Authors : D. Rasi and J. Suganthi
Abstract: This study proposes an enhanced Biotic Cross Pollination algorithm for visual based color image segmentation and object detection visual based color image segmentation and object detection. Here, the Global Biotic Cross Pollination Algorithm’s (GBCPA) performance is improvised with Evolutionary Strategy (ES) which exploits the structurally challenging objects based on color, texture, entropy and edge information in the Commission Internationale de l’Eclairage (CIE) L*a*b color space. The target objects are correlated by taking into consideration the knowledge of human perception based on Gestalt law with cognizance of signal characteristics in order to split natural scenes into visually unvarying regions. Hence, the object detection is performed with low computational complexity and without depending on a priori knowledge of the physically inspiring objects. The proposed color image segmentation algorithm is simulated using several test images and the results are compared with other proven image segmentation approaches reported in the literature. The test results demonstrate the superiority of the proposed segmentation algorithm in terms of segmentation and detection accuracy.
D. Rasi and J. Suganthi, 2016. A Visual Based Color Image Segmentation and Object Detection Algorithm Using an Enhanced Biotic Cross Pollination Algorithm. Asian Journal of Information Technology, 15: 406-417.