Environmental Factor-Based Segmentation of Images in Natural Environments

The robust segmentation of color images in a natural environment without specific constraints such as lighting or background is very important in the field of image processing and computer vision. In this paper, an environmentally adaptive image segmentation method using color invariant is proposed. The proposed method introduces a number of color invariant, such as W, C, U, N, and H, and automatically detects factors in the surrounding environment in which images such as lighting, shading, and highlights are taken. The image is then effectively split based on the edge by selecting the color invariant optimal for the detected environmental factors. In the experiment, we implemented the proposed edge-based image segmentation algorithm. Various image data taken in general environments without specific constraints were utilized as input images of the suggested system. In this study, various kinds of color images taken in different environments were tested, and each color invariant was extracted from the experiments that best expressed the environmental changes around them. As a result, a largest number of images were determined to have a change in the intensity of lighting, followed by highlights and shadows. In addition, there were a few images that determined that no special state environmental changes existed. As the results of the experiment show visually, the existing method did not correctly remove shadows and did not detect some areas of the circular shape. In addition, the existing method can also be found to be partially inaccurate in edge detection in many areas. On the other hand, the proposed method confirmed stable segmentation of images. The proposed color invariant-based image segmentation algorithm is expected to be useful in various pattern recognition areas such as face tracking, mobile object detection, gesture recognition, motion understanding, etc.