A compressive survey on different image processing techniques to identify the brain tumor

Abstract

Medical imaging technology has revolutionized health care over the past three decades allowing doctors to detect, cure and improve patient outcomes. Medicinal imaging makes picture of the internal organs, parts, tissues and bones for therapeutic examination and research pur-poses. It can likewise be utilized to think about elements of a few organs. X-ray and CT scanner are the two greatest after-effect of headway of imaging methods supplanting 2D procedures. X-ray is the standout amongst the most critical pre-processing ventures in tumor discovery. Magnetic resonance imaging (MRI) is really an imaging procedure in the restorative field. It is utilized as a part of radiology for imagining interior structures of the body and furthermore how they work. X-ray gives you the 3D picture of the inside bits of the body which enables the specialist to dissect the infection or tumor effortlessly though old imaging procedures like x-beam imaging gives you 2D pictures. In this paper we are introducing distinctive systems for distinguishing, preparing restorative pictures.

A bio‐inspired AlexNet‐DrpXLm architype for an effective brain stroke lesion detection and classification

“…To detect the abnormal brain images, the input images are trained and features are extracted depending on AlexNet [27][28][29] model. The last three layers of the AlexNet model are replaced with the dropout extreme learning machine (DrpXLM) [30][31][32][33] classifier to classify the images in efficient manner. Then the DrpXLM weight parameters are tuned with the help of improved dolphin swarm optimization (IDSO) 34 algorithm.…”

Facial emotion recognition using deep convolutional neural network and smoothing, mixture filters applied during preprocessing stage

“…Convolutional neural networks are not only for facial emotion recognition that we applied in the under described research, but also in several classifications such as human disease classification [11], [12], and plant disease classification [13]. Before deep CNN quite popular, the image classification uses a different machine learning algorithms and methods to classify in applications like brain tumor [14], [15], Plant disease [16], [17] and other [18], [19].…”

Convolutional Network based Animal Recognition using YOLO and Darknet

“…The pretrained version classifies images into object categories [13]. Darknet-53 is the foundation of Object detection and YOLO workflow [14]. Darknet-53 will give us 53 more layers has been added total of 106 layers are been consid er fo r Darknet-53 [15].…”