Open Access

ARTICLE

Adaptive Image Enhancement Using Hybrid Particle Swarm Optimization and Watershed Segmentation

by

1Assistant Professor / CSE, Vivekanandha College of Engineering for Women, Tiruchengode, Namakkal-637 205, Tamilnadu, India.
2 Professor / CSE, K.S.R Institute for Engineering and Technology, Tiruchengode, Namakkal-637 215, Tamilnadu, India.

* Corresponding Author: N. Mohanapriya,

Intelligent Automation & Soft Computing 2019, 25(4), 663-672. https://doi.org/10.31209/2018.100000041

Abstract

Medical images are obtained straight from the medical acquisition devices so that, the image quality becomes poor and may contain noises. Low contrast and poor quality are the major issues in the production of medical images. Medical imaging enhancement technology gives way to solve these issues; it helps the doctors to see the interior portions of the body for early diagnosis, also it improves the features the visual aspects of an image for a right diagnosis. This paper proposes a new blend of Particle Swarm Optimization (PSO) and Accelerated Particle Swarm Optimization (APSO) called Hybrid Partial Swarm Optimization (HPSO) to enhance medical images and also gives optimal results. The work starts with (i) watershed segmentation followed by (ii) HPSO enhancement algorithm. The watershed segmentation is a morphological gradient-based transformation technique. The gradient map of an image has different gradient values corresponds to different heights. It extracts the continuous boundaries of each region to give solid results and intuitively provides better performance on noisy images. After segmentation, the HPSO algorithm is applied to improve the quality of Computed Tomography (CT) images by calculating the local and global information. The transformation function uses the calculated information to optimize the medical image. The algorithm is tested on a real time data set of CT images, which were collected from MIT-BIH dataset and the performance is analyzed and compared with existing Region Merging (RM), Fuzzy C Means (FCM), Histogram Thresholding, Discrete Wavelet Transformation (DWT), Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Histogram Equalization (HE), Contrast Stretching and Adaptive Filtering based on PSNR, SSIM, CII, MSE, RMSE, BER and Execution time parameters. The experimental result shows that the proposed medical image enhancement algorithm achieves 96.7% accuracy and defeat the over segmentation problem of existing systems.

---

Keywords

---