint of the recognition problem, because it is impossible to adequately satisfy the conditions indicated above. It is accordingly required to solve the problem of transforming the original image into some other representation that would increase the recognition quality by comparison with the use of a "raw" pixel representation. 1 For many successful recognition systems, the given problem is currently solved by a person at the level of developing and selecting an appropriate image-processing algorithm that would distinguish one or the other global or local attributes on these images in accordance with criteria established, again by a person, even if it is sometimes less heuristic because the given criteria are based on fairly strict mathematical models. Many such attribute descriptions possess a certain stability with respect to a number of transformations over images, be they a brightness transformation, an affine transformation, a scale change, etc. Examples of such descriptions can now be standard popular key-point descriptors SIFT and SURF, as well as certain less known descriptors.However, from the viewpoint of machine training, there is special interest in models of attribute-selecting systems that would be capable of training to recognize these attributesi.e., they would be capable of independently distinguishing specific attributes on an image as a function of context, conditioned by a specific problem. A successful universal solution of the given problem would help one to substantially advance on the path of constructing completely automatic computer-vision systems and also possibly even improve the understanding of how biological visual systems function. MODEL FOR AUTOMATIC ATTRIBUTE SELECTIONA typical example of a model that solves the problem of automatic...

show abstract

Section: Model For Automatic Attribute Selectionmentioning

confidence: 57%

Section: Experiments With Image Restoration In Missing Regionsmentioning

confidence: 99%

See 1 more Smart Citation

A convolutional autoencoder as a generative model of images for problems of distinguishing attributes and restoring images in missing regions

2015

View full text Add to dashboard Cite

show abstract

“…Autoencoders have been used for de‐noising blurry images, as well as removing text or watermarks from images [28, 29], and has thus been established as a means of learning mappings from corrupted images to the original images.…”

Section: Theorymentioning

confidence: 99%

Deep convolutional neural network recovers pure absorbance spectra from highly scatter‐distorted spectra of cells

Magnussen

Solheim

Blazhko

et al. 2020

Journal of Biophotonics

View full text Add to dashboard Cite

Infrared spectroscopy of cells and tissues is prone to Mie scattering distortions, which grossly obscure the relevant chemical signals. The state-of-the-art Mie extinction extended multiplicative signal correction (ME-EMSC) algorithm is a powerful tool for the recovery of pure absorbance spectra from highly scatter-distorted spectra. However, the algorithm is computationally expensive and the correction of large infrared imaging datasets requires weeks of computations. In this paper, we present a deep convolutional descattering autoencoder (DSAE) which was trained on a set of ME-EMSC corrected infrared spectra and which can massively reduce the computation time for scatter correction. Since the raw spectra showed large variability in chemical features, different reference spectra matching the chemical signals of the spectra were used to initialize the ME-EMSC algorithm, which is beneficial for the quality of the correction and the speed of the algorithm. One DSAE was trained on the spectra, which were corrected with different reference spectra and validated on independent test data. The DSAE outperformed the ME-EMSC correction in terms of speed, robustness, and noise levels. We confirm that the same chemical information is contained in the DSAE corrected spectra as in the spectra corrected with ME-EMSC.

show abstract

“…Это было продемонстрировано в статье О. Щербакова и В. Батищева [6]. Главная особенность автоэнкодера заключается в том, что его входной слой соразмерен выходному, а скрытые слои имеют меньшую размерность, по-этому обучение может происходить без учителя.…”

Section: предложенный методunclassified