Image resolution enhancement by using interpolation followed by iterative back projection

Rasti, Pejman; Demirel, Hasan; Anbarjafari, Gholamreza

doi:10.1109/siu.2013.6531593

Cited by 26 publications

(12 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[2][3][4][5] The basic idea behind SR methods is to recover/estimate one or more high resolution (HR) image(s) from one or more low resolution (LR) images. 6,7 Huang and Tsai 8 as pioneers of SR proposed a method to improve the spatial resolution of satellite images of earth, where a large set of translated images of the same scene are available. They showed that SR, using multiple offset images of the same scene and a proper registration, can produce better HR images compared with spline interpolation.…”

Section: Introductionmentioning

confidence: 99%

Reducible dictionaries for single image super-resolution based on patch matching and mean shifting

Rasti

Nasrollahi

Orlova

et al. 2017

J. Electron. Imaging

View full text Add to dashboard Cite

Abstract. A single-image super-resolution (SR) method is proposed. The proposed method uses a generated dictionary from pairs of high resolution (HR) images and their corresponding low resolution (LR) representations. First, HR images and the corresponding LR ones are divided into patches of HR and LR, respectively, and then they are collected into separate dictionaries. Afterward, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary is calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary is passed through an illumination enhancement process. By this technique, the noticeable change of illumination between neighbor patches in the super-resolved image is significantly reduced. The enhanced HR patch represents the HR patch of the super-resolved image. Finally, to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image obtained using bicubic interpolation is calculated. The quantitative and qualitative analyses show the superiority of the proposed technique over the conventional and state-of-art methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Reducible dictionaries for single image super-resolution based on patch matching and mean shifting

Rasti

Nasrollahi

Orlova

et al. 2017

J. Electron. Imaging

View full text Add to dashboard Cite

show abstract

“…The main idea of using SVD in [2] for image equalization comes from this fact that Σ A contains the intensity information of the given image [15]. Wavelets have been used quite frequently as tools in many image processing applications such as feature extraction [16], compression [17], [18], face recognition [19], [20], image super resolution [2], [21], [22], and medical image enhancement [23]. The decomposition of images into different frequency ranges permits the isolation of the frequency components into certain subbands [24].…”

Section: Introductionmentioning

confidence: 99%

Medical image illumination enhancement and sharpening by using stationary wavelet transform

Rasti¹,

Daneshmand²,

Alisinanoglu³

et al. 2016

2016 24th Signal Processing and Communication Application Conference (SIU)

View full text Add to dashboard Cite

Özetçe -Çeşitli cihazlarla elde edilebilen tıbbi imgelerdeki ışıklandırma, hastanın tedavisinde kullanılan kimyasallardan dolayı farklılıklar gösterebilmektedir. Örnegin düşük kontrast veya çok parlak bir MRI imgesinin analizi düşük bilgi içerigi nedeniyle uzmanlar tarafından daha zor yapılacaktır. Bahsedilen bu probleme çözüm olabilmesi için bu makalede duragan dalgacık dönüşümü tabanlı yeni bir imge pekiştirme metodu önerilmektedir. Önerilen metod imge ışıklandırmasını pekiştirecek ve daha seçik imge elde edecektir. Önerilen metod, girdi imgesini duragan dalgacık dönüşümü kullanarak dört alt bölgeye ayırmaktadır. Ayrılan bölgelerdeki düşük-düşük alt bölge imgesinin ışıklandırması pekiştirilmektedir. Daha sonra yüksek frekanslı alt bölge imgesi girdi imgesine eklenerek ayrıt pekiştirilmesi yapılmaktadır. Bu metod, literatürde en gelişkin kontrast pekiştirme metodları olarak bilinen histogram eşitleme, yerel histogram eşitleme, tekil deger eşitleme, tekil deger ayrık dalgacık dönüşümü takiben tekil deger ayrıştırma metodlarıyla karşılaştırılmıştır. Deneysel sonuçlar önerilen metodun diger en gelişkin metodlara göre daha üstün oldugunu dogrulamaktadır.Anahtar Kelimeler-Tıbbi imge netleşme, kalıcı dalgacık dönüşümü, tıbbi imge işleme, tıbbi imge pekiştirme Abstract-Medical images captured by various devices have different illumination states based on chemicals used by patient prior to scanning. Consider a MRI image which has low contrast or is too bright, hence the experts cannot analysis that image due to poor representation of data in the image. In this paper we are proposing new medical image illumination enhancement and sharpening technique based on stationary wavelet transform which is addressing the aforementioned problem. The technique decomposes the input medical image into the four frequency subbands by using stationary wavelet transformation and enhances the illumination of the low-low subband image, and then it enhanced edges of image by adding the high frequency subbands to the image. The technique is compared with the conventional and state-of-art image illumination enhancement techniques such as histogram equalisation, local histogram equalisation, singular value equalisation, and discrete wavelet transform followed by singular value decomposition contrast enhancement techniques. The experimental results are showing the superiority of the proposed method over the conventional and the state-of-art techniques.

show abstract

“…For surveillance videos in real-world scenarios spatial domain approaches are more suitable as they can cope with the complicated motion structures of objects in the scene. These algorithms are generally divided into two groups: single-image-based and multipleimage-based super-resolution algorithms [1], [2].…”

Section: Introductionmentioning

confidence: 99%

Deep learning based super-resolution for improved action recognition

Nasrollahi

Escalera

Rasti

et al. 2015

2015 International Conference on Image Processing Theory, Tools and Applications (IPTA)

Self Cite

View full text Add to dashboard Cite

Action recognition systems mostly work with videos of proper quality and resolution. Even most challenging benchmark databases for action recognition, hardly include videos of low-resolution from, e.g., surveillance cameras. In videos recorded by such cameras, due to the distance between people and cameras, people are pictured very small and hence challenge action recognition algorithms. Simple upsampling methods, like bicubic interpolation, cannot retrieve all the detailed information that can help the recognition. To deal with this problem, in this paper we combine results of bicubic interpolation with results of a state-ofthe-art deep learning-based super-resolution algorithm, through an alpha-blending approach. The experimental results obtained on down-sampled version of a large subset of Hoolywood2 benchmark database show the importance of the proposed system in increasing the recognition rate of a state-of-the-art action recognition system for handling low-resolution videos.

show abstract

Image resolution enhancement by using interpolation followed by iterative back projection

Cited by 26 publications

References 23 publications

Reducible dictionaries for single image super-resolution based on patch matching and mean shifting

Reducible dictionaries for single image super-resolution based on patch matching and mean shifting

Medical image illumination enhancement and sharpening by using stationary wavelet transform

Deep learning based super-resolution for improved action recognition

Contact Info

Product

Resources

About