Noise Reduction in Video Sequences The State of Art and the Technique for Motion Detection

Reeja, S. R.; Kavya, N

doi:10.5120/9304-3526

Cited by 8 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three stages are taken to extract the images from the edges. Finally, the vertical and horizontal directions of all transitions' edge maps were removed and concatenated [11] .…”

Section: Literature Reviewmentioning

confidence: 99%

Lung carcinoma prediction for computed tomography using deep learning

Yaseen¹

2023

Int. J. Eng. Comput. Sci.

View full text Add to dashboard Cite

Lung carcinoma is one of the most common diseases in the world. In India one of the most occurring disease is lung cancer and lot of people die due to the reason that it can only be cured during its initial stages. It is caused by the uncontrollable cell proliferation in lung tissues. It can be treated in Initial phase by seeking therapy is recommended. Only Computed Tomography (CT) scans and blood test results can detect this. The tumour is diagnosed by blood test after the humans have been affected for at least four years. As a result, CT scanning is utilised to determine the early stage of cancer. CT pictures are classed as normal or abnormal. Focusing on the tumour region reveals the aberrant image. The dataset is in jpg format and is made up of CT scans. The dataset is in jpg format and is made up of CT scans. This algorithm is used to process images. During training, image expansion method like zooming, linear fills, trimming, and rotation are used to sample, to improve classification success rates. Cancerous cells are discovered early by whenever the lungs provide oxygen to humans and expel carbon dioxide from the body as it plays a key role. Using various deep learning models, we can detect lung cancer. These deep learning models are employed across a wide range of datasets. We can achieve accurate findings by employing the image processing method. Because the AlexNet model was so successful, the model-derived characteristics are final used to fully connected layer, individually as feedback to the softmax layer. Both together yielded an accuracy of 99.52%.

show abstract

“…Three stages are taken to extract the images from the edges. Finally, the vertical and horizontal directions of all transitions' edge maps were removed and concatenated [11] .…”

Section: Literature Reviewmentioning

confidence: 99%