Recognition of elephants in infrared images using mean-shift segmentation

Object recognition is an important task in image processing and computer vision. This paper aims to include suitable segmentation, feature extraction and classification methods for elephant recognition. Mean-shift filtering is used for image segmentation and k-nn classifier is used for the object recognition based on the shape features of the segmented image. This approach of object recognition detects elephants that are single as well as in group of different sizes and poses performing different activities. The infrared elephant images are considered for experimentation. The database created by us for this type of object recognition includes elephant, bear, horse, pig, tiger, and cow and lion images. The recognition rate is calculated for performance evaluation. The results indicate that our approach is successful in elephant recognition.