Enhancement in Brain Image Segmentation using Swarm Ant Lion Algorithm
Sonali Bansal1, Shubpreet Kaur2, Navdeep Kaur3

1Sonali Bansal, Departmet of CEC, CGC, Landran,Mohali, India. Dr.
Shubpreet Kaur, Departmet of CEC, CGC, Landran,Mohali, India.
3Navdeep Kaur, Departmet of CEC, CGC, Landran, Mohali,India.
Manuscript received on 02 July 2019 | Revised Manuscript received on 09 July 2019 | Manuscript published on 30 August 2019 | PP: 1623-1628 | Volume-8 Issue-10, August 2019 | Retrieval Number: J88270881019/2019©BEIESP | DOI: 10.35940/ijitee.J8827.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Brain tumor image segmentation is a play a vital role in the medical field or medical processing. Patient treatment with brain tumors is the significant level determine on early-stage detection of these tumors. Early stage detection of Brain Tumors will enhance the patient lives. The disease of brain tumors by a neurologist frequently uses a manual image segmentation that is a hard and time-consuming process, because of necessary automatic image segmentation. Nowadays, automatic image segmentation is very popular and can solve the issue of tumor brain image segmentation with better performance. The main motive of this research work is to provide a survey of MRI image based brain tumor segmentation techniques. There are various existing study papers, focusing on new techniques for Reasonable Magnetic Image-based brain tumor image segmentation. The main problem is considered a complicated process, because of the variability of tumor area of the complexity of determining the tumor position, size, shape and texture. In this research work, mainly worked on interference method, feature extraction, morphological operators, edge detection methods of gray level and Swarm Ant Lion Optimization based on brain tumor shape growing segmentation to optimize the image complexity and enhance the performance. In new algorithm implemented an inspiring nature method for segmentation of brain tumor image using hybridization of PSOA and ALO is also called a Swarm Ant Lion method. Evaluate the performance metrics with image quality factor (PSNR), Error Rate (MSE), and Exact value (Accuracy Rate). In research work, improve the performance metrics with PSNR and Accuracy Rate and reduce the error rates and compared with the existing method (PNN).
Keywords: Brain Image Segmentation, Probabilistic Neural Network, Ant Lion and Particle Swarm Optimization method.
Scope of the Article: Image Processing and Pattern Recognition