A parallel processing model for big medical image data

Wu, Minye; Zhou, Yang; Du, Zhikang; Wu, Xing

doi:10.1109/itaic.2014.7065048

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Parallel strategy is divided into data and model parallelisms [46]. As shown in FIGURE 1, data parallelism divides the data into multiple batches.…”

Section: B Parallel Strategymentioning

confidence: 99%

Parallel Region-Based Deep Residual Networks for Face Hallucination

et al. 2019

View full text Add to dashboard Cite

Face hallucination is a super-resolution algorithm specially designed to improve the resolution and quality of low-resolution (LR) input face images. Although a deep neural network offers an end-toend mapping from LR to high-resolution (HR) images, most of the deep learning-based face hallucinations neglect the structure prior for face images. To utilize the highly structured facial prior, a parallel regionbased deep residual network (PRDRN) was developed to predict the missing detailed information for accurate image reconstruction. Initially, the image is divided into multiple regions with the symmetry of face structures. Then, the sub-networks corresponding to multiple regions are trained in parallel. Finally, all reconstructed regions are combined to form the HR image. The experimental results on FEI, CASIA-Webface and CMU-MIT public face databases show that the proposed network outperforms other state-ofthe-art approaches.

show abstract

“…Parallel strategy is divided into data and model parallelisms [46]. As shown in FIGURE 1, data parallelism divides the data into multiple batches.…”

Section: B Parallel Strategymentioning

confidence: 99%

Parallel Region-Based Deep Residual Networks for Face Hallucination

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The work is lossless image encryption which can be implemented on medical images containing important information at large scale [3]. Parallel computing can provides great opportunity to handle medical images having large data by using a single processor with multiple cores [4]. Processing of these types of images that has large information and are big in size, results in wastage of time that can be overcome by parallelization of color components of images.…”

Section: Introductionmentioning

confidence: 99%

A Parallel Processing Technique Based on GMO and BCS for Medical Image Encryption

Singh*,

Singh,

Nath Rai

2020

IJITEE

View full text Add to dashboard Cite

Image encryption is a technique that provides security to an image and their data from unauthorized access in which there is the lightweight process (LWP) that can be parallelized resulting in the reduction of computation time. In this paper, parallel lossless image encryption, as well as the decryption technique, is proposed. The method is a parallel implementation of group modulo operation (GMO) based bit circular shift (BCS) of pixel bit-plane values. The backbone of this technique is circular bit rotation based on some modulo group key value. The key value used here is the result of group modulo operation. The binary bit values of pixels of the initial Image are rotated circularly to generate a new binary bit value of pixels encrypted image. The enhancement of this GMO and BCS based encryption are also given here by using the parallel implementation of the algorithm. The given results show the parallel implementation technique has the same level of encryption standard but has a better level of the time standard. As discussed in the result section, this technique can be used for medical image encryption as well as in multimedia applications where the transfer of image data is required over a network.

show abstract

“…For instance, stream processing is an approach to process big image without high demand of memory [1], but it can't reduce processing time. Parallel processing can reduce processing time but it needs multi-core CPUs and big memory [2].…”

Section: Introductionmentioning

confidence: 99%

Large area land cover mapping based on pyramid transformation with high-resolution PolSAR image

Zou

Sun

Jin

et al. 2016

2016 IEEE Radar Conference (RadarConf)

View full text Add to dashboard Cite

High-resolution PolSAR images are wildly used in land cover mapping. However, there are two problems when working with large areas, i.e., long processing time and large computer memory. Considering that properties of homogeneous area, such as forest, farm land, bare land, etc., are almost the same under different resolutions, which means that these areas can be processed in relatively low-resolution without decreasing mapping accuracy, this paper proposes a new land cover mapping method, to shorten processing time and reduce the demand of memory when high resolution images are used. In this method, relatively low-resolution images, used for homogeneous areas mapping, are obtained via pyramid transformation from the original image, due to the fact that pyramid transformation has good performance in retaining main information in the transformed images. The traditional pyramid transformation is adapted to PolSAR images. To verify the proposed method, iterated Freeman-Wishart classification is used based on pyramid transformation in this paper. Mapping accuracy and processing time of classification based on pyramid transformation and without pyramid transformation are compared. Experimental results show that processing time of classification based on pyramid transformation is reduced dramatically and the classification accuracy is improved.

show abstract

A parallel processing model for big medical image data

Cited by 3 publications

References 20 publications

Parallel Region-Based Deep Residual Networks for Face Hallucination

Parallel Region-Based Deep Residual Networks for Face Hallucination

A Parallel Processing Technique Based on GMO and BCS for Medical Image Encryption

Large area land cover mapping based on pyramid transformation with high-resolution PolSAR image

Contact Info

Product

Resources

About