CNN BASED IMAGE QUALITY IMPROVEMENT IN HAND HELD ULTRASOUND DEVICES

S.Ashlin lifty; R.Deepa

CNN BASED IMAGE QUALITY IMPROVEMENT IN HAND HELD ULTRASOUND DEVICES

Authors: S.Ashlin lifty, R.Deepa

Unique Paper ID: 153693
Volume: 8
Issue: 8
PageNo: 344-350

Keywords: Portable ultrasound device CNN Image quality improvement Median filter Histogram Equalisation Unsharp masking

Abstract:
Ultrasound technologies have grown popular in the medical field because they are more accurate, however the image quality of hand-held ultrasound devices is comparably low. The suggested method usesÂ Convolutional NeuralÂ NetworksÂ toÂ improveÂ theÂ image standard in handheld devices to high visuals. The suggested Convolutional Â NeuralÂ Networks Â to Â improveÂ the ImageÂ standard Â in Â handheld Â devices, leadingÂ toÂ High visuals. Through histogram equalization, the median filter is used to reduce undesired disturbance and to keep the details while maintaining a high dynamic range .Histogram equalisation approach is used to alter the dynamic valueÂ usingÂ itsÂ histogram.. It spreads out the most frequent pixel intensity values or stretches out the image's intensity range to improve the image contrast. Contrary to what its name suggests, unsharp masking is used to sharpen an image. Sharpening is important when post-processing most digital photos since it helps to emphasis detail. ToÂ accomplishÂ higherÂ resolution,Â aÂ ConvolutionalÂ NeuralÂ NetworkÂ isÂ oftenÂ used. CNN was created primarily to handle pixel data. It's a hierarchical model that builds a network, similar to a funnel, and then outputs a fully-connected layer where all the neurons are connected to one another and the output is processed. By employing CNN, it can provide more accurate training with high accuracy and produce a high-quality reconstruction image with fine details, structure, and speckle.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 8
Issue: 8
PageNo: 344-350

CNN BASED IMAGE QUALITY IMPROVEMENT IN HAND HELD ULTRASOUND DEVICES

Available:https://ijirt.org/Article?manuscript=153693

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now